arXiv cs.CL· Ziyuan Li, Juncheng Ni, Feng Li·· 12 小时前AI 评分26
EviGround-CT：用句子到体素定位验证 LLM 生成的胸部 CT 报告
EviGround-CT: Sentence-to-Volume Grounding for Verifying LLM-Generated Chest CT Reports
AI 导读
EviGround-CT 通过确定性提取器识别阳性发现句子，再用 3D 定位模型为每句预测证据掩码，以验证 LLM 生成的胸部 CT 报告。
正文
Abstract:Chest computed tomography (CT) reports generated by large language models (LLMs) can describe positive findings that lack localized evidence in the scan. We propose EviGround-CT to verify these findings after report generation. A deterministic extractor identifies positive finding sentences, and a 3D grounding model predicts an evidence mask for each sentence. Using the full sentence retains anatomical location, laterality, and descriptive modifiers in the grounding query. We evaluate report generation on CT-RATE, and grounding and verification on a held-out 100-case ReXGroundingCT subset. Using the available annotations, sentence-grounded verification raises evidence-supported precision (ESP) from 0.263 to 0.365 across 137 extracted in-scope positives, compared with category conditioning. The corresponding unsupported positive finding rate falls from 0.737 to 0.635. The paired case-level bootstrap ESP difference is +0.102 (95% confidence interval: [0.028, 0.181]). The predicted masks associate individual report statements with spatial evidence that can be inspected alongside the CT.
| Comments: | Accepted at IEEE BIBM 2026 |
| Subjects: | Computation and Language (cs.CL); Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG) |
| Cite as: | arXiv:2610.33038 [cs.CL] |
| (or arXiv:2610.33038v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2610.33038 arXiv-issued DOI via DataCite |
Submission history
From: Ziyuan Li [view email]
[v1]
Thu, 15 Oct 2026 09:14:43 UTC (724 KB)
来源：arXiv cs.CL · arxiv.org