In spoken languages, utterances are often shaped to be incomplete or vague for efficiency. This can lead to varying interpretations of the same input, based on different assumptions about the context. To ensure reliable user-model interactions in such scenarios, it is crucial for models to adeptly handle the inherent ambiguity in user queries. However, conversational agents built upon even the most recent large language models (LLMs) face challenges in processing ambiguous inputs, primarily due to the following two hurdles: (1) LLMs are not directly trained to handle inputs that are too ambiguous to be properly managed; (2) the degree of ambiguity in an input can vary according to the intrinsic knowledge of the LLMs, which is difficult to investigate. To address these issues, this paper proposes a method to align LLMs to explicitly handle ambiguous inputs. Specifically, we introduce a proxy task that guides LLMs to utilize their intrinsic knowledge to self-disambiguate a given input. We quantify the information gain from the disambiguation procedure as a measure of the extent to which the models perceive their inputs as ambiguous. This measure serves as a cue for selecting samples deemed ambiguous from the models' perspectives, which are then utilized for alignment. Experimental results from several question-answering datasets demonstrate that the LLMs fine-tuned with our approach are capable of handling ambiguous inputs while still performing competitively on clear questions within the task.

翻译：在口语中，话语常因效率而呈现不完整或模糊性，这导致基于不同语境假设对同一输入产生多种解读。为确保此类场景下用户与模型的可靠交互，模型必须妥善处理用户查询中固有的歧义性。然而，即便基于最新大型语言模型（LLM）构建的对话代理在处理歧义输入时仍面临挑战，主要体现在以下两点：（1）LLM未经过直接训练来处理歧义度过高而难以有效管理的输入；（2）输入的歧义程度取决于LLM的内禀知识，这一特性难以探究。为解决这些问题，本文提出一种对齐方法，使LLM能够明确处理歧义输入。具体而言，我们引入代理任务引导LLM利用内禀知识对输入进行自消歧。我们将消歧过程的信息增益量化为模型感知输入歧义程度的指标，基于该指标可筛选出模型视角下的歧义样本，并用于模型对齐。在多个问答数据集上的实验结果表明，经本方法微调的LLM不仅能处理歧义输入，还能在清晰任务问题中保持竞争性能。