Judges

TRL provides judges to easily compare two completions.

Make sure to have installed the required dependencies by running:

pip install trl[llm_judge]

Using the provided judges

TRL provides several judges out of the box. For example, you can use the HfPairwiseJudge to compare two completions using a pre-trained model from the Hugging Face model hub:

from trl import HfPairwiseJudge

judge = HfPairwiseJudge()
judge.judge(
    prompts=["What is the capital of France?", "What is the biggest planet in the solar system?"],
    completions=[["Paris", "Lyon"], ["Saturn", "Jupiter"]],
)  # Outputs: [0, 1]

Define your own judge

To define your own judge, we provide several base classes that you can subclass. For rank-based judges, you need to subclass BaseRankJudge and implement the BaseRankJudge.judge() method. For pairwise judges, you need to subclass BasePairJudge and implement the BasePairJudge.judge method. If you want to define a judge that doesn’t fit into these categories, you need to subclass BaseJudge and implement the BaseJudge.judge() method.

As an example, let’s define a pairwise judge that prefers shorter completions:

from trl import BasePairwiseJudge

class PrefersShorterJudge(BasePairwiseJudge):
    def judge(self, prompts, completions, shuffle_order=False):
        return [0 if len(completion[0]) > len(completion[1]) else 1 for completion in completions]

You can then use this judge as follows:

judge = PrefersShorterJudge()
judge.judge(
    prompts=["What is the capital of France?", "What is the biggest planet in the solar system?"],
    completions=[["Paris", "The capital of France is Paris."], ["Jupiter is the biggest planet in the solar system.", "Jupiter"]],
)  # Outputs: [0, 1]

BaseJudge

class trl.BaseJudge

< source >

( )

Base class for judges. The subclasses of this class should implement the judge method.

BaseRankJudge

class trl.BaseRankJudge

< source >

( )

Base class for LLM ranking judges.

Example:

class MyRankJudge(BaseRankJudge):
    def judge(self, prompts, completions, shuffle_order=True):
        return ...  # Your ranking logic here

judge = MyRankJudge()
judge.judge(
    prompts=["The capital of France is", "The capital of Germany is"],
    completions=[[" Paris", " Marseille", "Lyon"], [" Munich", " Berlin"]]
)  # [[0, 1, 2], [1, 0]]

judge

< source >

( prompts: List completions: List shuffle_order: bool = True )

Parameters

prompts (List[str]) — List of prompts.
completions (List[List[str]]) — List of completions list, where each element is a list of completions for the corresponding prompt.
shuffle_order (bool) — Whether to shuffle the order of the completions to avoid positional bias.

Judge the completion for the given prompts and return the ranks of each completion.

BasePairwiseJudge

class trl.BasePairwiseJudge

< source >

( )

Base class for pairwise judges.

judge

< source >

( prompts: List completions: List shuffle_order: bool = True )

Parameters

prompts (List[str]) — List of prompts.
completions (List[List[str]]) — List of completions pairs, where each element is a pair of completions for the corresponding prompt.
shuffle_order (bool) — Whether to shuffle the order of the completions to avoid positional bias.

Judge the completion pairs for the given prompts.

Note: If the judge returns -1 for any prompt, it indicates that the inner process used to compute the preference has failed. For instance, this could occur if the underlying language model returned an invalid answer. In such cases, the caller should handle these invalid indices appropriately, possibly by implementing fallback logic or error handling.

RandomRankJudge

class trl.RandomRankJudge

< source >

( )

Random rank, for testing purposes.

RandomPairwiseJudge

class trl.RandomPairwiseJudge

< source >

( )

Random pairwise judge, for testing purposes.

PairRMJudge

class trl.PairRMJudge

< source >

( )

LLM judge based on the PairRM model from AllenAI.

See: https://huggingface.co/llm-blender/PairRM

HfPairwiseJudge

class trl.HfPairwiseJudge

< source >

( model = 'meta-llama/Meta-Llama-3-70B-Instruct' token: Optional = None system_prompt: Optional = None )

Parameters

model (str, optional) — The model to use for the judge. Defaults to “meta-llama/Meta-Llama-3-70B-Instruct”.
token (str, optional) — The Hugging Face API token to use for the InferenceClient.
system_prompt (str, optional) — The system prompt to be used for the judge. If not provided, a default prompt is used. Note that the system prompt should contain the following placeholders: {prompt}, {response0}, and {response1}. Also, the inference is called with max_tokens=1, consequently the system prompt should ask for a single token response.

Pairwise judge based on the Hugging Face API with chat completion.

This judge is relevant for assessing the quality chat models, where the completion is a response to a given prompt.

OpenAIPairwiseJudge

class trl.OpenAIPairwiseJudge

< source >

( model = 'gpt-4-turbo-preview' system_prompt: Optional = None max_requests: Optional = 1000 )

Parameters

model (str, optional) — The model to use for the judge. Defaults to "gpt-4-turbo-preview".
system_prompt (str, optional) — The system prompt to be used for the judge. If not provided, a default prompt is used. Note that the system prompt should contain the following placeholders: {prompt}, {response0}, and {response1}. Also, the inference is called with max_tokens=1, consequently the system prompt should ask for a single token response.
max_requests (int, optional) — The maximum number of requests to make to the OpenAI API. Defaults to 1000. If set to None, there is no limit.

Judge based on the OpenAI API.

This judge is relevant for assessing the quality chat models, where the completion is a response to a given prompt.

< > Update on GitHub