Evidence-Grounded Generation

Overview

Evidence-grounded generation studies how language models can use documents, databases, images, and other sources to produce claims that readers can verify. Common approaches include retrieval-augmented generation, claim-level verification, evidence graphs, citation alignment, and abstention when support is insufficient. Benchmarks increasingly test not only answer accuracy but also whether each claim is supported by the cited evidence, including in medical, scientific, legal, and long-form tasks. A central challenge remains that retrieving relevant evidence does not ensure models will integrate it faithfully, and stricter grounding can trade off against coverage, fluency, or efficiency.

Latest papers

CardsList

156 papers7 papers in the last four weeks, down 72% on the four weeks before. 0.1% of all new papers.

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

    Mar 11, 2026Weixin Liu, Congning Ni, Qingyuan Song +4Claim VerificationHealthcare

  2. Coordinated Semantic Alignment and Evidence Constraints for Retrieval-Augmented Generation with Large Language Models

    Mar 4, 2026Xin Chen, Saili Uday Gadgil, Jiarong QiuRetrieval-Augmented GenerationEvidence-Grounded Generation

  3. MAPLE: Medical Aspect-Based Summarization with Phrase-Level Evidence

    Jan 6, 2026Bohao Chu, Hendrik Damm, Tabea M. G. Pakull +5HealthcareText Summarization

  4. From Evidence to Judgment: Trace-Augmented Reasoning under Conflicting Evidence

    Dec 18, 2025Shubham Mishra, Atharv Sharma, Dhruv Kumar +1Knowledge Conflicts in Language ModelsEvidence-Grounded Generation