Discourse Diversity in Multi-Turn Empathic Dialogue

2026-04-13

AI Summary

This work addresses the tendency of large language models to repeatedly employ identical discourse strategies in multi-turn empathetic conversations, which leads to rigid and less effective supportive responses. To mitigate this limitation, the authors propose the MINT framework, which, for the first time, incorporates cross-turn discourse strategy novelty as a reinforcement learning signal. By jointly optimizing empathetic quality and strategy diversity through a combined reward that integrates both empathy and novelty signals, MINT is applied to models with 1.7B and 4B parameters. Experimental results demonstrate that, on the 4B model, MINT reduces discourse strategy repetition by 26.3% and improves overall empathetic performance by 25.3%, significantly outperforming baseline approaches that optimize either empathetic quality alone or token-level diversity.

Technology Category

• Natural Language Processing: Discourse, Pragmatics & Argument Mining
• Machine Learning: Large Multimodal Models (LMMs)
• Search and Optimization: Learning to Search

Application Category

• Search and Retrieval-Augmented AI: Multilingual and cross-lingual Web search
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Economics, Online Markets and Human Computation: LLM based quality controls for crowd work

Abstract

Large language models (LLMs) produce responses rated as highly empathic in single-turn settings (Ayers et al., 2023; Lee et al., 2024), yet they are also known to be formulaic generators that reuse the same lexical patterns, syntactic templates, and discourse structures across tasks (Jiang et al., 2025; Shaib et al., 2024; Namuduri et al., 2025). Less attention has been paid to whether this formulaicity extends to the level of discourse moves, i.e., what a response does for the person it is addressing. This question is especially consequential for empathic dialogue, where effective support demands not just a kind response at one moment but varied strategies as a conversation unfolds (Stiles et al., 1998). Indeed, prior work shows that LLMs reuse the same tactic sequences more than human supporters in single-turn settings (Gueorguieva et al., 2026). We extend this analysis to multi-turn conversations and find that the rigidity compounds: once a tactic appears in a supporter turn, LLMs reuse it in the next at nearly double the rate of humans (0.50-0.56 vs. 0.27). This pattern holds across LLMs serving as supporters in real emotional support conversations, and is invisible to standard similarity metrics. To address this gap, we introduce MINT (Multi-turn Inter-tactic Novelty Training), the first reinforcement learning framework to optimize discourse move diversity across multi-turn empathic dialogue. The best MINT variant combines an empathy quality reward with a cross-turn tactic novelty signal, improving aggregate empathy by 25.3% over vanilla across 1.7B and 4B models while reducing cross-turn discourse move repetition by 26.3% on the 4B model, surpassing all baselines including quality-only and token-level diversity methods on both measures. These results suggest that what current models lack is not empathy itself, but the ability to vary their discourse moves across a conversation.

Problem

• discourse diversity
• empathic dialogue
• multi-turn conversation
• large language models
• discourse moves

Innovation

• discourse move diversity
• multi-turn empathic dialogue
• reinforcement learning
• MINT
• tactic novelty