--- base_model: Snowflake/snowflake-arctic-embed-m library_name: sentence-transformers metrics: - cosine_accuracy@1 - cosine_accuracy@3 - cosine_accuracy@5 - cosine_accuracy@10 - cosine_precision@1 - cosine_precision@3 - cosine_precision@5 - cosine_precision@10 - cosine_recall@1 - cosine_recall@3 - cosine_recall@5 - cosine_recall@10 - cosine_ndcg@10 - cosine_mrr@10 - cosine_map@100 - dot_accuracy@1 - dot_accuracy@3 - dot_accuracy@5 - dot_accuracy@10 - dot_precision@1 - dot_precision@3 - dot_precision@5 - dot_precision@10 - dot_recall@1 - dot_recall@3 - dot_recall@5 - dot_recall@10 - dot_ndcg@10 - dot_mrr@10 - dot_map@100 pipeline_tag: sentence-similarity tags: - sentence-transformers - sentence-similarity - feature-extraction - generated_from_trainer - dataset_size:363 - loss:MatryoshkaLoss - loss:MultipleNegativesRankingLoss widget: - source_sentence: What are some examples of algorithmic discrimination mentioned in the context, and how do they impact different areas such as hiring and healthcare? sentences: - "For example, facial recognition technology that can contribute to wrongful and\ \ discriminatory \narrests,31 hiring algorithms that inform discriminatory decisions,\ \ and healthcare algorithms that discount \nthe severity of certain diseases in\ \ Black Americans. Instances of discriminatory practices built into and \nresulting\ \ from AI and other automated systems exist across many industries, areas, and\ \ contexts. While automated \nsystems have the capacity to drive extraordinary\ \ advances and innovations, algorithmic discrimination \nprotections should be\ \ built into their design, deployment, and ongoing use. Many companies, non-profits,\ \ and federal government agencies are already taking steps to ensure the public\ \ \nis protected from algorithmic discrimination. Some companies have instituted\ \ bias testing as part of their product \nquality assessment and launch procedures,\ \ and in some cases this testing has led products to be changed or not \nlaunched,\ \ preventing harm to the public. Federal government agencies have been developing\ \ standards and guidance \nfor the use of automated systems in order to help prevent\ \ bias. Non-profits and companies have developed best \npractices for audits and\ \ impact assessments to help identify potential algorithmic discrimination and\ \ provide \ntransparency to the public in the mitigation of such biases. But there\ \ is much more work to do to protect the public from algorithmic discrimination\ \ to use and design \nautomated systems in an equitable way. The guardrails protecting\ \ the public from discrimination in their daily \nlives should include their digital\ \ lives and impacts—basic safeguards against abuse, bias, and discrimination to\ \ \nensure that all people are treated fairly when automated systems are used.\ \ This includes all dimensions of their \nlives, from hiring to loan approvals,\ \ from medical treatment and payment to encounters with the criminal \njustice\ \ system. Ensuring equity should also go beyond existing guardrails to consider\ \ the holistic impact that \nautomated systems make on underserved communities\ \ and to institute proactive protections that support these \ncommunities. •\n\ An automated system using nontraditional factors such as educational attainment\ \ and employment history as\npart of its loan underwriting and pricing model was\ \ found to be much more likely to charge an applicant who\nattended a Historically\ \ Black College or University (HBCU) higher loan prices for refinancing a student\ \ loan\nthan an applicant who did not attend an HBCU. This was found to be true\ \ even when controlling for\nother credit-related factors.32\n•\nA hiring tool\ \ that learned the features of a company's employees (predominantly men) rejected\ \ women appli­\ncants for spurious and discriminatory reasons; resumes with the\ \ word “women’s,” such as “women’s\nchess club captain,” were penalized in the\ \ candidate ranking.33\n•\nA predictive model marketed as being able to predict\ \ whether students are likely to drop out of school was\nused by more than 500\ \ universities across the country. The model was found to use race directly as\ \ a predictor,\nand also shown to have large disparities by race; Black students\ \ were as many as four times as likely as their\notherwise similar white peers\ \ to be deemed at high risk of dropping out. These risk scores are used by advisors\ \ \nto guide students towards or away from majors, and some worry that they are\ \ being used to guide\nBlack students away from math and science subjects.34\n\ •\nA risk assessment tool designed to predict the risk of recidivism for individuals\ \ in federal custody showed\nevidence of disparity in prediction. The tool overpredicts\ \ the risk of recidivism for some groups of color on the\ngeneral recidivism tools,\ \ and underpredicts the risk of recidivism for some groups of color on some of\ \ the\nviolent recidivism tools. The Department of Justice is working to reduce\ \ these disparities and has\npublicly released a report detailing its review of\ \ the tool.35 \n24\n" - "SECTION: APPENDIX: EXAMPLES OF AUTOMATED SYSTEMS\nAPPENDIX\nSystems that impact\ \ the safety of communities such as automated traffic control systems, elec \n\ -ctrical grid controls, smart city technologies, and industrial emissions and\ \ environmental\nimpact control algorithms; and\nSystems related to access to\ \ benefits or services or assignment of penalties such as systems that\nsupport\ \ decision-makers who adjudicate benefits such as collating or analyzing information\ \ or\nmatching records, systems which similarly assist in the adjudication of\ \ administrative or criminal\npenalties, fraud detection algorithms, services\ \ or benefits access control algorithms, biometric\nsystems used as access control,\ \ and systems which make benefits or services related decisions on a\nfully or\ \ partially autonomous basis (such as a determination to revoke benefits). 54\n" - "SECTION: SAFE AND EFFECTIVE SYSTEMS\n \n \n \n \n \n \n \nSAFE AND EFFECTIVE\ \ \nSYSTEMS \nWHAT SHOULD BE EXPECTED OF AUTOMATED SYSTEMS\nThe expectations for\ \ automated systems are meant to serve as a blueprint for the development of additional\ \ \ntechnical standards and practices that are tailored for particular sectors\ \ and contexts. In order to ensure that an automated system is safe and effective,\ \ it should include safeguards to protect the \npublic from harm in a proactive\ \ and ongoing manner; avoid use of data inappropriate for or irrelevant to the\ \ task \nat hand, including reuse that could cause compounded harm; and demonstrate\ \ the safety and effectiveness of \nthe system. These expectations are explained\ \ below. Protect the public from harm in a proactive and ongoing manner \nConsultation.\ \ The public should be consulted in the design, implementation, deployment, acquisition,\ \ and \nmaintenance phases of automated system development, with emphasis on early-stage\ \ consultation before a \nsystem is introduced or a large change implemented.\ \ This consultation should directly engage diverse impact­\ned communities to\ \ consider concerns and risks that may be unique to those communities, or disproportionate­\n\ ly prevalent or severe for them. The extent of this engagement and the form of\ \ outreach to relevant stakehold­\ners may differ depending on the specific automated\ \ system and development phase, but should include \nsubject matter, sector-specific,\ \ and context-specific experts as well as experts on potential impacts such as\ \ \ncivil rights, civil liberties, and privacy experts. For private sector applications,\ \ consultations before product \nlaunch may need to be confidential. Government\ \ applications, particularly law enforcement applications or \napplications that\ \ raise national security considerations, may require confidential or limited\ \ engagement based \non system sensitivities and preexisting oversight laws and\ \ structures. Concerns raised in this consultation \nshould be documented, and\ \ the automated system developers were proposing to create, use, or deploy should\ \ \nbe reconsidered based on this feedback." - source_sentence: What are some key needs identified by panelists for the future design of critical AI systems? sentences: - "It included discussion of the \ntechnical aspects \nof \ndesigning \nnon-discriminatory\ \ \ntechnology, \nexplainable \nAI, \nhuman-computer \ninteraction with an emphasis\ \ on community participation, and privacy-aware design. Welcome:\n•\nSorelle Friedler,\ \ Assistant Director for Data and Democracy, White House Office of Science and\n\ Technology Policy\n•\nJ. Bob Alotta, Vice President for Global Programs, Mozilla\ \ Foundation\n•\nNavrina Singh, Board Member, Mozilla Foundation\nModerator: Kathy\ \ Pham Evans, Deputy Chief Technology Officer for Product and Engineering, U.S\ \ \nFederal Trade Commission. Panelists: \n•\nLiz O’Sullivan, CEO, Parity AI\n\ •\nTimnit Gebru, Independent Scholar\n•\nJennifer Wortman Vaughan, Senior Principal\ \ Researcher, Microsoft Research, New York City\n•\nPamela Wisniewski, Associate\ \ Professor of Computer Science, University of Central Florida; Director,\nSocio-technical\ \ Interaction Research (STIR) Lab\n•\nSeny Kamara, Associate Professor of Computer\ \ Science, Brown University\nEach panelist individually emphasized the risks of\ \ using AI in high-stakes settings, including the potential for \nbiased data\ \ and discriminatory outcomes, opaque decision-making processes, and lack of public\ \ trust and \nunderstanding of the algorithmic systems. The interventions and\ \ key needs various panelists put forward as \nnecessary to the future design\ \ of critical AI systems included ongoing transparency, value sensitive and \n\ participatory design, explanations designed for relevant stakeholders, and public\ \ consultation. Various \npanelists emphasized the importance of placing trust\ \ in people, not technologies, and in engaging with \nimpacted communities to\ \ understand the potential harms of technologies and build protection by design\ \ into \nfuture systems. Panel 5: Social Welfare and Development. This event explored\ \ current and emerging uses of technology to \nimplement or improve social welfare\ \ systems, social development programs, and other systems that can impact \nlife\ \ chances. Welcome:\n•\nSuresh Venkatasubramanian, Assistant Director for Science\ \ and Justice, White House Office of Science\nand Technology Policy\n•\nAnne-Marie\ \ Slaughter, CEO, New America\nModerator: Michele Evermore, Deputy Director for\ \ Policy, Office of Unemployment Insurance \nModernization, Office of the Secretary,\ \ Department of Labor \nPanelists:\n•\nBlake Hall, CEO and Founder, ID.Me\n•\n\ Karrie Karahalios, Professor of Computer Science, University of Illinois, Urbana-Champaign\n\ •\nChristiaan van Veen, Director of Digital Welfare State and Human Rights Project,\ \ NYU School of Law's\nCenter for Human Rights and Global Justice\n58\n" - '20, 2021. https://www.vice.com/en/article/88npjv/amazons-ai-cameras-are-punishing­ drivers-for-mistakes-they-didnt-make 63 ' - 'Jan. 11, 2022. https://themarkup.org/machine-learning/2022/01/11/this-private-equity-firm-is-amassing-companies­ that-collect-data-on-americas-children 77. Reed Albergotti. Every employee who leaves Apple becomes an ‘associate’: In job databases used by employers to verify resume information, every former Apple employee’s title gets erased and replaced with a generic title. The Washington Post.' - source_sentence: How do automated identity controls at airports ensure assistance for individuals facing misidentification? sentences: - "SECTION: ALGORITHMIC DISCRIMINATION PROTECTIONS\n ­­­­­­­\nALGORITHMIC DISCRIMINATION\ \ Protections\nYou should not face discrimination by algorithms \nand systems\ \ should be used and designed in an \nequitable \nway. Algorithmic \ndiscrimination\ \ \noccurs when \nautomated systems contribute to unjustified different treatment\ \ or \nimpacts disfavoring people based on their race, color, ethnicity, \nsex\ \ \n(including \npregnancy, \nchildbirth, \nand \nrelated \nmedical \nconditions,\ \ \ngender \nidentity, \nintersex \nstatus, \nand \nsexual \norientation), religion,\ \ age, national origin, disability, veteran status, \ngenetic infor-mation, or\ \ any other classification protected by law. Depending on the specific circumstances,\ \ such algorithmic \ndiscrimination may violate legal protections. Designers,\ \ developers, \nand deployers of automated systems should take proactive and \n\ continuous measures to protect individuals and communities \nfrom algorithmic\ \ discrimination and to use and design systems in \nan equitable way. This protection\ \ should include proactive equity \nassessments as part of the system design,\ \ use of representative data \nand protection against proxies for demographic\ \ features, ensuring \naccessibility for people with disabilities in design and\ \ development, \npre-deployment and ongoing disparity testing and mitigation,\ \ and \nclear organizational oversight. Independent evaluation and plain \nlanguage\ \ reporting in the form of an algorithmic impact assessment, \nincluding disparity\ \ testing results and mitigation information, \nshould be performed and made public\ \ whenever possible to confirm \nthese protections." - "These critical protections have been adopted in some scenarios. Where automated\ \ systems have been introduced to \nprovide the public access to government benefits,\ \ existing human paper and phone-based processes are generally still \nin place,\ \ providing an important alternative to ensure access. Companies that have introduced\ \ automated call centers \noften retain the option of dialing zero to reach an\ \ operator. When automated identity controls are in place to board an \nairplane\ \ or enter the country, there is a person supervising the systems who can be turned\ \ to for help or to appeal a \nmisidentification. The American people deserve\ \ the reassurance that such procedures are in place to protect their rights, opportunities,\ \ \nand access." - "SECTION: APPENDIX: EXAMPLES OF AUTOMATED SYSTEMS\nAPPENDIX\nSystems that impact\ \ the safety of communities such as automated traffic control systems, elec \n\ -ctrical grid controls, smart city technologies, and industrial emissions and\ \ environmental\nimpact control algorithms; and\nSystems related to access to\ \ benefits or services or assignment of penalties such as systems that\nsupport\ \ decision-makers who adjudicate benefits such as collating or analyzing information\ \ or\nmatching records, systems which similarly assist in the adjudication of\ \ administrative or criminal\npenalties, fraud detection algorithms, services\ \ or benefits access control algorithms, biometric\nsystems used as access control,\ \ and systems which make benefits or services related decisions on a\nfully or\ \ partially autonomous basis (such as a determination to revoke benefits). 54\n" - source_sentence: How should the availability of human consideration and fallback mechanisms be determined in relation to the potential impact of automated systems on rights, opportunities, or access? sentences: - "In many scenarios, there is a reasonable expectation \nof human involvement in\ \ attaining rights, opportunities, or access. When automated systems make up part\ \ of \nthe attainment process, alternative timely human-driven processes should\ \ be provided. The use of a human \nalternative should be triggered by an opt-out\ \ process. Timely and not burdensome human alternative. Opting out should be timely\ \ and not unreasonably \nburdensome in both the process of requesting to opt-out\ \ and the human-driven alternative provided. Provide timely human consideration\ \ and remedy by a fallback and escalation system in the \nevent that an automated\ \ system fails, produces error, or you would like to appeal or con­\ntest its\ \ impacts on you \nProportionate. The availability of human consideration and\ \ fallback, along with associated training and \nsafeguards against human bias,\ \ should be proportionate to the potential of the automated system to meaning­\n\ fully impact rights, opportunities, or access. Automated systems that have greater\ \ control over outcomes, \nprovide input to high-stakes decisions, relate to sensitive\ \ domains, or otherwise have a greater potential to \nmeaningfully impact rights,\ \ opportunities, or access should have greater availability (e.g., staffing) and\ \ over­\nsight of human consideration and fallback mechanisms. Accessible. Mechanisms\ \ for human consideration and fallback, whether in-person, on paper, by phone,\ \ or \notherwise provided, should be easy to find and use. These mechanisms should\ \ be tested to ensure that users \nwho have trouble with the automated system\ \ are able to use human consideration and fallback, with the under­\nstanding\ \ that it may be these users who are most likely to need the human assistance.\ \ Similarly, it should be \ntested to ensure that users with disabilities are\ \ able to find and use human consideration and fallback and also \nrequest reasonable\ \ accommodations or modifications. Convenient. Mechanisms for human consideration\ \ and fallback should not be unreasonably burdensome as \ncompared to the automated\ \ system’s equivalent. 49\n" - "SECTION: DATA PRIVACY\n \n \n \n \n \n \nDATA PRIVACY \nWHAT SHOULD BE EXPECTED\ \ OF AUTOMATED SYSTEMS\nThe expectations for automated systems are meant to serve\ \ as a blueprint for the development of additional \ntechnical standards and practices\ \ that are tailored for particular sectors and contexts. Data access and correction.\ \ People whose data is collected, used, shared, or stored by automated \nsystems\ \ should be able to access data and metadata about themselves, know who has access\ \ to this data, and \nbe able to correct it if necessary. Entities should receive\ \ consent before sharing data with other entities and \nshould keep records of\ \ what data is shared and with whom. Consent withdrawal and data deletion. Entities\ \ should allow (to the extent legally permissible) with­\ndrawal of data access\ \ consent, resulting in the deletion of user data, metadata, and the timely removal\ \ of \ntheir data from any systems (e.g., machine learning models) derived from\ \ that data.68\nAutomated system support. Entities designing, developing, and\ \ deploying automated systems should \nestablish and maintain the capabilities\ \ that will allow individuals to use their own automated systems to help \nthem\ \ make consent, access, and control decisions in a complex data ecosystem. Capabilities\ \ include machine \nreadable data, standardized data formats, metadata or tags\ \ for expressing data processing permissions and \npreferences and data provenance\ \ and lineage, context of use and access-specific tags, and training models for\ \ \nassessing privacy risk. Demonstrate that data privacy and user control are\ \ protected \nIndependent evaluation. As described in the section on Safe and\ \ Effective Systems, entities should allow \nindependent evaluation of the claims\ \ made regarding data policies. These independent evaluations should be \nmade\ \ public whenever possible. Care will need to be taken to balance individual privacy\ \ with evaluation data \naccess needs." - "SECTION: NOTICE AND EXPLANATION\n \n \n \n \n \nNOTICE & \nEXPLANATION \nWHY\ \ THIS PRINCIPLE IS IMPORTANT\nThis section provides a brief summary of the problems\ \ which the principle seeks to address and protect \nagainst, including illustrative\ \ examples. •\nA predictive policing system claimed to identify individuals at\ \ greatest risk to commit or become the victim of\ngun violence (based on automated\ \ analysis of social ties to gang members, criminal histories, previous experi­\n\ ences of gun violence, and other factors) and led to individuals being placed\ \ on a watch list with no\nexplanation or public transparency regarding how the\ \ system came to its conclusions.85 Both police and\nthe public deserve to understand\ \ why and how such a system is making these determinations. •\nA system awarding\ \ benefits changed its criteria invisibly." - source_sentence: What topics were discussed during the meetings related to the development of the Blueprint for an AI Bill of Rights? sentences: - " \nGAI systems can produce content that is inciting, radicalizing, or threatening,\ \ or that glorifies violence, \nwith greater ease and scale than other technologies.\ \ LLMs have been reported to generate dangerous or \nviolent recommendations,\ \ and some models have generated actionable instructions for dangerous or \n \n\ \ \n9 Confabulations of falsehoods are most commonly a problem for text-based\ \ outputs; for audio, image, or video \ncontent, creative generation of non-factual\ \ content can be a desired behavior. 10 For example, legal confabulations have\ \ been shown to be pervasive in current state-of-the-art LLMs. See also, \ne.g.,\ \ \n \n7 \nunethical behavior." - 'SECTION: LISTENING TO THE AMERICAN PEOPLE APPENDIX • OSTP conducted meetings with a variety of stakeholders in the private sector and civil society. Some of these meetings were specifically focused on providing ideas related to the development of the Blueprint for an AI Bill of Rights while others provided useful general context on the positive use cases, potential harms, and/or oversight possibilities for these technologies.' - "Transgender travelers have described degrading experiences associated\nwith these\ \ extra screenings.43 TSA has recently announced plans to implement a gender-neutral\ \ algorithm44 \nwhile simultaneously enhancing the security effectiveness capabilities\ \ of the existing technology. •\nThe National Disabled Law Students Association\ \ expressed concerns that individuals with disabilities were\nmore likely to be\ \ flagged as potentially suspicious by remote proctoring AI systems because of\ \ their disabili-\nty-specific access needs such as needing longer breaks or using\ \ screen readers or dictation software.45 \n•\nAn algorithm designed to identify\ \ patients with high needs for healthcare systematically assigned lower\nscores\ \ (indicating that they were not as high need) to Black patients than to those\ \ of white patients, even\nwhen those patients had similar numbers of chronic\ \ conditions and other markers of health.46 In addition,\nhealthcare clinical\ \ algorithms that are used by physicians to guide clinical decisions may include\n\ sociodemographic variables that adjust or “correct” the algorithm’s output on\ \ the basis of a patient’s race or\nethnicity, which can lead to race-based health\ \ inequities.47\n25\nAlgorithmic \nDiscrimination \nProtections \n" model-index: - name: SentenceTransformer based on Snowflake/snowflake-arctic-embed-m results: - task: type: information-retrieval name: Information Retrieval dataset: name: Unknown type: unknown metrics: - type: cosine_accuracy@1 value: 0.7608695652173914 name: Cosine Accuracy@1 - type: cosine_accuracy@3 value: 0.8695652173913043 name: Cosine Accuracy@3 - type: cosine_accuracy@5 value: 0.9130434782608695 name: Cosine Accuracy@5 - type: cosine_accuracy@10 value: 0.9782608695652174 name: Cosine Accuracy@10 - type: cosine_precision@1 value: 0.7608695652173914 name: Cosine Precision@1 - type: cosine_precision@3 value: 0.2898550724637682 name: Cosine Precision@3 - type: cosine_precision@5 value: 0.18260869565217389 name: Cosine Precision@5 - type: cosine_precision@10 value: 0.0978260869565217 name: Cosine Precision@10 - type: cosine_recall@1 value: 0.7608695652173914 name: Cosine Recall@1 - type: cosine_recall@3 value: 0.8695652173913043 name: Cosine Recall@3 - type: cosine_recall@5 value: 0.9130434782608695 name: Cosine Recall@5 - type: cosine_recall@10 value: 0.9782608695652174 name: Cosine Recall@10 - type: cosine_ndcg@10 value: 0.8567216523715442 name: Cosine Ndcg@10 - type: cosine_mrr@10 value: 0.8190217391304349 name: Cosine Mrr@10 - type: cosine_map@100 value: 0.8203804347826088 name: Cosine Map@100 - type: dot_accuracy@1 value: 0.7608695652173914 name: Dot Accuracy@1 - type: dot_accuracy@3 value: 0.8695652173913043 name: Dot Accuracy@3 - type: dot_accuracy@5 value: 0.9130434782608695 name: Dot Accuracy@5 - type: dot_accuracy@10 value: 0.9782608695652174 name: Dot Accuracy@10 - type: dot_precision@1 value: 0.7608695652173914 name: Dot Precision@1 - type: dot_precision@3 value: 0.2898550724637682 name: Dot Precision@3 - type: dot_precision@5 value: 0.18260869565217389 name: Dot Precision@5 - type: dot_precision@10 value: 0.0978260869565217 name: Dot Precision@10 - type: dot_recall@1 value: 0.7608695652173914 name: Dot Recall@1 - type: dot_recall@3 value: 0.8695652173913043 name: Dot Recall@3 - type: dot_recall@5 value: 0.9130434782608695 name: Dot Recall@5 - type: dot_recall@10 value: 0.9782608695652174 name: Dot Recall@10 - type: dot_ndcg@10 value: 0.8567216523715442 name: Dot Ndcg@10 - type: dot_mrr@10 value: 0.8190217391304349 name: Dot Mrr@10 - type: dot_map@100 value: 0.8203804347826088 name: Dot Map@100 --- # SentenceTransformer based on Snowflake/snowflake-arctic-embed-m This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [Snowflake/snowflake-arctic-embed-m](https://huggingface.co/Snowflake/snowflake-arctic-embed-m). It maps sentences & paragraphs to a 768-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more. ## Model Details ### Model Description - **Model Type:** Sentence Transformer - **Base model:** [Snowflake/snowflake-arctic-embed-m](https://huggingface.co/Snowflake/snowflake-arctic-embed-m) - **Maximum Sequence Length:** 512 tokens - **Output Dimensionality:** 768 tokens - **Similarity Function:** Cosine Similarity ### Model Sources - **Documentation:** [Sentence Transformers Documentation](https://sbert.net) - **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers) - **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers) ### Full Model Architecture ``` SentenceTransformer( (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: BertModel (1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': True, 'pooling_mode_mean_tokens': False, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True}) (2): Normalize() ) ``` ## Usage ### Direct Usage (Sentence Transformers) First install the Sentence Transformers library: ```bash pip install -U sentence-transformers ``` Then you can load this model and run inference. ```python from sentence_transformers import SentenceTransformer # Download from the 🤗 Hub model = SentenceTransformer("northstaranlyticsma24/artic_ft_midterm") # Run inference sentences = [ 'What topics were discussed during the meetings related to the development of the Blueprint for an AI Bill of Rights?', 'SECTION: LISTENING TO THE AMERICAN PEOPLE\nAPPENDIX\n• OSTP conducted meetings with a variety of stakeholders in the private sector and civil society. Some of these\nmeetings were specifically focused on providing ideas related to the development of the Blueprint for an AI\nBill of Rights while others provided useful general context on the positive use cases, potential harms, and/or\noversight possibilities for these technologies.', ' \nGAI systems can produce content that is inciting, radicalizing, or threatening, or that glorifies violence, \nwith greater ease and scale than other technologies. LLMs have been reported to generate dangerous or \nviolent recommendations, and some models have generated actionable instructions for dangerous or \n \n \n9 Confabulations of falsehoods are most commonly a problem for text-based outputs; for audio, image, or video \ncontent, creative generation of non-factual content can be a desired behavior. 10 For example, legal confabulations have been shown to be pervasive in current state-of-the-art LLMs. See also, \ne.g., \n \n7 \nunethical behavior.', ] embeddings = model.encode(sentences) print(embeddings.shape) # [3, 768] # Get the similarity scores for the embeddings similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [3, 3] ``` ## Evaluation ### Metrics #### Information Retrieval * Evaluated with [InformationRetrievalEvaluator](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator) | Metric | Value | |:--------------------|:-----------| | cosine_accuracy@1 | 0.7609 | | cosine_accuracy@3 | 0.8696 | | cosine_accuracy@5 | 0.913 | | cosine_accuracy@10 | 0.9783 | | cosine_precision@1 | 0.7609 | | cosine_precision@3 | 0.2899 | | cosine_precision@5 | 0.1826 | | cosine_precision@10 | 0.0978 | | cosine_recall@1 | 0.7609 | | cosine_recall@3 | 0.8696 | | cosine_recall@5 | 0.913 | | cosine_recall@10 | 0.9783 | | cosine_ndcg@10 | 0.8567 | | cosine_mrr@10 | 0.819 | | **cosine_map@100** | **0.8204** | | dot_accuracy@1 | 0.7609 | | dot_accuracy@3 | 0.8696 | | dot_accuracy@5 | 0.913 | | dot_accuracy@10 | 0.9783 | | dot_precision@1 | 0.7609 | | dot_precision@3 | 0.2899 | | dot_precision@5 | 0.1826 | | dot_precision@10 | 0.0978 | | dot_recall@1 | 0.7609 | | dot_recall@3 | 0.8696 | | dot_recall@5 | 0.913 | | dot_recall@10 | 0.9783 | | dot_ndcg@10 | 0.8567 | | dot_mrr@10 | 0.819 | | dot_map@100 | 0.8204 | ## Training Details ### Training Dataset #### Unnamed Dataset * Size: 363 training samples * Columns: sentence_0 and sentence_1 * Approximate statistics based on the first 363 samples: | | sentence_0 | sentence_1 | |:--------|:---------------------------------------------------------------------------------|:------------------------------------------------------------------------------------| | type | string | string | | details | | | * Samples: | sentence_0 | sentence_1 | |:-----------------------------------------------------------------------------------------------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------| | What are the five principles outlined in the Blueprint for an AI Bill of Rights intended to protect against? | SECTION: USING THIS TECHNICAL COMPANION


























-
USING THIS TECHNICAL COMPANION
The Blueprint for an AI Bill of Rights is a set of five principles and associated practices to help guide the design,
use, and deployment of automated systems to protect the rights of the American public in the age of artificial
intelligence. This technical companion considers each principle in the Blueprint for an AI Bill of Rights and
provides examples and concrete steps for communities, industry, governments, and others to take in order to
build these protections into policy, practice, or the technological design process. Taken together, the technical protections and practices laid out in the Blueprint for an AI Bill of Rights can help
guard the American public against many of the potential and actual harms identified by researchers, technolo­
gists, advocates, journalists, policymakers, and communities in the United States and around the world. This
technical companion is intended to be used as a reference by people across many circumstances – anyone
impacted by automated systems, and anyone developing, designing, deploying, evaluating, or making policy to
govern the use of an automated system. Each principle is accompanied by three supplemental sections:
1
2
WHY THIS PRINCIPLE IS IMPORTANT:
This section provides a brief summary of the problems that the principle seeks to address and protect against, including
illustrative examples. WHAT SHOULD BE EXPECTED OF AUTOMATED SYSTEMS:
• The expectations for automated systems are meant to serve as a blueprint for the development of additional technical
standards and practices that should be tailored for particular sectors and contexts. • This section outlines practical steps that can be implemented to realize the vision of the Blueprint for an AI Bill of Rights. The
expectations laid out often mirror existing practices for technology development, including pre-deployment testing, ongoing
monitoring, and governance structures for automated systems, but also go further to address unmet needs for change and offer
concrete directions for how those changes can be made. • Expectations about reporting are intended for the entity developing or using the automated system. The resulting reports can
be provided to the public, regulators, auditors, industry standards groups, or others engaged in independent review, and should
be made public as much as possible consistent with law, regulation, and policy, and noting that intellectual property, law
enforcement, or national security considerations may prevent public release. Where public reports are not possible, the
information should be provided to oversight bodies and privacy, civil liberties, or other ethics officers charged with safeguard
ing individuals’ rights. These reporting expectations are important for transparency, so the American people can have
confidence that their rights, opportunities, and access as well as their expectations about technologies are respected. 3
HOW THESE PRINCIPLES CAN MOVE INTO PRACTICE:
This section provides real-life examples of how these guiding principles can become reality, through laws, policies, and practices. It describes practical technical and sociotechnical approaches to protecting rights, opportunities, and access. The examples provided are not critiques or endorsements, but rather are offered as illustrative cases to help
provide a concrete vision for actualizing the Blueprint for an AI Bill of Rights. Effectively implementing these
processes require the cooperation of and collaboration among industry, civil society, researchers, policymakers,
technologists, and the public. | | How does the technical companion suggest that automated systems should be monitored and reported on to ensure transparency and protect individual rights? | SECTION: USING THIS TECHNICAL COMPANION


























-
USING THIS TECHNICAL COMPANION
The Blueprint for an AI Bill of Rights is a set of five principles and associated practices to help guide the design,
use, and deployment of automated systems to protect the rights of the American public in the age of artificial
intelligence. This technical companion considers each principle in the Blueprint for an AI Bill of Rights and
provides examples and concrete steps for communities, industry, governments, and others to take in order to
build these protections into policy, practice, or the technological design process. Taken together, the technical protections and practices laid out in the Blueprint for an AI Bill of Rights can help
guard the American public against many of the potential and actual harms identified by researchers, technolo­
gists, advocates, journalists, policymakers, and communities in the United States and around the world. This
technical companion is intended to be used as a reference by people across many circumstances – anyone
impacted by automated systems, and anyone developing, designing, deploying, evaluating, or making policy to
govern the use of an automated system. Each principle is accompanied by three supplemental sections:
1
2
WHY THIS PRINCIPLE IS IMPORTANT:
This section provides a brief summary of the problems that the principle seeks to address and protect against, including
illustrative examples. WHAT SHOULD BE EXPECTED OF AUTOMATED SYSTEMS:
• The expectations for automated systems are meant to serve as a blueprint for the development of additional technical
standards and practices that should be tailored for particular sectors and contexts. • This section outlines practical steps that can be implemented to realize the vision of the Blueprint for an AI Bill of Rights. The
expectations laid out often mirror existing practices for technology development, including pre-deployment testing, ongoing
monitoring, and governance structures for automated systems, but also go further to address unmet needs for change and offer
concrete directions for how those changes can be made. • Expectations about reporting are intended for the entity developing or using the automated system. The resulting reports can
be provided to the public, regulators, auditors, industry standards groups, or others engaged in independent review, and should
be made public as much as possible consistent with law, regulation, and policy, and noting that intellectual property, law
enforcement, or national security considerations may prevent public release. Where public reports are not possible, the
information should be provided to oversight bodies and privacy, civil liberties, or other ethics officers charged with safeguard
ing individuals’ rights. These reporting expectations are important for transparency, so the American people can have
confidence that their rights, opportunities, and access as well as their expectations about technologies are respected. 3
HOW THESE PRINCIPLES CAN MOVE INTO PRACTICE:
This section provides real-life examples of how these guiding principles can become reality, through laws, policies, and practices. It describes practical technical and sociotechnical approaches to protecting rights, opportunities, and access. The examples provided are not critiques or endorsements, but rather are offered as illustrative cases to help
provide a concrete vision for actualizing the Blueprint for an AI Bill of Rights. Effectively implementing these
processes require the cooperation of and collaboration among industry, civil society, researchers, policymakers,
technologists, and the public. | | What is the significance of the number 14 in the given context? | 14
 | * Loss: [MatryoshkaLoss](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#matryoshkaloss) with these parameters: ```json { "loss": "MultipleNegativesRankingLoss", "matryoshka_dims": [ 768, 512, 256, 128, 64 ], "matryoshka_weights": [ 1, 1, 1, 1, 1 ], "n_dims_per_step": -1 } ``` ### Training Hyperparameters #### Non-Default Hyperparameters - `eval_strategy`: steps - `per_device_train_batch_size`: 20 - `per_device_eval_batch_size`: 20 - `num_train_epochs`: 5 - `multi_dataset_batch_sampler`: round_robin #### All Hyperparameters
Click to expand - `overwrite_output_dir`: False - `do_predict`: False - `eval_strategy`: steps - `prediction_loss_only`: True - `per_device_train_batch_size`: 20 - `per_device_eval_batch_size`: 20 - `per_gpu_train_batch_size`: None - `per_gpu_eval_batch_size`: None - `gradient_accumulation_steps`: 1 - `eval_accumulation_steps`: None - `torch_empty_cache_steps`: None - `learning_rate`: 5e-05 - `weight_decay`: 0.0 - `adam_beta1`: 0.9 - `adam_beta2`: 0.999 - `adam_epsilon`: 1e-08 - `max_grad_norm`: 1 - `num_train_epochs`: 5 - `max_steps`: -1 - `lr_scheduler_type`: linear - `lr_scheduler_kwargs`: {} - `warmup_ratio`: 0.0 - `warmup_steps`: 0 - `log_level`: passive - `log_level_replica`: warning - `log_on_each_node`: True - `logging_nan_inf_filter`: True - `save_safetensors`: True - `save_on_each_node`: False - `save_only_model`: False - `restore_callback_states_from_checkpoint`: False - `no_cuda`: False - `use_cpu`: False - `use_mps_device`: False - `seed`: 42 - `data_seed`: None - `jit_mode_eval`: False - `use_ipex`: False - `bf16`: False - `fp16`: False - `fp16_opt_level`: O1 - `half_precision_backend`: auto - `bf16_full_eval`: False - `fp16_full_eval`: False - `tf32`: None - `local_rank`: 0 - `ddp_backend`: None - `tpu_num_cores`: None - `tpu_metrics_debug`: False - `debug`: [] - `dataloader_drop_last`: False - `dataloader_num_workers`: 0 - `dataloader_prefetch_factor`: None - `past_index`: -1 - `disable_tqdm`: False - `remove_unused_columns`: True - `label_names`: None - `load_best_model_at_end`: False - `ignore_data_skip`: False - `fsdp`: [] - `fsdp_min_num_params`: 0 - `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False} - `fsdp_transformer_layer_cls_to_wrap`: None - `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None} - `deepspeed`: None - `label_smoothing_factor`: 0.0 - `optim`: adamw_torch - `optim_args`: None - `adafactor`: False - `group_by_length`: False - `length_column_name`: length - `ddp_find_unused_parameters`: None - `ddp_bucket_cap_mb`: None - `ddp_broadcast_buffers`: False - `dataloader_pin_memory`: True - `dataloader_persistent_workers`: False - `skip_memory_metrics`: True - `use_legacy_prediction_loop`: False - `push_to_hub`: False - `resume_from_checkpoint`: None - `hub_model_id`: None - `hub_strategy`: every_save - `hub_private_repo`: False - `hub_always_push`: False - `gradient_checkpointing`: False - `gradient_checkpointing_kwargs`: None - `include_inputs_for_metrics`: False - `eval_do_concat_batches`: True - `fp16_backend`: auto - `push_to_hub_model_id`: None - `push_to_hub_organization`: None - `mp_parameters`: - `auto_find_batch_size`: False - `full_determinism`: False - `torchdynamo`: None - `ray_scope`: last - `ddp_timeout`: 1800 - `torch_compile`: False - `torch_compile_backend`: None - `torch_compile_mode`: None - `dispatch_batches`: None - `split_batches`: None - `include_tokens_per_second`: False - `include_num_input_tokens_seen`: False - `neftune_noise_alpha`: None - `optim_target_modules`: None - `batch_eval_metrics`: False - `eval_on_start`: False - `eval_use_gather_object`: False - `batch_sampler`: batch_sampler - `multi_dataset_batch_sampler`: round_robin
### Training Logs | Epoch | Step | cosine_map@100 | |:------:|:----:|:--------------:| | 1.0 | 19 | 0.7434 | | 2.0 | 38 | 0.7973 | | 2.6316 | 50 | 0.8048 | | 3.0 | 57 | 0.8048 | | 4.0 | 76 | 0.8204 | | 5.0 | 95 | 0.8204 | ### Framework Versions - Python: 3.10.12 - Sentence Transformers: 3.1.1 - Transformers: 4.44.2 - PyTorch: 2.4.1+cu121 - Accelerate: 0.34.2 - Datasets: 3.0.0 - Tokenizers: 0.19.1 ## Citation ### BibTeX #### Sentence Transformers ```bibtex @inproceedings{reimers-2019-sentence-bert, title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks", author = "Reimers, Nils and Gurevych, Iryna", booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing", month = "11", year = "2019", publisher = "Association for Computational Linguistics", url = "https://arxiv.org/abs/1908.10084", } ``` #### MatryoshkaLoss ```bibtex @misc{kusupati2024matryoshka, title={Matryoshka Representation Learning}, author={Aditya Kusupati and Gantavya Bhatt and Aniket Rege and Matthew Wallingford and Aditya Sinha and Vivek Ramanujan and William Howard-Snyder and Kaifeng Chen and Sham Kakade and Prateek Jain and Ali Farhadi}, year={2024}, eprint={2205.13147}, archivePrefix={arXiv}, primaryClass={cs.LG} } ``` #### MultipleNegativesRankingLoss ```bibtex @misc{henderson2017efficient, title={Efficient Natural Language Response Suggestion for Smart Reply}, author={Matthew Henderson and Rami Al-Rfou and Brian Strope and Yun-hsuan Sung and Laszlo Lukacs and Ruiqi Guo and Sanjiv Kumar and Balint Miklos and Ray Kurzweil}, year={2017}, eprint={1705.00652}, archivePrefix={arXiv}, primaryClass={cs.CL} } ```