Omissions

Follow this topic Ask about this topic

Momentum

1 paper in the last four weeks, against 1 the four weeks before. 0.0% of all new papers.

Jul 6Week of Sep 21

Latest papers 13

All topics

LLM Judges Verify Presence, Not Absence: Omission Blindness in AI Clinical Notes and What Recovers It
Aug 31, 2026Sebastian Fox, Luke Markham, Ryan Lail +1Omissions Model Auditing
Composo
Positive-Unlabeled Preference Optimization For Chest X-ray Report Generation
Aug 5, 2026Yuta Kobayashi, Pradyun Ramesh, Muhammad Ahmed Chaudhry +5Radiology Report Generation Medical Vision-Language Models
Columbia University · Stanford University · Emory University
Judging Is Not Enumerating: Silent Omissions in LLM-Authored Acceptable Sets
Aug 2, 2026Wenhui Chen, Jianlin Chen, Ziyao Lin +2Omissions Assessment
University of Macau · South China University of Technology · Independent Researcher
Subtract, Transport, or Replay? Auditable Deletion from Language-Model Memory
Jul 30, 2026Vishwajith RameshLarge Language Model Memory Deletion
Vy Labs, Inc.
Where Facts Go Missing: A Layerwise Taxonomy and Per-Layer Attribution of Information Omission in Air-Gapped LLMAgent Pipelines
Jul 24, 2026Santhiya RajanOmissions Reasoning Gaps
Multiverse Computing
CARE: A Conformal Safety Layer for Medical Summarization
Jun 8, 2026Suhana Bedi, Bridget Lin, Anson Y. Zhou +5Summarization Large Language Model Safety
Department of Biomedical Data Science, Stanford University · Department of Anesthesiology, Perioperative and Pain Medicine, Stanford University · Department of Computer Science, Stanford University +2
From Statute to Control Flow: Span-Grounded Deontic Trees for Defeasible Scope Parsing
Jun 8, 2026Jian Chen, Siyuan Li, Chucheng Wan +1Legal Natural Language Processing Benchmarks Omissions
The Hong Kong University of Science and Technology (Guangzhou) Guangzhou, China · Sun Yat-Sen University Guangzhou, China
Diagnosing and Correcting Concept Omission in Multimodal Diffusion Transformers
May 14, 2026Kanghyun Baek, Jaihyun Lew, Chaehun Shin +2Diffusion Transformers Omissions
Interdisciplinary Program in Artificial Intelligence, Seoul National University, Seoul, South Korea · Department of Electrical and Computer Engineering, Seoul National University, Seoul, South Korea · Department of Computer Science & Engineering, Korea University, Seoul, South Korea +1
To Whom Do Language Models Align? Measuring Principal Hierarchies Under High-Stakes Competing Demands
May 12, 2026Fangyi Yu, Nabeel Seedat, Jonathan Richard Schwarz +1High-Stakes Domains Social Norms
Thomson Reuters Foundational Research, 5 Canada Square, London · Imperial College London · University of Oxford
Omission Constraints Decay While Commission Constraints Persist in Long-Context LLM Agents
Apr 22, 2026Yeran GamageCompliance Omissions
University of South Florida · Independent AI Security Researcher
Bureaucratic Silences: What the Canadian AI Register Reveals, Omits, and Obscures
Apr 16, 2026Dipto Das, Christelle Tessono, Syed Ishtiaque Ahmed +1Eu Artificial Intelligence Act Transparency
Department of Computer Science · University of Toronto · Toronto, Ontario, Canada +1
IatroBench: A Pre-Registered Benchmark of Clinical Omission in Language Models
Apr 9, 2026David GringrasOmissions Large Language Model Safety
Harvard T.H. Chan School of Public Health
Delta-K: Boosting Multi-Instance Generation via Cross-Attention Augmentation
Mar 10, 2026Zitong Wang, Zijun Shen, Haohao Xu +2Omissions
School of Software Engineering, Sun Yat-sen University · Nanjing University · College of Management and Economics, Tianjin University

Aug 31, 2026, cs.CLJ/K move · Enter open · S save

LLM Judges Verify Presence, Not Absence: Omission Blindness in AI Clinical Notes and What Recovers It

Sebastian Fox, Luke Markham, Ryan Lail, Michael Karotsieris

Composo

Omissions Model Auditing Large Language Model Judges False-Negative Rate

Open paper AskPDF arXiv

Ambient AI scribes draft clinical notes, and published audits find their dominant error is omission: information the encounter established that the note fails to record. The standard check is an LLM judge: a second model reads the note against the transcript and flags problems. We ask whether judges detect omissions. Public corpora cannot supply the answer key: their clinician reference notes and transcripts are materially discrepant. Our benchmark has 500 single-error note pairs from audited fact sheets, 298 with a named fact certainly absent and 202 added-or-altered controls. Across eight judge designs, paired discrimination (the flawed note below its clean twin, 0.5 a coin flip) reads 0.79-0.94 on added or altered content and 0.50-0.63 on omissions. On single notes, no design flags omissions reliably more often than perfect notes. Wording changes, voting and GEPA prompt optimisation move the operating point without creating usable detection. Restructuring the task recovers it: list the facts the transcript establishes, then check the note for each. Two methods reach it independently and trade off: a per-fact pipeline, and a GEPA-evolved prompt doing the same in one call. The pipeline's flags name the missing fact and its severity at 2.7% false alarms. The single call detects more (36.9% against 24.6%, p=0.002) at 6.2% false alarms and a tenth of the cost per note. A physician author validated 70 items and, where the two routes disagree, sided with the pipeline on 10 of 10 (p=0.002). A second clinician, not an author, graded the severity rubric blind and agrees to within a grade. On real vendor notes from a companion census no benchmark threshold transfers, but the re-calibrated single call detects more than the best of the eight at half its false-alarm rate. Omissions whose fact is restated elsewhere defeat both routes. We release the benchmark, prompts and judgements.

Momentum

Related topics

Latest papers 13