让大模型学会自我怀疑，减少幻觉错误。
LaMsS: When Large Language Models Meet Self-Skepticism
- 在模型中引入怀疑标记，实现不同层级的自我质疑。
- 在多选题和开放域问答上准确率提升，优于基线方法。
- 适合需要高可靠性的AI应用，如医疗与法律领域。
幻觉是大语言模型（LLMs）面临的主要挑战，限制其在某些领域的进一步应用。人类的怀疑思维有助于自我认知与反思，可缓解幻觉问题。受此启发，我们提出一种新方法LaMsS，将大模型的语义理解能力与自我怀疑机制结合。通过引入一系列怀疑标记并扩充到词汇表中，进行预训练与微调，使模型在生成每个正常标记后可接一个怀疑标记，表示不同层次的怀疑程度。通过计算响应的怀疑度，可定义一个具备自知能力的模型，仅当怀疑度低于阈值时才回答问题。在多选题与开放域问答基准测试中，以回答准确率、AUC和平均精度衡量，LaMsS表现优于基线方法，并可在多任务及域外设置中良好泛化。本研究为人工智能中的自我怀疑建模提供了新思路。项目代码与模型检查点见https://anonymous.4open.science/r/SM-1E76。
原文摘要 · Abstract (English)
Hallucination is a major challenge for large language models (LLMs), preventing their further application in some fields. The skeptical thinking of humankind could be useful for LLMs to self-cognition, self-reflection and alleviate their hallucinations. Inspired by this consideration, we propose a novel approach called LaMsS, which combines the semantic understanding capability of LLMs with self-skepticism. By introducing a series of skepticism tokens and augmenting them into the vocabulary, we conduct both pertaining and finetuning, which allow the LLM to decode each normal token followed by a skeptical token, representing different skepticism levels. By calculating the response skepticism given a query, one can define a new self-aware LLM which is only willing to answer with relative lower skepticism level than the threshold. By examining the accuracy, AUC and AP of willingly answering questions, we demonstrate that LaMsS achieves better performance than baselines on both multi-choice questions and open-domain question-answering benchmarks, and can generalize to multi-task and out-of-domain settings. Our study sheds some lights on the self-skepticism modeling on further artificial intelligence. Project code and model checkpoints can be found in https://anonymous.4open.science/r/SM-1E76.
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。