对话推理的对比学习
Contrastive Learning for Inference in Dialogue
AI总结：
本文针对对话中归纳推理因信息差距而表现不佳的问题，提出利用负样本的对比学习方法来缓解，实验证明该方法能提升模型的推理生成能力。
摘要：
推理，尤其是源自归纳过程的推理，是我们对话中补充说话者隐含或明确传达信息的关键组成部分。尽管近期的大型语言模型在推理任务上展现出显著进步，但它们在归纳推理（即上下文中并非所有信息都存在）上的表现远逊于演绎推理。本文中，我们基于由语义信息差距定义的任务难度来分析模型行为——这一差距区分了归纳推理与演绎推理（Johnson-Laird, 1988, 1993）。我们的分析揭示，对话上下文与期望推理之间的信息差异对归纳推理过程构成了重大挑战。为缓解这一信息差距，我们研究了一种通过输入负样本的对比学习方法。我们的实验表明，负样本有助于模型理解错误之处，并改善其推理生成。
英文摘要：
Inference, especially those derived from inductive processes, is a crucial component in our conversation to complement the information implicitly or explicitly conveyed by a speaker. While recent large language models show remarkable advances in inference tasks, their performance in inductive reasoning, where not all information is present in the context, is far behind deductive reasoning. In this paper, we analyze the behavior of the models based on the task difficulty defined by the semantic information gap -- which distinguishes inductive and deductive reasoning (Johnson-Laird, 1988, 1993). Our analysis reveals that the disparity in information between dialogue contexts and desired inferences poses a significant challenge to the inductive inference process. To mitigate this information gap, we investigate a contrastive learning approach by feeding negative samples. Our experiments suggest negative samples help models understand what is wrong and improve their inference generations.
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。
