Discourse Diversity in Multi-Turn Empathic Dialogue

Hongli Zhan; Emma S. Gueorguieva; Javier Hernandez; Jina Suh; Desmond C. Ong; Junyi Jessy Li

cs.CLApr 13, 2026

Discourse Diversity in Multi-Turn Empathic Dialogue

Authors: Hongli Zhan, Emma S. Gueorguieva, Javier Hernandez, Jina Suh, Desmond C. Ong, Junyi Jessy Li

Organizations: The University of Texas at Austin · Microsoft Research · University of Washington

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.

Figures & tables

Figure 1: As the seeker’s needs evolve, vanilla LLMs recycle a narrow tactic set, whereas Mint adapts its discourse moves across turns.

Figure 2: Left: Tactic prevalence (percentage of turns containing each tactic). LLMs heavily overuse advice (

64

–

89

%) and information (

63

–

80

%) while under-using questioning (

25

–

34

% vs.

42

% for humans). Right: Tactic stickiness. Blue:

P(T\in\text{turn}_{t}\mid T\in\text{turn}_{t-1})

; gray:

P(T\in\text{turn}_{t}\mid T\notin\text{turn}_{t-1})

. For humans, whether a tactic appeared in the previous turn has limited influence; for LLMs, the gap is dramatic. The two phenomena compound: tactics that LLMs overuse (e.g., advice ) are also the stickiest, creating a loop of repetitiveness.

Source	# Pairs	Bigram	BLEU-2	BERTSc.	Stick.
Human	265	0.022	0.035	0.865	0.266
GPT-3.5-turbo	1,066	0.100	0.134	0.860	0.516
GPT-4	228	0.089	0.127	0.858	0.556
Llama-2-70B-Chat	103	0.119	0.159	0.860	0.502

Table 1: Cross-turn similarity between consecutive supporter turns. The first three columns measure lexical and semantic overlap; Stick. = tactic stickiness

P(T\in\text{turn}_{t}\mid T\in\text{turn}_{t-1})

(the lower the better). Only stickiness reveals that LLMs repeat discourse moves at roughly double the human rate.

Figure 3: Overview of Mint . Step 1 : A multi-turn conversation provides tactic history. Step 2 : The policy

\pi_{\theta}

generates a new supporter response, and a sentence-level tactic tagger labels each sentence. Step 3 : The tactic distribution of the current turn (

Q

) is compared against the historical profile (

P

) via

D_{\mathrm{KL}}(Q\|P)

for novelty and

H(Q)

for within-turn breadth, yielding a combined quality-weighted diversity reward optimized with GRPO.

Figure 4: Aggregate empathy vs. tactic stickiness. Mint (Q + D ${}_{\text{KL}}$ ) gives the best trade-off across both model sizes.

				Empathy $\uparrow$ (1–5 scale)			Neg. Behaviors $\downarrow$ (1–5 scale)			Agg. $\uparrow$	Tactic Diversity
Model	Family	Method	Words	Valid.	Elab.	Underst.	Unsol. Adv.	Self-Or.	Dismiss.	Agg.	Tac/Turn	Stick. $\downarrow$
Human (Gold)			20.6	$1.98$	$1.62$	$1.47$	$1.93$	$1.48$	$2.29$	$2.90$	$1.97$	$0.27$
		Vanilla	70.0	$3.76$	$1.55$	$2.50$	$1.99$	$1.07$	$1.17$	$3.60$	$4.49$	$0.51$
		Tactic Prompt	66.8	$4.09$ *	$2.22$ *	$2.93$ *	$1.60$ *	1.16 *	$1.07$ *	$3.90$ *	$3.73$	$0.45$
	Prompt-based	Tactic $+$ History	66.4	$3.99$ *	$2.10$ *	$2.90$ *	$1.45$ *	$1.14$	$1.04$ *	$3.89$ *	$3.63$	$0.40$ *
		VS (Vanilla)	42.2	2.84 *	$1.52$	2.07 *	2.30 *	$1.12$	1.67 *	3.22 *	$3.02$	$0.41$ *

Table 2: Results on the Lend-an-Ear test set (

315

supporter turns,

50

conversations). Empathy columns report three positive dimensions (

1

–

5

scale) and three negative behavioral dimensions; Agg. combines positive and reverse-coded negative dimensions. Tac/Turn = unique tactics per response; Stick. = tactic stickiness

P(T\in\text{turn}_{t}\mid T\in\text{turn}_{t-1})

\downarrow

. Significance: paired bootstrap (

10{,}000

resamples) vs. Vanilla;

*

p{<}.01

(Bonferroni-corrected across

7

empathy dimensions

+

stickiness). Gray cells = significantly worse .

Appendix figures & tables5 assets

Supplementary material from the paper’s appendix.

Appendix

Panel of Figure 5 — Figure 5: Shared prompt template for the tactic taggers, used for both training and inference. The highlighted placeholder {tactic_definition} is filled per-adapter; {Full_Response} and {Sentence} are filled with the target response and sentence.

Diversity metric	Satisfaction measure	$\rho$	$p$	$n$
Avg. stickiness	Successful	$-0.155$	$0.204$	69
	Engaged	$-0.177$	$0.146$	69
	PositiveInteraction	$-0.172$	$0.157$	69
	UseAgain	-0.287	0.017 *	69
Avg. new tactics	Successful	$0.008$	$0.946$	69
	Engaged	$0.199$	$0.101$	69

Appendix

Table 4: Conversation-level Spearman correlations between tactic diversity and user satisfaction in the

69

SENSE-7 conversations. *

p<0.05

Panel of Figure 6 — Figure 6: Prompt for filtering conversations where the user is seeking emotional support (§ 5.1 ).

	Valid.	Elab.	Underst.	Unsol. Adv.	Self-Or.	Dismiss.	Mean
Experts 1 & 2	0.25 ∗	0.69 ∗	0.47 ∗	0.70 ∗	0.82 ∗	0.35	0.55
Experts 2 & 3	0.58 ∗	0.73 ∗	0.43	0.69 ∗	0.52 ∗	0.51	0.58
Experts 3 & 1	0.39 ∗	0.62 ∗	0.37	0.54 ∗	0.70 ∗	0.49	0.52
gpt-oss-120b	0.67 ∗	0.54 ∗	0.44 ∗	0.76 ∗	0.71 ∗	0.35 ∗	0.58

Appendix

Table 5: Inter-annotator agreement (weighted Cohen’s

\kappa_{w}

) on the

6

Lend-an-Ear ( Kumar et al., 2026 ) empathy evaluation sub-components. Top rows: pairwise agreement among the three expert annotators. Bottom row: gpt-oss-120b evaluated against the expert median, following Kumar et al. (2026) . Valid. = validating emotions, Elab. = encouraging elaboration, Underst. = demonstrating understanding, Unsol. Adv. = unsolicited advice giving, Self-Or. = self-oriented, Dismiss. = dismissing emotions.

{}^{*}p<0.01

(Bonferroni-corrected across

6

empathy dimensions).

Panel of Figure 7 — Figure 7: Prompt template for turn-level empathy evaluation. Placeholders in braces are filled dynamically: framework with the full empathic communication framework (§ G.1 ), few_shot with three expert-scored examples, history / current_turn with the conversation context, and question / rubric with the sub-component criterion (Table 6 ).

Emotion-Aware Dialogue Generation

Emotion-aware dialogue generation adapts conversational responses to users’ feelings, context, and interaction goals across text, speech, and multimodal settings.

See all 54 papers

AI generates well-liked but templatic empathic responses
Apr 9, 2026Emma S. Gueorguieva, Hongli Zhan, Jina Suh +4Emotion-Aware Dialogue Generation Language Model Generation Evaluation
Department of Psychology, The University of Texas at Austin. · Department of Linguistics, The University of Texas at Austin. · Department of Computer Science and Engineering, The University of Washington. +2
Dual-Loop Self-Evolution via Verifiable Emotion Feedback for Multi-Turn Empathetic Dialogue
Aug 11, 2026Yi Wei, Shuo Jiang, Huaixia Dou +5Reinforcement Learning with Verifiable Rewards Curriculum Learning
Qwen DianJin Team, Alibaba Cloud Computing · Beihang University · School of Computer Science and Technology, Soochow University
Practicing with Language Models Cultivates Human Empathic Communication
Mar 16, 2026Aakriti Kumar, Nalin Poungpeth, Diyi Yang +2
Kellogg School of Management, Northwestern University. · Northwestern Institute on Complex Systems, Northwestern University. · Ryan Institute on Complexity, Northwestern University. +3

Apr 9, 2026J/K move · Enter open · S save

AI generates well-liked but templatic empathic responses

Emma S. Gueorguieva, Hongli Zhan, Jina Suh, Javier Hernandez+3

Department of Psychology, The University of Texas at Austin. · Department of Linguistics, The University of Texas at Austin. · Department of Computer Science and Engineering, The University of Washington.+2

Emotion-Aware Dialogue Generation Language Model Generation Evaluation

Open paper AskPDF arXiv

Recent research shows that greater numbers of people are turning to Large Language Models (LLMs) for emotional support, and that people rate LLM responses as more empathic than human-written responses. We suggest a reason for this success: LLMs have learned and consistently deploy a well-liked template for expressing empathy. We develop a taxonomy of 10 empathic language "tactics" that include validating someone's feelings and paraphrasing, and apply this taxonomy to characterize the language that people and LLMs produce when writing empathic responses. Across a set of 2 studies comparing a total of n = 3,265 AI-generated (by six models) and n = 1,290 human-written responses, we find that LLM responses are highly formulaic at a discourse functional level. We discovered a template -- a structured sequence of tactics -- that matches between 83--90% of LLM responses (and 60--83% in a held out sample), and when those are matched, covers 81--92% of the response. By contrast, human-written responses are more diverse. We end with a discussion of implications for the future of AI-generated empathy.

Abstract

Emotion-Aware Dialogue Generation

Explore similar work

AI generates well-liked but templatic empathic responses

Dual-Loop Self-Evolution via Verifiable Emotion Feedback for Multi-Turn Empathetic Dialogue

Practicing with Language Models Cultivates Human Empathic Communication