询问专家：利用语言模型提升目标导向对话模型中的策略推理能力
Ask an Expert: Leveraging Language Models to Improve Strategic Reasoning in Goal-Oriented Dialogue Models
AI总结：
本文提出“询问专家”框架，让对话模型在每轮可咨询大语言模型专家并选择性采纳建议，在心理健康支持任务中相比基线提升约10%，接近人类水平。
摘要：
现有对话模型可能会遇到训练数据中未能充分表示的场景，从而生成不自然、不恰当或无帮助的回复。我们提出“询问专家”（Ask an Expert）框架，在该框架中，模型在训练时可访问一位“专家”，并能在每一轮对话中向其咨询。建议通过与该专家的结构化对话来获取，模型被优化为根据上下文和对话历史选择性地利用（或忽略）这些建议。在本研究中，专家以大语言模型（LLM）的形式出现。我们在心理健康支持领域评估该框架，其中专家对话的结构由预先指定的提示（prompts）勾勒，这些提示反映了该领域从业者所学习的推理策略。使用“询问专家”的Blenderbot模型在所有专家规模下均表现出质量提升，包括参数少于对话模型本身的专家。我们最好的模型相比基线实现了约10%的提升，在“吸引力”（engagingness）和“帮助性”（helpfulness）指标上接近人类水平。
英文摘要：
Existing dialogue models may encounter scenarios which are not well-represented in the training data, and as a result generate responses that are unnatural, inappropriate, or unhelpful. We propose the "Ask an Expert" framework in which the model is trained with access to an "expert" which it can consult at each turn. Advice is solicited via a structured dialogue with the expert, and the model is optimized to selectively utilize (or ignore) it given the context and dialogue history. In this work the expert takes the form of an LLM. We evaluate this framework in a mental health support domain, where the structure of the expert conversation is outlined by pre-specified prompts which reflect a reasoning strategy taught to practitioners in the field. Blenderbot models utilizing "Ask an Expert" show quality improvements across all expert sizes, including those with fewer parameters than the dialogue model itself. Our best model provides a $\sim 10\%$ improvement over baselines, approaching human-level scores on "engingingness" and "helpfulness" metrics.
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。
