arXiv AI August 18, 2026 By Bhaskar Gurram

Valid Per-Field Selective Risk Control for Document Extraction: Three Failure Modes, a Validity Ladder, and When Conditioning Pays

arXiv:2608. 14639v1 Announce Type: cross Abstract: Per-field accept/review with selective risk at most alpha -- accept a field only if the error rate among accepted fields is controlled -- is the trust contract document-extraction systems need, and the natural procedure silently violates it on real documents.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv AI.

llms

arXiv AI

Aug 11

Private Anytime Selective-Risk Certification for Federated Retrieval-Augmented Generation: Guarantees and Empirical Limits

arXiv:2608. 07913v1 Announce Type: cross Abstract: Selective-risk certificates promise that accepted outputs meet a declared error target.

By Sanjeda Akter, Ibne Farabi Shihab, Anuj Sharma

rag nlp safety

arXiv Machine Learning

Jul 27

SURE-RAG: Sufficiency and Uncertainty-Aware Evidence Verification for Selective Retrieval-Augmented Generation

arXiv:2605. 03534v2 Announce Type: replace-cross Abstract: Retrieval-augmented generation (RAG) grounds answers in retrieved passages, yet relevance does not guarantee sufficiency: a topical passage may still fail to justify the answer.

By Jingxi Qiu, Zeyu Han, Cheng Huang

llms rag benchmarks safety

Hugging Face Trending Papers

Jul 30

Share the Judge, Learn the Deferral: Where Specialization Helps LLM Evaluation

Agentic systems have widened the gap between producing candidate outputs and reviewing them. This paper asks a practical architectural question: should domain specialization be built into an evaluator's weights, or into the rule that decides when its judgment can be trusted?

llms agents fine-tuning

arXiv Machine Learning

Aug 11

Quality-Diversity Stress Tests for Process Reward Models:What Archive Coverage Can and Cannot Certify

arXiv:2608. 08008v1 Announce Type: new Abstract: Process reward models (PRMs) score intermediate reasoning steps and are widely used for search, ranking, and training, but optimization can exploit these learned proxies by increasing reward while turning correct reasoning into incorrect reasoning.

By Ibne Farabi Shihab, Fariya Afrin

fine-tuning safety

arXiv AI

Jul 23

Unlearning as Distribution Restoration: A Controlled Counterfactual Study, a Validated Selective Screen, and the Limits of Oracle-Free Certification

arXiv:2607. 19442v1 Announce Type: cross Abstract: Machine unlearning is commonly evaluated by matching a retrained oracle on trained probes.

By Sen Yang, Yuen-Hei Yeung

benchmarks

Hugging Face Trending Papers

Aug 8

Private Anytime Selective-Risk Certification for Federated Retrieval-Augmented Generation: Guarantees and Empirical Limits

Selective-risk certificates promise that accepted outputs meet a declared error target. We develop Fed-SRC, a score-agnostic certificate for federated, differentially private, adaptively monitored retrieval-augmented generation.

rag nlp safety

Related stories

Private Anytime Selective-Risk Certification for Federated Retrieval-Augmented Generation: Guarantees and Empirical Limits

SURE-RAG: Sufficiency and Uncertainty-Aware Evidence Verification for Selective Retrieval-Augmented Generation

Share the Judge, Learn the Deferral: Where Specialization Helps LLM Evaluation

Quality-Diversity Stress Tests for Process Reward Models:What Archive Coverage Can and Cannot Certify

Unlearning as Distribution Restoration: A Controlled Counterfactual Study, a Validated Selective Screen, and the Limits of Oracle-Free Certification

Private Anytime Selective-Risk Certification for Federated Retrieval-Augmented Generation: Guarantees and Empirical Limits