arXiv Machine Learning
Jun 9
Decoy-Calibrated Failure Audits for Language Models
arXiv:2606. 09046v1 Announce Type: new Abstract: Useful audits reveal not only how often a model fails, but also where its failures concentrate.
Prior Audit-Repair Context Shifts LLM Verifier Thresholds Toward Leniency
arXiv:2608. 16003v1 Announce Type: new Abstract: Automated checking pipelines increasingly place one language model as the checker and another (or the same one) as the fixer.
Related stories
arXiv AI
Aug 18
What Do Compliance Detectors Read? An Audit of Activation Probes and Guard Models
arXiv:2608. 16852v1 Announce Type: new Abstract: Regulatory compliance monitoring in deployed language models is increasingly implemented as a legal and audit control, checking model outputs against written rules spanning data protection, healthcare, financial regulation, and platform policy.
arXiv AI
Aug 12
Similarity Gates Approve Reversals: A Validity Audit of Embedding-Cosine Thresholds in Agent Systems
arXiv:2608. 10216v1 Announce Type: cross Abstract: Agent frameworks ship quality gates that compare text blocks by embedding-cosine similarity and decide at a fixed cutoff.
arXiv AI
Sep 17
Beyond Accuracy: How Procedural Traces Shift the Decision Criterion of LLM Overseers
The paper investigates how procedural traces—detailed step-by-step accounts of a language model’s reasoning—affect the decision-making of LLM overseers tasked with auditing another model’s outputs. Using signal detection theory, the authors evaluated five overseers on 19 compliance tasks, finding that while error detection remains high when disconfirming evidence is always visible, more elaborate traces shift the decision criterion toward rejection, leading to increased false alarms. The study also shows that providing option labels reduces the stated inability to link evidence to options, yet some overseers still exhibit residual rejection of correct work that grows with trace detail.
arXiv Machine Learning
Jun 15
Code Correctness Signals in LLM Hidden States: Pre-Generation Probing and Repair Geometry
arXiv:2606. 14530v1 Announce Type: new Abstract: Large language models encode rich information in their hidden states.
arXiv AI
Sep 1
LLM Judges Verify Presence, Not Absence: Omission Blindness in AI Clinical Notes and What Recovers It
arXiv:2608.31016v1 Announce Type: cross Abstract: Ambient AI scribes draft clinical notes, and published audits find their dominant error is omission: information the encounter established that the n...
arXiv Computation and Language
Aug 31
Why Didn't It Check? Unsupported Final Claims and Their Repair in Two Tool-Equipped Language Models
The study investigates how language models equipped with tools can still produce unsupported final claims, even when a single tool call could resolve the uncertainty. It defines two metrics—occurrence (how often unsupported claims arise) and conditional repair (how often they are fixed when evidence is provided). Experiments on Qwen3-32B and Gemma 4 show that providing the missing evidence consistently repairs all unsupported claims in the Qwen3-32B setup, while the Gemma 4 model never produced unsupported claims under the tested conditions.
arXiv AI
Aug 26
More Rejective, Not More Discriminative: The Unit of Verification in Pre-Execution LLM Oversight
The paper introduces the twin‑prefix framework to evaluate how the size of the verification unit—i.e., how many actions a pre‑execution LLM monitor reviews in one call—affects its performance. By pairing each gold plan with a twin that differs by a single write and injecting a controlled error, the authors isolate the impact of review length on catch rates and false rejections. Their findings show that longer review windows increase rejection rates but do not improve discrimination, with the highest informedness occurring at one or two actions across all judges and domains.
arXiv Computation and Language
3d ago
Safety Monitors Mostly Catch What the Model Already Refuses
The paper evaluates safety monitors by measuring recall only on prompts that the target model actually answers, rather than on all harmful prompts. Across several guard systems, recall at a 1% false‑positive rate drops sharply when focusing on answered prompts, with monitors catching refused requests 1.1–6.4 times more often than answered ones. Rewriting prompts to be less explicit dramatically increases compliance and reveals that many harmful requests slip past monitors, especially when phrasing is softened. Fine‑tuning guards on these rewritten prompts improves recall from 0.24 to 0.89 on answered requests and generalizes to unseen benchmarks.
arXiv AI
Aug 3
Validation Evidence in LLM Repair Agents: How Much of What Passes Actually Tests the Bug?
arXiv:2607. 28871v1 Announce Type: cross Abstract: When a repair agent runs a test and sees it pass, the result is treated as evidence about the reported defect.
arXiv Computation and Language
Sep 10
When Auditors Fabricate: Batch-Size Degradation and Confident Hallucination in LLM Detection of Planted Document Contamination
arXiv:2609.09696v1 Announce Type: new Abstract: Large language models are increasingly proposed as automated auditors of document quality, yet their reliability as detectors of planted errors is poor...
arXiv AI
Jul 28
Task-Conditional Faithfulness Auditing of Multimodal LLMs for Grid Diagnosis
arXiv:2607. 24539v1 Announce Type: new Abstract: Multimodal large language models (LLMs) can combine topology, measurements, and incident text for grid diagnosis, yet answer accuracy does not establish that task-appropriate evidence was used.