Research

Paper

AI LLM February 26, 2026

ClinDet-Bench: Beyond Abstention, Evaluating Judgment Determinability of LLMs in Clinical Decision-Making

Authors

Yusuke Watanabe, Yohei Kobashi, Takeshi Kojima, Yusuke Iwasawa, Yasushi Okuno, Yutaka Matsuo

Abstract

Clinical decisions are often required under incomplete information. Clinical experts must identify whether available information is sufficient for judgment, as both premature conclusion and unnecessary abstention can compromise patient safety. To evaluate this capability of large language models (LLMs), we developed ClinDet-Bench, a benchmark based on clinical scoring systems that decomposes incomplete-information scenarios into determinable and undeterminable conditions. Identifying determinability requires considering all hypotheses about missing information, including unlikely ones, and verifying whether the conclusion holds across them. We find that recent LLMs fail to identify determinability under incomplete information, producing both premature judgments and excessive abstention, despite correctly explaining the underlying scoring knowledge and performing well under complete information. These findings suggest that existing benchmarks are insufficient to evaluate the safety of LLMs in clinical settings. ClinDet-Bench provides a framework for evaluating determinability recognition, leading to appropriate abstention, with potential applicability to medicine and other high-stakes domains, and is publicly available.

Metadata

arXiv ID: 2602.22771
Provider: ARXIV
Primary Category: cs.AI
Published: 2026-02-26
Fetched: 2026-02-27 04:35

Related papers

Raw Data (Debug)
{
  "raw_xml": "<entry>\n    <id>http://arxiv.org/abs/2602.22771v1</id>\n    <title>ClinDet-Bench: Beyond Abstention, Evaluating Judgment Determinability of LLMs in Clinical Decision-Making</title>\n    <updated>2026-02-26T09:03:41Z</updated>\n    <link href='https://arxiv.org/abs/2602.22771v1' rel='alternate' type='text/html'/>\n    <link href='https://arxiv.org/pdf/2602.22771v1' rel='related' title='pdf' type='application/pdf'/>\n    <summary>Clinical decisions are often required under incomplete information. Clinical experts must identify whether available information is sufficient for judgment, as both premature conclusion and unnecessary abstention can compromise patient safety. To evaluate this capability of large language models (LLMs), we developed ClinDet-Bench, a benchmark based on clinical scoring systems that decomposes incomplete-information scenarios into determinable and undeterminable conditions. Identifying determinability requires considering all hypotheses about missing information, including unlikely ones, and verifying whether the conclusion holds across them. We find that recent LLMs fail to identify determinability under incomplete information, producing both premature judgments and excessive abstention, despite correctly explaining the underlying scoring knowledge and performing well under complete information. These findings suggest that existing benchmarks are insufficient to evaluate the safety of LLMs in clinical settings. ClinDet-Bench provides a framework for evaluating determinability recognition, leading to appropriate abstention, with potential applicability to medicine and other high-stakes domains, and is publicly available.</summary>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.AI'/>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.DB'/>\n    <published>2026-02-26T09:03:41Z</published>\n    <arxiv:comment>17 pages, 3 figures, 10 tables</arxiv:comment>\n    <arxiv:primary_category term='cs.AI'/>\n    <author>\n      <name>Yusuke Watanabe</name>\n    </author>\n    <author>\n      <name>Yohei Kobashi</name>\n    </author>\n    <author>\n      <name>Takeshi Kojima</name>\n    </author>\n    <author>\n      <name>Yusuke Iwasawa</name>\n    </author>\n    <author>\n      <name>Yasushi Okuno</name>\n    </author>\n    <author>\n      <name>Yutaka Matsuo</name>\n    </author>\n  </entry>"
}