README.md

metadata

title: README
emoji: 🐠
colorFrom: yellow
colorTo: gray
sdk: gradio
pinned: false

GTAlign: Game-Theoretic Alignment of LLM Assistants for Mutual Welfare

GTAlign applies game-theoretic principles to fine-tune reasoning LLMs, encouraging them to make decisions that are not only accurate but also rational, cooperative, and transparent in dialogue settings.

Models

We have released five model checkpoints, and we are preparing more thoroughly trained models.

Model Name	Size	Dataset	Hugging Face Link
GTAlign/Qwen2.5-3B-Math-140step	3B	Math	Model
GTAlign/Qwen2.5-3B-Medium-110step	3B	Medium	Model
GTAlign/Qwen2.5-3B-AbgQA-140step	3B	Ambig-QA	Model
GTAlign/Qwen2.5-3B-WildGuard-140step	3B	WildGuard	Model
GTAlign/Qwen2.5-3B-Full-160step	3B	Full	Model