TCM-DiagCommit：基于 TCM-SD 的中医证据条件辨证选择与决策基准
TCM-DiagCommit: A TCM-SD-Derived Benchmark for Evidence-Conditioned Syndrome Selection and Commitment
AI 导读
研究者推出 TCM-DiagCommit 基准，将公开 TCM-SD/ZY-BERT 资源中的 1,834 个病例转换为覆盖 148 个证型标签的 23,842 条任务数据，用于评估中医辨证中的标签区分、证据更新与不确定性下的决策。
正文 · 原文
Abstract:Traditional Chinese Medicine (TCM) syndrome differentiation is usually evaluated as static final-label selection over complete clinical records. This setting hides three diagnostic behaviors: whether a model distinguishes semantic-neighbor syndrome labels from easy random distractors, whether it updates predictions as evidence fields are revealed, and whether it should commit under uncertainty. We introduce TCM-DiagCommit, a benchmark derived from the public TCM-SD/ZY-BERT resource while retaining its source syndrome labels; it converts 1,834 source cases into 23,842 task rows over 148 syndrome labels. The benchmark combines random, profile-neighbor, and full-vocabulary candidate ladders with staged t1/t2/t3 evidence. It also includes fixed-label tongue/pulse perturbations and insufficient-evidence variants. A benchmark-defined action contract scores commit, acquire, defer, and abstain. Across five zero-shot DirectLLM calibrations, random10 top-1 accuracy is 63.2% to 66.4%, but hard20 falls to 24.7% to 30.3% and full148 to 14.8% to 22.3%; on hard20, WT(all) wrong-terminal commits remain 62.2% to 74.3%. These results show that final-answer accuracy alone is insufficient for diagnostic benchmark evaluation: answer selection, evidence use, and benchmark commitment scoring should be measured separately.
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.37243 [cs.AI] |
| (or arXiv:2610.37243v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.37243 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Yue Hu [view email]
[v1]
Tue, 27 Oct 2026 13:46:04 UTC (598 KB)
来源：arXiv cs.AI · arxiv.org