Do we need to answer that question? Salience and Answerability of Potential Questions in Naturalistic Dialogue
Summary
This paper empirically investigates the relationship between salience and answerability of questions in naturalistic dialogue, finding a robust but low positive correlation that is weaker than in monologic text, indicating that conversational structure is less predictable.
View Cached Full Text
Cached at: 09/28/26, 09:49 AM
# Do we need to answer that question? Salience and Answerability of Potential Questions in Naturalistic Dialogue Source: [https://arxiv.org/abs/2609.31130](https://arxiv.org/abs/2609.31130) [View PDF](https://arxiv.org/pdf/2609.31130) > Abstract:We empirically investigate Question Under Discussion based modelling in naturalistic dialogue by studying whether the salience of generated potential questions predicts their subsequent resolution\. Building on Wu et al\. \(2024\), we construct a dataset of 7,124 questions automatically generated from utterances and preceding context from the British National Corpus, and annotated for salience and answerability\. We find a robust but low positive correlation between salience and answerability in dialogue, indicating that more salient questions are more likely to be addressed\. However, this effect is markedly weaker than in monologic text, suggesting that conversational structure is less predictable\. We further observe that structured interactions exhibit stronger alignment between annotators than less organised dialogues\. ## Submission history From: Amandine Decker \[[view email](https://arxiv.org/show-email/99eaa4f8/2609.31130)\] \[via CCSD proxy\] **\[v1\]**Fri, 25 Sep 2026 11:23:45 UTC \(1,284 KB\)
Similar Articles
Two Axes of LLM Abstention: Answer Correctness and Question Answerability
This paper investigates the two axes of LLM abstention: answer correctness and question answerability. It shows that a single confidence threshold conflates these two failure modes, and proposes a three-class selective acceptance framework with separate budgets. Experiments across five instruction-tuned models reveal that answerability is internally legible but poorly captured by output confidence or self-assessments.
Topics as Proxies for Sociodemographics: How Conversational Context Affects LLM Answers
This paper investigates how LLMs produce different outcomes based on conversational context, finding that topic, rather than explicit user demographics, is the primary driver of disparities in high-stakes scenarios like salary advice.
Prompt Robustness Is Task-Dependent: Comparing Objective and Belief-Style Questions in LLM Evaluation
This paper investigates how prompt robustness varies between objective and subjective questions in LLM evaluations, finding that sensitivity to prompt changes depends on question type, prompt change, and model.
TurnNat: Automatic Evaluation of Turn-Taking Naturalness in Dyadic Spoken Dialogue
TurnNat is a likelihood-based framework for automatically evaluating turn-taking naturalness in dyadic spoken dialogue, using a causal turn-taking prediction model trained on natural conversations to measure timing atypicality via negative log-likelihood.
Semantic Variability of Replies Across LLMs: Implications for Designing Conversation-Based Assessment
The study examines the semantic consistency of LLM-generated replies across different models and conversational contexts, highlighting the need for infrastructure and design strategies to maintain stable responses for conversation-based assessments.