mlsanityData to 14 Oct 2026

Stage-Audit: Auditable Source-Frontier Discovery for Cross-Wiki Tables

arXiv 2605.20478 ↗First posted 19 May 2026cs.CLcited by 0

Not on the map. Why?

Abstract (arXiv)

LLM-curated tables can appear source-grounded while containing unsupported rows: the curator may recall entries from parametric memory and retroactively attach page-level citations that are not the actual source. We study this hazard in Seed2Frontier discovery: the task of finding complement Wikipedia pages from a seed page to assemble a structured table. Stage-Audit addresses it with disjoint curator-auditor write rights, a row-level source-citation gate, and a 12-check audit taxonomy over keys, schema, source roles, cardinality, and scope. On a curated 51-instance Seed2Frontier evaluation set spanning 15 top-level domains, Stage-Audit improves source-frontier precision over a vanilla LLM curator from 0.356 to 0.505 (+42% relative) and F1 from 0.334 to 0.451 (+35%), while maintaining explicit per-row source traceability. The vanilla-LLM-vs-Stage-Audit comparison isolates the policy contribution rather than LLM-based discovery in general.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 22 of its 23 references that are in the map. First posted on arXiv 19 May 2026.

Builds on

22 of 23 references.

References · 22

  1. 2023Self-Refine: Iterative Refinement with Self-Feedbackcited by 3,442
  2. 2022Constitutional AI: Harmlessness from AI Feedbackcited by 3,050
  3. 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflectioncited by 1,839
  4. 2023Improving Factuality and Reasoning in Language Models through Multiagent Debatecited by 1,784
  5. 2023FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generationcited by 1,282
  6. 2023Large Language Models Cannot Self-Correct Reasoning Yetcited by 1,017
  7. 2024LLM Evaluators Recognize and Favor Their Own Generationscited by 686
  8. 2025Why Do Multi-Agent LLM Systems Fail?cited by 604
  9. 2023Enabling Large Language Models to Generate Text with Citationscited by 595
  10. 2022RARR: Researching and Revising What Language Models Say, Using Language Modelscited by 287
  11. 2020HybridQA: A Dataset of Multi-Hop Question Answering over Tabular and Textual Datacited by 264
  12. 2024Self-Preference Bias in LLM-as-a-Judgecited by 258
10 more
  1. 2024When Can LLMs Actually Correct Their Own Mistakes? A Critical Survey of Self-Correction of LLMscited by 240
  2. 2020Open Question Answering over Tables and Textcited by 163
  3. 2024Long-form factuality in large language modelscited by 155
  4. 2024WikiContradict: A Benchmark for Evaluating LLMs on Real-World Knowledge Conflicts from Wikipediacited by 44
  5. 2023Open-WikiTable: Dataset for Open Domain Question Answering with Complex Reasoning over Tablecited by 40
  6. 2025KARMA: Leveraging Multi-Agent LLMs for Automated Knowledge Graph Enrichmentcited by 27
  7. 2024SPADE: Synthesizing Data Quality Assertions for Large Language Model Pipelinescited by 19
  8. 2025SRAG: Structured Retrieval-Augmented Generation for Multi-Entity Question Answering over Wikipedia Graphcited by 11
  9. 2025Do Large Language Models Know What They Are Capable Of?cited by 10
  10. 2026PaperTrail: A Claim-Evidence Interface for Grounding Provenance in LLM-based Scholarly Q&Acited by 2

Built on by

Not cited yet.