@inproceedings{oh-etal-2026-finest,
title = "{FINEST}: Improving {LLM} Responses to Sensitive Topics Through Fine-Grained Evaluation",
author = "Oh, Juhyun and
Lee, Nayeon and
Jung, Chani and
Jin, Jiho and
Myung, Junho and
Lee, Jongwon and
Song, Taieui and
Oh, Alice",
editor = "Demberg, Vera and
Inui, Kentaro and
Marquez, Llu{\'i}s",
booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {EACL} 2026",
month = mar,
year = "2026",
address = "Rabat, Morocco",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.findings-eacl.327/",
pages = "6207--6226",
ISBN = "979-8-89176-386-9",
abstract = "Large Language Models (LLMs) often default to overly cautious and vague responses when handling sensitive topics, sacrificing helpfulness for safety. Existing evaluation frameworks lack systematic methods to identify and address specific weaknesses in responses to sensitive topics, making it difficult to improve both safety and helpfulness simultaneously. To address this, we introduce FINEST, a FINE-grained response evaluation taxonomy for Sensitive Topics, which breaks down helpfulness and harmlessness into errors across three main categories: Content, Logic, and Appropriateness. Experiments on a Korean-sensitive question dataset demonstrate that our score- and error-based improvement pipeline, guided by FINEST, significantly improves the model responses across all three categories, outperforming refinement without guidance. Notably, score-based improvement{---}providing category-specific scores and justifications{---}yields the most significant gains, reducing the error sentence ratio for Appropriateness by up to 33.09{\%}. This work lays the foundation for a more explainable and comprehensive evaluation and improvement of LLM responses to sensitive questions."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="oh-etal-2026-finest">
<titleInfo>
<title>FINEST: Improving LLM Responses to Sensitive Topics Through Fine-Grained Evaluation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Juhyun</namePart>
<namePart type="family">Oh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nayeon</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chani</namePart>
<namePart type="family">Jung</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiho</namePart>
<namePart type="family">Jin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Junho</namePart>
<namePart type="family">Myung</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jongwon</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Taieui</namePart>
<namePart type="family">Song</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alice</namePart>
<namePart type="family">Oh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-03</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EACL 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Vera</namePart>
<namePart type="family">Demberg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kentaro</namePart>
<namePart type="family">Inui</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lluís</namePart>
<namePart type="family">Marquez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Rabat, Morocco</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-386-9</identifier>
</relatedItem>
<abstract>Large Language Models (LLMs) often default to overly cautious and vague responses when handling sensitive topics, sacrificing helpfulness for safety. Existing evaluation frameworks lack systematic methods to identify and address specific weaknesses in responses to sensitive topics, making it difficult to improve both safety and helpfulness simultaneously. To address this, we introduce FINEST, a FINE-grained response evaluation taxonomy for Sensitive Topics, which breaks down helpfulness and harmlessness into errors across three main categories: Content, Logic, and Appropriateness. Experiments on a Korean-sensitive question dataset demonstrate that our score- and error-based improvement pipeline, guided by FINEST, significantly improves the model responses across all three categories, outperforming refinement without guidance. Notably, score-based improvement—providing category-specific scores and justifications—yields the most significant gains, reducing the error sentence ratio for Appropriateness by up to 33.09%. This work lays the foundation for a more explainable and comprehensive evaluation and improvement of LLM responses to sensitive questions.</abstract>
<identifier type="citekey">oh-etal-2026-finest</identifier>
<location>
<url>https://aclanthology.org/2026.findings-eacl.327/</url>
</location>
<part>
<date>2026-03</date>
<extent unit="page">
<start>6207</start>
<end>6226</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T FINEST: Improving LLM Responses to Sensitive Topics Through Fine-Grained Evaluation
%A Oh, Juhyun
%A Lee, Nayeon
%A Jung, Chani
%A Jin, Jiho
%A Myung, Junho
%A Lee, Jongwon
%A Song, Taieui
%A Oh, Alice
%Y Demberg, Vera
%Y Inui, Kentaro
%Y Marquez, Lluís
%S Findings of the Association for Computational Linguistics: EACL 2026
%D 2026
%8 March
%I Association for Computational Linguistics
%C Rabat, Morocco
%@ 979-8-89176-386-9
%F oh-etal-2026-finest
%X Large Language Models (LLMs) often default to overly cautious and vague responses when handling sensitive topics, sacrificing helpfulness for safety. Existing evaluation frameworks lack systematic methods to identify and address specific weaknesses in responses to sensitive topics, making it difficult to improve both safety and helpfulness simultaneously. To address this, we introduce FINEST, a FINE-grained response evaluation taxonomy for Sensitive Topics, which breaks down helpfulness and harmlessness into errors across three main categories: Content, Logic, and Appropriateness. Experiments on a Korean-sensitive question dataset demonstrate that our score- and error-based improvement pipeline, guided by FINEST, significantly improves the model responses across all three categories, outperforming refinement without guidance. Notably, score-based improvement—providing category-specific scores and justifications—yields the most significant gains, reducing the error sentence ratio for Appropriateness by up to 33.09%. This work lays the foundation for a more explainable and comprehensive evaluation and improvement of LLM responses to sensitive questions.
%U https://aclanthology.org/2026.findings-eacl.327/
%P 6207-6226
Markdown (Informal)
[FINEST: Improving LLM Responses to Sensitive Topics Through Fine-Grained Evaluation](https://aclanthology.org/2026.findings-eacl.327/) (Oh et al., Findings 2026)
ACL
- Juhyun Oh, Nayeon Lee, Chani Jung, Jiho Jin, Junho Myung, Jongwon Lee, Taieui Song, and Alice Oh. 2026. FINEST: Improving LLM Responses to Sensitive Topics Through Fine-Grained Evaluation. In Findings of the Association for Computational Linguistics: EACL 2026, pages 6207–6226, Rabat, Morocco. Association for Computational Linguistics.