教语言模型主动收集信息
Teaching Language Models To Gather Information Proactively
AI总结：
针对大语言模型被动回应、无法主动收集缺失信息的问题，研究提出主动信息收集范式与强化微调策略，训练的模型在自动评估和人工偏好上均显著优于基线，助力大模型成为协作伙伴。
摘要：
大型语言模型（LLM）正越来越多地被期待充当协作伙伴，通过来回对话解决复杂、模糊的问题。然而，当前的LLM在真实场景中往往表现不佳，面对不完整或表述不明确的提示时，只会被动回应或进行狭隘的澄清，无法主动收集对高质量解决方案至关重要的缺失信息。在本研究中，我们提出了一种新的任务范式：主动信息收集，即LLM必须识别所提供上下文中的缺口，并通过有针对性的问题策略性地引出用户隐含的知识。为了系统地研究和训练这种能力，我们设计了一个可扩展框架，该框架可生成部分指定的真实任务，掩盖关键信息并模拟真实的模糊性。在此设置下，我们的核心创新是一种强化微调策略，该策略会对那些能引出真正新的、隐含的用户信息（如隐藏的领域专业知识或细粒度需求）的问题给予奖励，这些信息原本不会被主动说出。实验表明，我们训练的Qwen-2.5-7B模型在自动评估指标上比o3-mini高出18%。更重要的是，人工评估显示，我们的模型生成的澄清问题和最终大纲分别获得了42%和28%的标注人员偏好。这些结果共同凸显了主动澄清在将LLM从被动文本生成器提升为真正的协作思维伙伴方面的价值。
英文摘要：
Large language models (LLMs) are increasingly expected to function as collaborative partners, engaging in back-and-forth dialogue to solve complex, ambiguous problems. However, current LLMs often falter in real-world settings, defaulting to passive responses or narrow clarifications when faced with incomplete or under-specified prompts, falling short of proactively gathering the missing information that is crucial for high-quality solutions. In this work, we introduce a new task paradigm: proactive information gathering, where LLMs must identify gaps in the provided context and strategically elicit implicit user knowledge through targeted questions. To systematically study and train this capability, we design a scalable framework that generates partially specified, real-world tasks, masking key information and simulating authentic ambiguity. Within this setup, our core innovation is a reinforcement finetuning strategy that rewards questions that elicit genuinely new, implicit user information -- such as hidden domain expertise or fine-grained requirements -- that would otherwise remain unspoken. Experiments demonstrate that our trained Qwen-2.5-7B model significantly outperforms o3-mini by 18% on automatic evaluation metrics. More importantly, human evaluation reveals that clarification questions and final outlines generated by our model are favored by human annotators by 42% and 28% respectively. Together, these results highlight the value of proactive clarification in elevating LLMs from passive text generators to genuinely collaborative thought partners.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
