Learning the Latent Rules of a Game from Data: A Chess Story
BFauber
Abstract
We demonstrate that small pretrained foundational generative language models with millions of parameters can learn the latent rules of a process from data associated with the process. Inspired by Stefan Zweig's novella "Schachnovelle," also known as "The Royal Game" in English, we show that 28M and 125M parameter pretrained foundational small language models (SLMs) can be instruction fine-tuned with 1,000-to-1,000,000 examples to learn the rules of chess, propose legal moves, and accurately solve chess problems. We also explore the impact of successive language model fine-tuning epochs on improved outcomes and demonstrate reductions in model hallucinations by increasing the number of instruction fine-tuning examples.
Community
Instruction fine-tuned small language models (SLMs) with 28M and 125M parameters can learn chess rules and solve chess problems using only single-move game play data. Additionally, increasing the number of fine-tuning examples reduces model hallucinations and enhances performance, highlighting the importance of relevant data in customizing GenAI language model pipelines.
This is an automated message from the Librarian Bot. I found the following papers similar to this paper.
The following papers were recommended by the Semantic Scholar API
- Exploring the Learning Capabilities of Language Models using LEVERWORLDS (2024)
- Physics of Language Models: Part 2.2, How to Learn From Mistakes on Grade-School Math Problems (2024)
- Layer Swapping for Zero-Shot Cross-Lingual Transfer in Large Language Models (2024)
- Can Models Learn Skill Composition from Examples? (2024)
- Fine-tuning large language models for domain adaptation: Exploration of training strategies, scaling, model merging and synergistic capabilities (2024)
Please give a thumbs up to this comment if you found it helpful!
If you want recommendations for any Paper on Hugging Face checkout this Space
You can directly ask Librarian Bot for paper recommendations by tagging it in a comment:
@librarian-bot
recommend
Models citing this paper 0
No model linking this paper
Datasets citing this paper 0
No dataset linking this paper
Spaces citing this paper 0
No Space linking this paper