Graph-to-text counterfactual verification for interpretable emotion recognition in conversation

Emotion Recognition in Conversation (ERC) requires models to infer utterance-level emotions from both local wording and dialogue-level context. Graph-based ERC methods capture speaker interactions and contextual dependencies, but their graph representations are usually consumed by task-specific classifiers. They are therefore difficult to expose to large language models (LLMs) as transparent reasoning evidence. In contrast, direct LLM prompting can generate explanations, but it often lacks explicit structural grounding and rarely compares alternative emotion hypotheses in a systematic way. To address these limitations, we propose GATOC-ERC, a graph-to-text counterfactual prompting framework for text-only ERC. The framework first builds an utterance-level dialogue graph to encode local conversational dependencies. A Producer and GraphTranslator pipeline then converts graph-derived node, neighbor, and relation information into textual graph-context summaries. These summaries can be used by a frozen LLM through standard text prompts. Given this graph-conditioned evidence, the model performs counterfactual emotion verification. It generates candidate-specific rationales for possible emotions and contrasts them to select the most contextually consistent label. Experiments on IEMOCAP and MELD show that GATOC-ERC achieves competitive text-only ERC performance while producing interpretable reasoning traces. Ablation, faithfulness, cross-dataset transfer, prompt sensitivity, and cost analyses further clarify the contribution and limitations of the graph-to-text interface and the counterfactual verification process.

Authors

Institutions

Publication Details

Journal
Frontiers in Artificial Intelligence
Published
2026-11-18
DOI
https://doi.org/10.3389/frai.2026.1926067
Primary Topic
Emotion and Mood Recognition
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

Graph-to-text counterfactual verification for interpretable emotion recognition in conversation

Zhenyu Deng, Zibo Xu, Jia Liu, Shibo Jin et al.
2 links
Frontiers in Artificial Intelligence
Emotion and Mood Recognition
article

Graph-to-text counterfactual verification for interpretable emotion recognition in conversation

Zhenyu Deng, Zibo Xu, Jia Liu, Shibo Jin, Xueliang Zhang
article en

Abstract

Emotion Recognition in Conversation (ERC) requires models to infer utterance-level emotions from both local wording and dialogue-level context. Graph-based ERC methods capture speaker interactions and contextual dependencies, but their graph representations are usually consumed by task-specific classifiers. They are therefore difficult to expose to large language models (LLMs) as transparent reasoning evidence. In contrast, direct LLM prompting can generate explanations, but it often lacks explicit structural grounding and rarely compares alternative emotion hypotheses in a systematic way. To address these limitations, we propose GATOC-ERC, a graph-to-text counterfactual prompting framework for text-only ERC. The framework first builds an utterance-level dialogue graph to encode local conversational dependencies. A Producer and GraphTranslator pipeline then converts graph-derived node, neighbor, and relation information into textual graph-context summaries. These summaries can be used by a frozen LLM through standard text prompts. Given this graph-conditioned evidence, the model performs counterfactual emotion verification. It generates candidate-specific rationales for possible emotions and contrasts them to select the most contextually consistent label. Experiments on IEMOCAP and MELD show that GATOC-ERC achieves competitive text-only ERC performance while producing interpretable reasoning traces. Ablation, faithfulness, cross-dataset transfer, prompt sensitivity, and cost analyses further clarify the contribution and limitations of the graph-to-text interface and the counterfactual verification process.

Frontiers in Artificial IntelligenceVol. 9
Tianjin University (CN), TianjinSino-German University of Applied Sciences (CN)
Emotion and Mood Recognition
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