在用户与语言模型智能体的交互中,用户话语常为提升效率而出现省略(遗漏单词或短语)或表述不精确(缺乏确切性)的情况。这可能导致同一输入因不同假设或背景知识而产生不同解读。因此,智能体必须熟练处理查询中固有的歧义,以确保可靠性。然而,即便是最先进的大语言模型(LLMs)在此类场景下仍面临挑战,主要障碍包括:(1)LLMs未经过处理歧义话语的显式训练;(2)LLMs感知到的歧义程度可能因自身掌握的知识而有所不同。为解决这些问题,我们提出了感知歧义对齐(Alignment with Perceived Ambiguity,APA),这是一种新型流程,通过利用LLMs自身对歧义的评估(即感知歧义),使LLMs对齐以处理歧义查询。在问答数据集上的实验结果表明,APA能让LLMs显式检测并处理歧义查询,同时保留回答清晰问题的能力。此外,我们的研究结果证明,APA的表现优于使用金标准标签的训练方式,尤其在分布外场景中效果更突出。数据和代码可在https://github.com/heyjoonkim/APA获取。
英文摘要:
In interactions between users and language model agents, user utterances frequently exhibit ellipsis (omission of words or phrases) or imprecision (lack of exactness) to prioritize efficiency. This can lead to varying interpretations of the same input based on different assumptions or background knowledge. It is thus crucial for agents to adeptly handle the inherent ambiguity in queries to ensure reliability. However, even state-of-the-art large language models (LLMs) still face challenges in such scenarios, primarily due to the following hurdles: (1) LLMs are not explicitly trained to deal with ambiguous utterances; (2) the degree of ambiguity perceived by the LLMs may vary depending on the possessed knowledge. To address these issues, we propose Alignment with Perceived Ambiguity (APA), a novel pipeline that aligns LLMs to manage ambiguous queries by leveraging their own assessment of ambiguity (i.e., perceived ambiguity). Experimental results on question-answering datasets demonstrate that APA empowers LLMs to explicitly detect and manage ambiguous queries while retaining the ability to answer clear questions. Furthermore, our finding proves that APA excels beyond training with gold-standard labels, especially in out-of-distribution scenarios. The data and code are available at https://github.com/heyjoonkim/APA.
Tool Retrieval Bridge: Aligning Vague Instructions with Retriever Preferences via Bridge Model
Department of Gastroenterology, Renmin Hospital, Wuhan University(武汉大学人民医院消化内科);School of Computer Science, Wuhan University(武汉大学计算机学院);State Grid Corporation(国家电网公司)
Asking Clarification Questions to Handle Ambiguity in Open-Domain QA
Seoul National University(首尔大学);Chung-Ang University(中央大学);NAVER AI Lab(NAVER AI实验室);NAVER Cloud(NAVER云);University of Richmond(里士满大学);KAIST AI(韩国科学技术院人工智能研究所);Samsung Electronics Mobile eXperience(三星电子移动体验部门)
Paul G. Allen School of Computer Science & Engineering, University of Washington(华盛顿大学保罗·G·艾伦计算机科学与工程学院);Massachusetts Institute of Technology(麻省理工学院);Allen Institute for AI(艾伦人工智能研究所)