paper-with-me

홈 › Papers

Teaching LLMs to Refine with Tools

2024-12-22 · Dian Yu, Yuheng Zhang, Jiahao Xu, Tian Liang, Linfeng Song, Zhaopeng Tu, Haitao Mi, Dong Yu

Large language models (LLMs) can refine their responses based on feedback, enabling self-improvement through iterative training or test-time refinement. However, existing methods predominantly focus on refinement within the same reasoning format, which may lead to non-correcting behaviors. We propose CaP, a novel approach that uses external tools to refine chain-of-thought (CoT) responses generated by the same or other LLMs. CaP employs a two-stage training process: supervised fine-tuning followed by preference optimization with DPO variants. Our observations highlight the critical role of preference optimization in enabling effective refinement. Additionally, we compare several sampling strategies to leverage CoT and tools at inference time. Experimental results demonstrate CaP's potential for effective cross-reasoning refinement and efficient inference.

📄 PDF Abstract BibTeX arXiv:2412.16871

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

DPO 설명 없음
Focus 설명 없음

Similar Papers 제목 키워드 기반

Teaching LLMs Music Theory with In-Context Learning and Chain-of-Thought Prompting: Pedagogical Strategies for Machines

2025-03-28 · Liam Pond, Ichiro Fujinaga

This study evaluates the baseline capabilities of Large Language Models (LLMs) like ChatGPT, Claude, and Gemini to learn concepts in music theory through in-context learning and chain-of-thought prompting. Using carefull…

In-Context LearningKey Detection

SearchSkill: Teaching LLMs to Use Search Tools with Evolving Skill Banks

2026-05-09 · Jinchao Hu, Meizhi Zhong, Kehai Chen, Min Zhang arxiv

Teaching language models to use search tools is not only a question of whether they search, but also of whether they issue good queries. This is especially important in open-domain question answering, where broad or copi…

Open-Domain Question Answering

Teaching Algorithmic Reasoning via In-context Learning

2022-11-15 · Hattie Zhou, Azade Nova, Hugo Larochelle, Aaron Courville 외

Large language models (LLMs) have shown increasing in-context learning capabilities through scaling up model and data size. Despite this progress, LLMs are still unable to solve algorithmic reasoning problems. While prov…

In-Context Learning

A Review of Digital Learning Environments for Teaching Natural Language Processing in K-12 Education

2023-10-02 · Xiaoyi Tian, Kristy Elizabeth Boyer

Natural Language Processing (NLP) plays a significant role in our daily lives and has become an essential part of Artificial Intelligence (AI) education in K-12. As children grow up with NLP-powered applications, it is c…

Text Generation

EducationQ: Evaluating LLMs' Teaching Capabilities Through Multi-Agent Dialogue Framework

2025-04-21 · Yao Shi, Rongkeng Liang, Yong Xu

Large language models (LLMs) increasingly serve as educational tools, yet evaluating their teaching capabilities remains challenging due to the resource-intensive, context-dependent, and methodologically complex nature o…