# Discourse Diversity in Multi-Turn Empathic Dialogue

arXiv: https://arxiv.org/abs/2604.11742 · HTML: https://mlsanity.com/paper/2604.11742/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 42 of its 77 references that are in the map.
- First posted on arXiv 13 Apr 2026.

## Builds on (most cited first, 30 of 42)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [DAPO: An Open-Source LLM Reinforcement Learning System at Scale](https://mlsanity.com/paper/2503.14476/) (2025)
- [HybridFlow: A Flexible and Efficient RLHF Framework](https://mlsanity.com/paper/2409.19256/) (2024)
- [WildChat: 1M ChatGPT Interaction Logs in the Wild](https://mlsanity.com/paper/2405.01470/) (2024)
- [Towards Emotional Support Dialog Systems](https://mlsanity.com/paper/2106.01144/) (2021)
- [A Long Way to Go: Investigating Length Correlations in RLHF](https://mlsanity.com/paper/2310.03716/) (2023)
- [A Computational Approach to Understanding Empathy Expressed in Text-Based Mental Health Support](https://mlsanity.com/paper/2009.08441/) (2020)
- [Artificial Hivemind: The Open-Ended Homogeneity of Language Models (and Beyond)](https://mlsanity.com/paper/2510.22954/) (2025)
- [Verbalized Sampling: How to Mitigate Mode Collapse and Unlock LLM Diversity](https://mlsanity.com/paper/2510.01171/) (2025)
- [MISC: A MIxed Strategy-Aware Model Integrating COMET for Emotional Support Conversation](https://mlsanity.com/paper/2203.13560/) (2022)
- [Plug-and-Play Policy Planner for Large Language Model Powered Dialogue Agents](https://mlsanity.com/paper/2311.00262/) (2023)
- [Improving Multi-turn Emotional Support Dialogue Generation with Lookahead Strategy Planning](https://mlsanity.com/paper/2210.04242/) (2022)
- [Detection and Measurement of Syntactic Templates in Generated Text](https://mlsanity.com/paper/2407.00211/) (2024)
- [Diversity-Aware Policy Optimization for Large Language Model Reasoning](https://mlsanity.com/paper/2505.23433/) (2025)
- [Investigating Affective Use and Emotional Well-being on ChatGPT](https://mlsanity.com/paper/2504.03888/) (2025)
- [Large Language Models Produce Responses Perceived to be Empathic](https://mlsanity.com/paper/2403.18148/) (2024)
- [TransESC: Smoothing Emotional Support Conversation via Turn-Level State Transition](https://mlsanity.com/paper/2305.03296/) (2023)
- [AI Companions Reduce Loneliness](https://mlsanity.com/paper/2407.19096/) (2024)
- [Diversity-Incentivized Exploration for Versatile Reasoning](https://mlsanity.com/paper/2509.26209/) (2025)
- [RLVER: Reinforcement Learning with Verifiable Emotion Rewards for Empathetic Agents](https://mlsanity.com/paper/2507.03112/) (2025)
- [When Large Language Models are Reliable for Judging Empathic Communication](https://mlsanity.com/paper/2506.10150/) (2025)
- [Post-training Large Language Models for Diverse High-Quality Responses](https://mlsanity.com/paper/2509.04784/) (2025)
- [Facilitating Multi-turn Emotional Support Conversation with Positive Emotion Elicitation: A Reinforcement Learning Approach](https://mlsanity.com/paper/2307.07994/) (2023)
- [Large Language Models are Capable of Offering Cognitive Reappraisal, if Guided](https://mlsanity.com/paper/2404.01288/) (2024)

## Built on by (most cited first, 1 of 1)

- [Evolving Support Priorities in Empathetic Reinforcement Learning](https://mlsanity.com/paper/2609.34249/) (2026)

## Abstract (arXiv)

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.