CIG: Measuring Conversational Information Gain in Deliberative Dialogues with Semantic Memory Dynamics

ACL ARR 2026 January Submission4075 Authors

Keywords: discourse analysis, conversation analysis, deliberation, conversation quality, deliberative quality, communication, group conversation, moderation, facilitation

Abstract: Measuring the quality of public deliberation requires evaluating not just civility or argument structure, but the informational progress a conversation makes. 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 \textbf{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 discussion) 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.

Paper Type: Long

Research Area: Special Theme (conference specific)

Research Area Keywords: evaluation and metrics, conversational modeling, NLP tools for social analysis, discourse relations, evaluation methodologies, metrics, conversation

Contribution Types: Model analysis & interpretability, NLP engineering experiment, Data resources

Languages Studied: English

Submission Number: 4075