@inproceedings{mehreen-etal-2026-empathy,
title = "Empathy Is Not the Scapegoat for Declines in Factuality and Reliability",
author = "Mehreen, Kanwal and
Shi, Letian and
Zhang, Deheng and
Wang, Yuxia",
editor = "Zhang, Yue and
Xu, Ruifeng and
Purwarianti, Ayu and
Rong, Tong and
Suzuki, Jun",
booktitle = "Proceedings of the 15th International Joint Conference on Natural Language Processing and the 5th Conference of the {A}sia-Pacific Chapter of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
month = nov,
year = "2026",
address = "Hengqin, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.aacl-long.86/",
pages = "1874--1902",
ISBN = "979-8-89176-439-2",
abstract = "Language models are increasingly expected to support users in stressful or uncertain situations, where warmth and empathy are desirable. While recent work links warmer models to lower factuality and reliability, we show that this conclusion is incomplete: prior studies often use warmth as a global persona and conflate tone effects with SFT data distribution shift. We revisit this issue through prompting, fine-tuning, factual robustness, and empathy evaluation, using an 11-dataset benchmark suite and EmoFact, a benchmark for factual accuracy under emotional context. Across three large language models, we find that warmth effects are task- and model-dependent, and that task-aligned adaptive tone can improve empathy while preserving reliability. We further train human-validated empathy evaluators to evaluate the output of our finetuned model. Our results suggest that models can be made more supportive in human relationships and social interactions without compromising overall reliability."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mehreen-etal-2026-empathy">
<titleInfo>
<title>Empathy Is Not the Scapegoat for Declines in Factuality and Reliability</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kanwal</namePart>
<namePart type="family">Mehreen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Letian</namePart>
<namePart type="family">Shi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Deheng</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuxia</namePart>
<namePart type="family">Wang</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>Proceedings of the 15th International Joint Conference on Natural Language Processing and the 5th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)</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">979-8-89176-439-2</identifier>
</relatedItem>
<abstract>Language models are increasingly expected to support users in stressful or uncertain situations, where warmth and empathy are desirable. While recent work links warmer models to lower factuality and reliability, we show that this conclusion is incomplete: prior studies often use warmth as a global persona and conflate tone effects with SFT data distribution shift. We revisit this issue through prompting, fine-tuning, factual robustness, and empathy evaluation, using an 11-dataset benchmark suite and EmoFact, a benchmark for factual accuracy under emotional context. Across three large language models, we find that warmth effects are task- and model-dependent, and that task-aligned adaptive tone can improve empathy while preserving reliability. We further train human-validated empathy evaluators to evaluate the output of our finetuned model. Our results suggest that models can be made more supportive in human relationships and social interactions without compromising overall reliability.</abstract>
<identifier type="citekey">mehreen-etal-2026-empathy</identifier>
<location>
<url>https://aclanthology.org/2026.aacl-long.86/</url>
</location>
<part>
<date>2026-11</date>
<extent unit="page">
<start>1874</start>
<end>1902</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Empathy Is Not the Scapegoat for Declines in Factuality and Reliability
%A Mehreen, Kanwal
%A Shi, Letian
%A Zhang, Deheng
%A Wang, Yuxia
%Y Zhang, Yue
%Y Xu, Ruifeng
%Y Purwarianti, Ayu
%Y Rong, Tong
%Y Suzuki, Jun
%S Proceedings of the 15th International Joint Conference on Natural Language Processing and the 5th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2026
%8 November
%I Association for Computational Linguistics
%C Hengqin, China
%@ 979-8-89176-439-2
%F mehreen-etal-2026-empathy
%X Language models are increasingly expected to support users in stressful or uncertain situations, where warmth and empathy are desirable. While recent work links warmer models to lower factuality and reliability, we show that this conclusion is incomplete: prior studies often use warmth as a global persona and conflate tone effects with SFT data distribution shift. We revisit this issue through prompting, fine-tuning, factual robustness, and empathy evaluation, using an 11-dataset benchmark suite and EmoFact, a benchmark for factual accuracy under emotional context. Across three large language models, we find that warmth effects are task- and model-dependent, and that task-aligned adaptive tone can improve empathy while preserving reliability. We further train human-validated empathy evaluators to evaluate the output of our finetuned model. Our results suggest that models can be made more supportive in human relationships and social interactions without compromising overall reliability.
%U https://aclanthology.org/2026.aacl-long.86/
%P 1874-1902
Markdown (Informal)
[Empathy Is Not the Scapegoat for Declines in Factuality and Reliability](https://aclanthology.org/2026.aacl-long.86/) (Mehreen et al., AACL-IJCNLP 2026)
ACL
- Kanwal Mehreen, Letian Shi, Deheng Zhang, and Yuxia Wang. 2026. Empathy Is Not the Scapegoat for Declines in Factuality and Reliability. In Proceedings of the 15th International Joint Conference on Natural Language Processing and the 5th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (Volume 1: Long Papers), pages 1874–1902, Hengqin, China. Association for Computational Linguistics.