Reasoning About Intent for Ambiguous Requests
This addresses user frustration and safety risks in AI interactions by improving transparency and efficiency for ambiguous requests, though it is incremental as it builds on existing methods with a novel structured output approach.
The paper tackles the problem of large language models responding to ambiguous requests by implicitly committing to one interpretation, which can cause user frustration and safety risks, and proposes generating multiple interpretation-answer pairs in a single structured response, achieving higher coverage of valid answers than baselines in experiments on conversational question answering and semantic parsing.
Large language models often respond to ambiguous requests by implicitly committing to one interpretation. Intent misunderstandings can frustrate users and create safety risks. To address this, we propose generating multiple interpretation-answer pairs in a single structured response to ambiguous requests. Our models are trained with reinforcement learning and customized reward functions using multiple valid answers as supervision. Experiments on conversational question answering and semantic parsing demonstrate that our method achieves higher coverage of valid answers than baseline approaches. Human evaluation confirms that predicted interpretations are highly aligned with their answers. Our approach promotes transparency with explicit interpretations, achieves efficiency by requiring only one generation step, and supports downstream applications through its structured output format.