@inproceedings{wang-etal-2026-selective,
title = "Selective Reflection for Context-Sensitive Emotion Recognition in Conversation",
author = "Wang, Xinyu and
Feng, Weijie and
Wang, Hongchuang and
Cheng, Zhiyong",
editor = "Zhang, Yue and
Xu, Ruifeng and
Purwarianti, Ayu and
Rong, Tong and
Suzuki, Jun",
booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {IJCNLP}-{AACL} 2026",
month = nov,
year = "2026",
address = "Hengqin, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.findings-aacl.126/",
pages = "2466--2481",
ISBN = "979-8-89176-444-6",
abstract = "Recent advances in Large Language Models have transformed Emotion Recognition in Conversation, yet existing instruction-tuned approaches still produce high-confidence misjudgments on utterances whose surface text is weakly informative but whose emotion depends on the surrounding situation. We propose SRERC, a selective reflective correction framework for LLM-based ERC. SRERC uses a verdict teacher to assess contextual support for the first-pass prediction and triggers reflective decoding only when reflection has an actionable role. For selected cases, an SRC generator constructs a Scene-aware Reflection Context, which provides target-specific situational grounding and verification probes for an SRC-conditioned second pass. This gated design enables targeted correction while preserving non-gated predictions and limiting unnecessary over-correction. Experiments on IEMOCAP, MELD, and EmoryNLP show that SRERC achieves the highest average weighted-F1 across the three benchmarks, with diagnostic gains on context-sensitive cases where surface cues are insufficient or misleading."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wang-etal-2026-selective">
<titleInfo>
<title>Selective Reflection for Context-Sensitive Emotion Recognition in Conversation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Xinyu</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Weijie</namePart>
<namePart type="family">Feng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hongchuang</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhiyong</namePart>
<namePart type="family">Cheng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: IJCNLP-AACL 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yue</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruifeng</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ayu</namePart>
<namePart type="family">Purwarianti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tong</namePart>
<namePart type="family">Rong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jun</namePart>
<namePart type="family">Suzuki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Hengqin, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-444-6</identifier>
</relatedItem>
<abstract>Recent advances in Large Language Models have transformed Emotion Recognition in Conversation, yet existing instruction-tuned approaches still produce high-confidence misjudgments on utterances whose surface text is weakly informative but whose emotion depends on the surrounding situation. We propose SRERC, a selective reflective correction framework for LLM-based ERC. SRERC uses a verdict teacher to assess contextual support for the first-pass prediction and triggers reflective decoding only when reflection has an actionable role. For selected cases, an SRC generator constructs a Scene-aware Reflection Context, which provides target-specific situational grounding and verification probes for an SRC-conditioned second pass. This gated design enables targeted correction while preserving non-gated predictions and limiting unnecessary over-correction. Experiments on IEMOCAP, MELD, and EmoryNLP show that SRERC achieves the highest average weighted-F1 across the three benchmarks, with diagnostic gains on context-sensitive cases where surface cues are insufficient or misleading.</abstract>
<identifier type="citekey">wang-etal-2026-selective</identifier>
<location>
<url>https://aclanthology.org/2026.findings-aacl.126/</url>
</location>
<part>
<date>2026-11</date>
<extent unit="page">
<start>2466</start>
<end>2481</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Selective Reflection for Context-Sensitive Emotion Recognition in Conversation
%A Wang, Xinyu
%A Feng, Weijie
%A Wang, Hongchuang
%A Cheng, Zhiyong
%Y Zhang, Yue
%Y Xu, Ruifeng
%Y Purwarianti, Ayu
%Y Rong, Tong
%Y Suzuki, Jun
%S Findings of the Association for Computational Linguistics: IJCNLP-AACL 2026
%D 2026
%8 November
%I Association for Computational Linguistics
%C Hengqin, China
%@ 979-8-89176-444-6
%F wang-etal-2026-selective
%X Recent advances in Large Language Models have transformed Emotion Recognition in Conversation, yet existing instruction-tuned approaches still produce high-confidence misjudgments on utterances whose surface text is weakly informative but whose emotion depends on the surrounding situation. We propose SRERC, a selective reflective correction framework for LLM-based ERC. SRERC uses a verdict teacher to assess contextual support for the first-pass prediction and triggers reflective decoding only when reflection has an actionable role. For selected cases, an SRC generator constructs a Scene-aware Reflection Context, which provides target-specific situational grounding and verification probes for an SRC-conditioned second pass. This gated design enables targeted correction while preserving non-gated predictions and limiting unnecessary over-correction. Experiments on IEMOCAP, MELD, and EmoryNLP show that SRERC achieves the highest average weighted-F1 across the three benchmarks, with diagnostic gains on context-sensitive cases where surface cues are insufficient or misleading.
%U https://aclanthology.org/2026.findings-aacl.126/
%P 2466-2481
Markdown (Informal)
[Selective Reflection for Context-Sensitive Emotion Recognition in Conversation](https://aclanthology.org/2026.findings-aacl.126/) (Wang et al., Findings 2026)
ACL