用语义记忆动态评估对话信息增量，衡量讨论进展质量。
CIG: Measuring Conversational Information Gain in Deliberative Dialogues with Semantic Memory Dynamics
- 构建动态语义记忆模型，逐条整合对话中的原子论点。
- 从新颖性、相关性、影响范围三维度量化每句话的信息增益。
- 基于大模型预测信息增益，适合研究公共讨论质量与效果。
评估公众讨论质量不仅需关注文明程度或论证结构，还需衡量对话中的信息进展。本文提出对话信息增益（CIG）框架，通过建模讨论的演化语义记忆来评估每条发言对主题集体理解的推进作用。系统从发言中提取原子论点，并逐步整合为结构化记忆状态。基于此记忆，从新颖性、相关性和影响范围三个可解释维度对每条发言进行评分。我们在两个受控讨论场景（电视辩论与社区讨论）中人工标注了80个片段，结果表明，由记忆驱动的动态指标（如论点更新次数）比传统启发式方法（如发言长度或TF-IDF）更能准确反映人类对信息增益的感知。我们还开发了基于大语言模型的有效CIG预测器，为对话中以信息为核心的讨论质量分析与审议成效评估提供了新路径。
原文摘要 · Abstract (English)
Measuring the quality of public deliberation requires evaluating not only civility or argument structure, but also the informational progress of a conversation. We introduce a framework for Conversational Information Gain (CIG) that evaluates each utterance in terms of how it advances collective understanding of the target topic. To operationalize CIG, we model an evolving semantic memory of the discussion: the system extracts atomic claims from utterances and incrementally consolidates them into a structured memory state. Using this memory, we score each utterance along three interpretable dimensions: Novelty, Relevance, and Implication Scope. We annotate 80 segments from two moderated deliberative settings (TV debates and community discussions) with these dimensions and show that memory-derived dynamics (e.g., the number of claim updates) correlate more strongly with human-perceived CIG than traditional heuristics such as utterance length or TF--IDF. We develop effective LLM-based CIG predictors paving the way for information-focused conversation quality analysis in dialogues and deliberative success.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。