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.
What the Window Does Not Contain: Auditing Provenance in a Document-Grounded Instability Benchmark
Related stories
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 Computation and Language
Sep 10
In RAG We Trust? Measuring Robustness of Retrieval-Augmented Generation Under Document Poisoning
arXiv:2609.09243v1 Announce Type: cross Abstract: Retrieval-augmented generation (RAG) grounds a language model in retrieved documents, which reduces hallucination but creates a new attack surface: i...
arXiv Computation and Language
Oct 15
Confidently Wrong: Detecting Hallucinations in Financial Question Answering from LLM Internal States
arXiv:2607.11414v2 Announce Type: replace Abstract: Large language models (LLMs) in financial applications fail most consequentially when they are confidently wrong. Hedged, uncertain answers invite...
arXiv Computation and Language
Oct 9
CiteVQA: Benchmarking Evidence Attribution for Trustworthy Document Intelligence
CiteVQA is a benchmark that evaluates multimodal large language models on both answering document questions and providing element‑level bounding‑box citations for the evidence used. It contains 1,897 questions across 711 PDFs in seven domains and two languages, with ground‑truth citations generated via an automated pipeline and strict quality control. The evaluation metric, Strict Attributed Accuracy (SAA), rewards a prediction only when both the answer and the cited region are correct, revealing widespread attribution hallucination in current models.
arXiv Computation and Language
Sep 22
Re:CAP - Auditing Retrieval Coverage in Production RAG Pipelines
Re:CAP is a reference‑free audit loop for retrieval‑augmented generation (RAG) pipelines that probes for missing documents instead of enumerating all relevant ones. It identifies covered topics, generates probing questions, retrieves candidate documents, and uses an LLM judge to keep only those that add new information. On several benchmarks, Re:CAP recovers a significant portion of gold documents that flat BM25 or hybrid retrieval misses, and human evaluation shows most of these documents add new information.
arXiv AI
Oct 9
Large Language Model Turnover Undermines Screening for Artificial Intelligence-Assisted Scientific Writing
The study examines how the rapid turnover of large language models (LLMs) undermines the effectiveness of AI‑detectors used to screen scientific manuscripts. By comparing 4,000 PNAS abstracts rewritten by 23 different LLM versions released between June 2023 and August 2026, the authors show that detectors trained on past versions can fail dramatically at generation boundaries, missing up to 96% of rewrites just after a sharp transition. Even detectors updated to newer versions can overlook rewrites of older models, and a commercial detector missed most rewrites of the newest version while flagging few human‑written abstracts.
arXiv Computation and Language
Aug 31
Fidelity Is Not Enough: Dispatch-Level Instrumentation for Agentic Datasheet Extraction
The paper reports that a model can pass fidelity checks—verifying that extracted values match the source—without actually opening a datasheet, due to a hidden constraint that disables tool use. To address this, the authors log every tool call in an agentic benchmark and develop two instruments: a rule‑based failure‑attribution classifier and a silent‑failure detector that flags runs based solely on which tools were invoked. While the detector shows low false positives on clean extractions and recovers all planted faults, its recall against correct tool usage but incorrect answers remains unmeasured, and a partial causal chamber confirms only a subset of claims, highlighting limitations in physical verification.
arXiv AI
Jun 29
CalBrief: A Pilot Diagnostic Benchmark for Evidence-Calibrated Scientific Briefing with Large Language Models
arXiv:2606. 27383v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used as research assistants, yet it remains unclear whether they can calibrate research takeaways to the strength and scope of the supporting evidence.
arXiv Machine Learning
Aug 14
Are Large Language Models Reliable Reviewers? A Benchmark for Error Detection in Financial Documents
arXiv:2608. 12342v1 Announce Type: cross Abstract: Ensuring the accuracy of financial documents is critical for economic analysis, regulatory compliance, and corporate decision-making.
arXiv Machine Learning
Oct 3
When a Data Artifact Isn't a Shortcut: Causal Auditing of Synthetic RLVR Corpora
The paper audits whether synthetic distractors in RLVR corpora act as shortcuts for learning policies. A classifier using only surface statistics barely outperforms chance, and manual inspection reveals that code distractors are almost identical to correct answers. Experiments with a paraphrase‑matched control show no exploitation advantage for the unmodified data, indicating that the detectable artifact was not used by the policy.
arXiv AI
Aug 17
CLAIR-Fin: An Adversarial Multi-Agent Framework for Claim-Level Verification and Adaptive Debate in Cross-Modal Financial QA
arXiv:2608. 13706v1 Announce Type: cross Abstract: Existing defenses against hallucination in retrieval-augmented and multi-agent pipelines remain partial: evidence is trusted despite modality disagreement, debate verifies an aggregate report rather than individual claims, and such verification occurs only after drafting, leaving inter-agent errors undetected until the final text.