arXiv Machine Learning July 7, 2026 By Weixin Liu, Congning Ni, Qingyuan Song, Susannah L. Rose, Murat Kantarcioglu, Bradley A. Malin, Zhijun Yin

Coverage-Controlled Preference Mining from Noisy Claim Verification for Evidence-Grounded Generation

Read the original on arXiv Machine Learning →

arXiv:2603. 10494v2 Announce Type: replace-cross Abstract: Evidence-grounded generation produces summaries whose claims should be supported by supplied evidence, but claim-level verifiers provide noisy feedback and can reward models that simply say less.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

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

arXiv Machine Learning

Jul 24

Best-of-Evidence: Best-of-N Selection under Partial Verification

arXiv:2607. 20950v1 Announce Type: new Abstract: BoN improves model outputs by sampling several candidates and selecting one with a proxy score, but it assumes that complete candidates can be evaluated reliably.

By Cenwei Zhang, Teng Fang, Yuxia Wang, Derek Li, Bryan Dai, Lei You

multimodal

arXiv Computation and Language

Sep 14

MedSNIP: Building and Benchmarking Snippet-Level Granularity for Medical Fact Verification

arXiv:2609.12884v1 Announce Type: new Abstract: A medical claim's correctness often depends not on the claim alone, but on the clinical structure around it. A claim may require a lab reference range,...

By Hasan Iqbal, Sarfraz Ahmad, Hyunjae Kim, Sihyeon Park, Junjie Liao, Qingyu Chen, Preslav Nakov, Yuxia Wang

rag benchmarks

arXiv AI

Jun 2

Hallucination Detection-Guided Preference Optimization for Clinical Summarization

arXiv:2605. 28910v2 Announce Type: replace-cross Abstract: Large language models (LLMs) have shown promise on summarization tasks, but they often produce hallucinations, which are unsupported or incorrect statements that limit their reliability in specialized healthcare applications.

By Shamanth Kuthpadi Seethakantha, Dung Ngoc Thai, Vara Prasad Gudi, Simran Tiwari, Rami Matar, Avijit Mitra, Wenlong Zhao, Andrew McCallum, Wael Salloum

llms nlp fine-tuning safety

arXiv Computation and Language

Sep 17

EviGen: Predictive Evidence Scaffolding for Verifiable Clinical Rationale Generation

arXiv:2609.18852v1 Announce Type: new Abstract: Longitudinal electronic health records (EHRs) capture years of patient history across notes, codes, labs, and procedures, and contain evidence needed t...

By Fengnan Li, Heman Burre, Liwen Sun, Roshni Varma, Matthew M. Engelhard

llms rag

Hugging Face Trending Papers

Jul 23

Best-of-Evidence: Best-of-N Selection under Partial Verification

BoN improves model outputs by sampling several candidates and selecting one with a proxy score, but it assumes that complete candidates can be evaluated reliably. Many vision-language tasks instead provide only partial verification: a finding, span, value, region, or relation may be checkable even when no dependable whole-response verifier exists.

multimodal

One email a morning, machine-written

Related stories

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

Best-of-Evidence: Best-of-N Selection under Partial Verification

MedSNIP: Building and Benchmarking Snippet-Level Granularity for Medical Fact Verification

Hallucination Detection-Guided Preference Optimization for Clinical Summarization

EviGen: Predictive Evidence Scaffolding for Verifiable Clinical Rationale Generation

Best-of-Evidence: Best-of-N Selection under Partial Verification