@inproceedings{parmar-mazumdar-2025-emotionally,
title = "Emotionally Aware or Tone-Deaf? Evaluating Emotional Alignment in {LLM}-Based Conversational Recommendation Systems",
author = "Parmar, Darshna and
Mazumdar, Pramit",
editor = "Zhang, Chen and
Allaway, Emily and
Shen, Hua and
Miculicich, Lesly and
Li, Yinqiao and
M'hamdi, Meryem and
Limkonchotiwat, Peerat and
Bai, Richard He and
T.y.s.s., Santosh and
Han, Sophia Simeng and
Thapa, Surendrabikram and
Rim, Wiem Ben",
booktitle = "Proceedings of the 9th Widening NLP Workshop",
month = nov,
year = "2025",
address = "Suzhou, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.winlp-main.26/",
pages = "167--174",
ISBN = "979-8-89176-351-7",
abstract = "Recent advances in Large Language Models (LLMs) have enhanced the fluency and coherence of Conversational Recommendation Systems (CRSs), yet emotional intelligence remains a critical gap. In this study, we systematically evaluate the emotional behavior of six state-of-the-art LLMs in CRS settings using the ReDial and INSPIRED datasets. We propose an emotion-aware evaluation framework incorporating metrics such as Emotion Alignment, Emotion Flatness, and per-emotion F1-scores. Our analysis shows that most models frequently default to emotionally flat or mismatched responses, often misaligning with user affect (e.g., joy misread as neutral). We further examine patterns of emotional misalignment and their impact on user-centric qualities such as personalization, justification, and satisfaction. Through qualitative analysis, we demonstrate that emotionally aligned responses enhance user experience, while misalignments lead to loss of trust and relevance. This work highlights the need for emotion-aware design in CRS and provides actionable insights for improving affective sensitivity in LLM-generated recommendations."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="parmar-mazumdar-2025-emotionally">
<titleInfo>
<title>Emotionally Aware or Tone-Deaf? Evaluating Emotional Alignment in LLM-Based Conversational Recommendation Systems</title>
</titleInfo>
<name type="personal">
<namePart type="given">Darshna</namePart>
<namePart type="family">Parmar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pramit</namePart>
<namePart type="family">Mazumdar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 9th Widening NLP Workshop</title>
</titleInfo>
<name type="personal">
<namePart type="given">Chen</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Emily</namePart>
<namePart type="family">Allaway</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hua</namePart>
<namePart type="family">Shen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lesly</namePart>
<namePart type="family">Miculicich</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yinqiao</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Meryem</namePart>
<namePart type="family">M’hamdi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Peerat</namePart>
<namePart type="family">Limkonchotiwat</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Richard</namePart>
<namePart type="given">He</namePart>
<namePart type="family">Bai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Santosh</namePart>
<namePart type="family">T.y.s.s.</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sophia</namePart>
<namePart type="given">Simeng</namePart>
<namePart type="family">Han</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Surendrabikram</namePart>
<namePart type="family">Thapa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wiem</namePart>
<namePart type="given">Ben</namePart>
<namePart type="family">Rim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Suzhou, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-351-7</identifier>
</relatedItem>
<abstract>Recent advances in Large Language Models (LLMs) have enhanced the fluency and coherence of Conversational Recommendation Systems (CRSs), yet emotional intelligence remains a critical gap. In this study, we systematically evaluate the emotional behavior of six state-of-the-art LLMs in CRS settings using the ReDial and INSPIRED datasets. We propose an emotion-aware evaluation framework incorporating metrics such as Emotion Alignment, Emotion Flatness, and per-emotion F1-scores. Our analysis shows that most models frequently default to emotionally flat or mismatched responses, often misaligning with user affect (e.g., joy misread as neutral). We further examine patterns of emotional misalignment and their impact on user-centric qualities such as personalization, justification, and satisfaction. Through qualitative analysis, we demonstrate that emotionally aligned responses enhance user experience, while misalignments lead to loss of trust and relevance. This work highlights the need for emotion-aware design in CRS and provides actionable insights for improving affective sensitivity in LLM-generated recommendations.</abstract>
<identifier type="citekey">parmar-mazumdar-2025-emotionally</identifier>
<location>
<url>https://aclanthology.org/2025.winlp-main.26/</url>
</location>
<part>
<date>2025-11</date>
<extent unit="page">
<start>167</start>
<end>174</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Emotionally Aware or Tone-Deaf? Evaluating Emotional Alignment in LLM-Based Conversational Recommendation Systems
%A Parmar, Darshna
%A Mazumdar, Pramit
%Y Zhang, Chen
%Y Allaway, Emily
%Y Shen, Hua
%Y Miculicich, Lesly
%Y Li, Yinqiao
%Y M’hamdi, Meryem
%Y Limkonchotiwat, Peerat
%Y Bai, Richard He
%Y T.y.s.s., Santosh
%Y Han, Sophia Simeng
%Y Thapa, Surendrabikram
%Y Rim, Wiem Ben
%S Proceedings of the 9th Widening NLP Workshop
%D 2025
%8 November
%I Association for Computational Linguistics
%C Suzhou, China
%@ 979-8-89176-351-7
%F parmar-mazumdar-2025-emotionally
%X Recent advances in Large Language Models (LLMs) have enhanced the fluency and coherence of Conversational Recommendation Systems (CRSs), yet emotional intelligence remains a critical gap. In this study, we systematically evaluate the emotional behavior of six state-of-the-art LLMs in CRS settings using the ReDial and INSPIRED datasets. We propose an emotion-aware evaluation framework incorporating metrics such as Emotion Alignment, Emotion Flatness, and per-emotion F1-scores. Our analysis shows that most models frequently default to emotionally flat or mismatched responses, often misaligning with user affect (e.g., joy misread as neutral). We further examine patterns of emotional misalignment and their impact on user-centric qualities such as personalization, justification, and satisfaction. Through qualitative analysis, we demonstrate that emotionally aligned responses enhance user experience, while misalignments lead to loss of trust and relevance. This work highlights the need for emotion-aware design in CRS and provides actionable insights for improving affective sensitivity in LLM-generated recommendations.
%U https://aclanthology.org/2025.winlp-main.26/
%P 167-174
Markdown (Informal)
[Emotionally Aware or Tone-Deaf? Evaluating Emotional Alignment in LLM-Based Conversational Recommendation Systems](https://aclanthology.org/2025.winlp-main.26/) (Parmar & Mazumdar, WiNLP 2025)
ACL