Thinking LLMs: General Instruction Following with Thought Generation
Abstract
LLMs are typically trained to answer user questions or follow instructions similarly to how human experts respond. However, in the standard alignment framework they lack the basic ability of explicit thinking before answering. Thinking is important for complex questions that require reasoning and planning -- but can be applied to any task. We propose a training method for equipping existing LLMs with such thinking abilities for general instruction following without use of additional human data. We achieve this by an iterative search and optimization procedure that explores the space of possible thought generations, allowing the model to learn how to think without direct supervision. For each instruction, the thought candidates are scored using a judge model to evaluate their responses only, and then optimized via preference optimization. We show that this procedure leads to superior performance on AlpacaEval and Arena-Hard, and shows gains from thinking on non-reasoning categories such as marketing, health and general knowledge, in addition to more traditional reasoning & problem-solving tasks.
Community
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
- TICKing All the Boxes: Generated Checklists Improve LLM Evaluation and Generation (2024)
- Self-Judge: Selective Instruction Following with Alignment Self-Evaluation (2024)
- Response Tuning: Aligning Large Language Models without Instruction (2024)
- Wait, that's not an option: LLMs Robustness with Incorrect Multiple-Choice Options (2024)
- To CoT or not to CoT? Chain-of-thought helps mainly on math and symbolic reasoning (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
Will the code for this be shared?
That's an interesting approach to teaching LLM 'thinking'! What types of synthetic data have proven most effective in practice?
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