Paper
FINEST: Improving LLM Responses to Sensitive Topics Through Fine-Grained Evaluation
Authors
Juhyun Oh, Nayeon Lee, Chani Jung, Jiho Jin, Junho Myung, Jongwon Lee, Taeui Song, Alice Oh
Abstract
Large Language Models (LLMs) often generate overly cautious and vague responses on 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.
Metadata
Related papers
Gen-Searcher: Reinforcing Agentic Search for Image Generation
Kaituo Feng, Manyuan Zhang, Shuang Chen, Yunlong Lin, Kaixuan Fan, Yilei Jian... • 2026-03-30
On-the-fly Repulsion in the Contextual Space for Rich Diversity in Diffusion Transformers
Omer Dahary, Benaya Koren, Daniel Garibi, Daniel Cohen-Or • 2026-03-30
Graphilosophy: Graph-Based Digital Humanities Computing with The Four Books
Minh-Thu Do, Quynh-Chau Le-Tran, Duc-Duy Nguyen-Mai, Thien-Trang Nguyen, Khan... • 2026-03-30
ParaSpeechCLAP: A Dual-Encoder Speech-Text Model for Rich Stylistic Language-Audio Pretraining
Anuj Diwan, Eunsol Choi, David Harwath • 2026-03-30
RAD-AI: Rethinking Architecture Documentation for AI-Augmented Ecosystems
Oliver Aleksander Larsen, Mahyar T. Moghaddam • 2026-03-30
Raw Data (Debug)
{
"raw_xml": "<entry>\n <id>http://arxiv.org/abs/2603.04123v1</id>\n <title>FINEST: Improving LLM Responses to Sensitive Topics Through Fine-Grained Evaluation</title>\n <updated>2026-03-04T14:41:54Z</updated>\n <link href='https://arxiv.org/abs/2603.04123v1' rel='alternate' type='text/html'/>\n <link href='https://arxiv.org/pdf/2603.04123v1' rel='related' title='pdf' type='application/pdf'/>\n <summary>Large Language Models (LLMs) often generate overly cautious and vague responses on 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.</summary>\n <category scheme='http://arxiv.org/schemas/atom' term='cs.CL'/>\n <published>2026-03-04T14:41:54Z</published>\n <arxiv:comment>Accepted to EACL 2026 Findings</arxiv:comment>\n <arxiv:primary_category term='cs.CL'/>\n <author>\n <name>Juhyun Oh</name>\n </author>\n <author>\n <name>Nayeon Lee</name>\n </author>\n <author>\n <name>Chani Jung</name>\n </author>\n <author>\n <name>Jiho Jin</name>\n </author>\n <author>\n <name>Junho Myung</name>\n </author>\n <author>\n <name>Jongwon Lee</name>\n </author>\n <author>\n <name>Taeui Song</name>\n </author>\n <author>\n <name>Alice Oh</name>\n </author>\n </entry>"
}