Theory of mind inspired mental state reasoning with large language models for empathetic response generation

Abstract As conversational AI expands into emotionally sensitive domains such as mental health support and counseling, empathetic response generation has become a key research challenge. Existing empathetic dialogue systems either reflect the user’s surface level emotions or, when relying on external commonsense knowledge bases, capture only generic patterns. We propose a Theory of Mind inspired framework in which a large language model first infers the speaker’s five mental states of Belief, Desire, Emotion, Intent, and Knowledge from the multi turn dialogue history and then uses them as conditioning signals for empathetic response generation. A preliminary study on a theory of mind benchmark indicates that the LLMs employed perform reasonably on mental state inference in both multiple choice and free form settings. On an empathetic dialogue dataset, injecting the self generated inferences improved response quality under both automatic metrics and LLM as judge evaluation. In the LoRA fine-tuned setting, the ToM condition performed comparably to COMET, an external commonsense knowledge baseline, with higher ROUGE-L point estimates for all four backbones and a significant advantage for one. Shuffled and corrupted descriptions consistently degraded response quality, whereas the ToM condition and a context-grounded factual-summary control performed similarly, indicating that contextual grounding is the primary source of the benefit. These findings suggest that speaker grounded mental state reasoning can be an effective strategy for empathetic dialogue systems.

Authors

Institutions

Publication Details

Journal
Scientific Reports
Published
2026-11-16
DOI
https://doi.org/10.1038/s41598-026-77880-0
Primary Topic
Speech and dialogue systems
Type
article
Field-Weighted Citation Impact
0.00

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

Theory of mind inspired mental state reasoning with large language models for empathetic response generation

Hayoung Lee, Seonghee Lee
1 links
Scientific Reports
Speech and dialogue systems
article

Theory of mind inspired mental state reasoning with large language models for empathetic response generation

Hayoung Lee, Seonghee Lee
article en

Abstract

Abstract As conversational AI expands into emotionally sensitive domains such as mental health support and counseling, empathetic response generation has become a key research challenge. Existing empathetic dialogue systems either reflect the user’s surface level emotions or, when relying on external commonsense knowledge bases, capture only generic patterns. We propose a Theory of Mind inspired framework in which a large language model first infers the speaker’s five mental states of Belief, Desire, Emotion, Intent, and Knowledge from the multi turn dialogue history and then uses them as conditioning signals for empathetic response generation. A preliminary study on a theory of mind benchmark indicates that the LLMs employed perform reasonably on mental state inference in both multiple choice and free form settings. On an empathetic dialogue dataset, injecting the self generated inferences improved response quality under both automatic metrics and LLM as judge evaluation. In the LoRA fine-tuned setting, the ToM condition performed comparably to COMET, an external commonsense knowledge baseline, with higher ROUGE-L point estimates for all four backbones and a significant advantage for one. Shuffled and corrupted descriptions consistently degraded response quality, whereas the ToM condition and a context-grounded factual-summary control performed similarly, indicating that contextual grounding is the primary source of the benefit. These findings suggest that speaker grounded mental state reasoning can be an effective strategy for empathetic dialogue systems.

Scientific Reports
Electronics and Telecommunications Research Institute (KR), Korea Telecom (South Korea) (KR)
Electronics and Telecommunications Research Institute
Speech and dialogue systems
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon