让小模型学会说‘不知道’，有效减少幻觉。
Honest AI: Fine-Tuning "Small" Language Models to Say "I Don't Know", and Reducing Hallucination in RAG
- 用新数据微调小模型，训练其主动承认未知
- 混合方法在CRAG基准上得分最高，优于纯RAG
- 适合资源有限但需高准确性的企业应用
幻觉是大语言模型在实际应用中的主要障碍，尤其在对信息准确性敏感的企业场景中。本文提出Honest AI：一种新策略，通过微调参数少于100亿的小型语言模型，使其学会在不确定时说“我不知道”，从而降低幻觉。同时探索了多种替代RAG方案，包括结合搜索引擎与知识图谱结果的RAG、基于基础模型的微调，以及两者的组合。尽管所有方法均提升模型表现，但仅使用RAG的效果提升不显著，需配合微调才能取得更好结果。最终混合方法在CRAG基准上取得最高分，验证了其有效性。该方法强调使用小型模型，兼顾性能与资源效率。
原文摘要 · Abstract (English)
Hallucination is a key roadblock for applications of Large Language Models (LLMs), particularly for enterprise applications that are sensitive to information accuracy. To address this issue, two general approaches have been explored: Retrieval-Augmented Generation (RAG) to supply LLMs with updated information as context, and fine-tuning the LLMs with new information and desired output styles. In this paper, we propose Honest AI: a novel strategy to fine-tune "small" language models to say "I don't know" to reduce hallucination, along with several alternative RAG approaches. The solution ranked 1st in Task 2 for the false premise question. The alternative approaches include using RAG with search engine and knowledge graph results, fine-tuning base LLMs with new information and combinations of both approaches. Although all approaches improve the performance of the LLMs, RAG alone does not significantly improve the performance and fine-tuning is needed for better results. Finally, the hybrid approach achieved the highest score in the CRAG benchmark. In addition, our approach emphasizes the use of relatively small models with fewer than 10 billion parameters, promoting resource efficiency.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。