对话中的推理：通过对话模拟为大型语言模型解决主观性任务
Reasoning in Conversation: Solving Subjective Tasks through Dialogue Simulation for Large Language Models
AI总结：
针对LLM在主观性任务上表现不佳的问题，本文提出RiC方法，通过模拟对话挖掘上下文知识而非使用思维链，并在12项任务上验证其显著提升效果。
摘要：
大型语言模型（LLM）已在开放域问答和数学推理等客观性任务上取得显著表现，这类任务通常可以通过回忆已学到的事实性知识或思维链风格的推理来解决。然而，我们发现LLM在隐喻识别、黑色幽默检测等主观性任务上的表现仍不理想。与客观性任务相比，主观性任务更关注解释或情绪反应，而不是普遍接受的推理路径。基于这些任务的特点以及LLM强大的对话生成能力，我们提出RiC（Reasoning in Conversation，对话中的推理），这是一种专注于通过对话模拟解决主观性任务的方法。RiC的动机是通过模拟对话来挖掘有用的上下文信息，而不是提供思维链风格的理由，从而提供对话背后潜在的有用知识以给出最终答案。我们在12项任务上评估了基于API的LLM和开源LLM，包括GPT-4、ChatGPT和OpenChat。实验结果表明，与各种基线相比，RiC能够带来显著提升。
英文摘要：
Large Language Models (LLMs) have achieved remarkable performance in objective tasks such as open-domain question answering and mathematical reasoning, which can often be solved through recalling learned factual knowledge or chain-of-thought style reasoning. However, we find that the performance of LLMs in subjective tasks is still unsatisfactory, such as metaphor recognition, dark humor detection, etc. Compared to objective tasks, subjective tasks focus more on interpretation or emotional response rather than a universally accepted reasoning pathway. Based on the characteristics of the tasks and the strong dialogue-generation capabilities of LLMs, we propose RiC (Reasoning in Conversation), a method that focuses on solving subjective tasks through dialogue simulation. The motivation of RiC is to mine useful contextual information by simulating dialogues instead of supplying chain-of-thought style rationales, thereby offering potential useful knowledge behind dialogues for giving the final answers. We evaluate both API-based and open-source LLMs including GPT-4, ChatGPT, and OpenChat across twelve tasks. Experimental results show that RiC can yield significant improvement compared with various baselines.
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。
