mlsanityData to 14 Oct 2026

Do Benchmarks Underestimate LLM Performance? Evaluating Hallucination Detection With LLM-First Human-Adjudicated Assessment

arXiv 2605.08462 ↗First posted 8 May 2026cs.CL cs.AIcited by 0

On the map: LLM agents and tool use → Medical and scientific domain agents

Abstract (arXiv)

Hallucination remains a persistent challenge in Large Language Models (LLMs), particularly in context-grounded settings such as RAG and agentic AI systems. This study focuses on contextual hallucination detection in summarization tasks. We analyze the QAGS-C and SummEval datasets by comparing original benchmark annotations with reason and span-based predictions from Gemini 2.5 Flash and GPT-5 Mini. To address systematic divergences between human labels and LLM judgments, we re-evaluated all conflicted samples through a human adjudication process involving 2 cross-cultural adjudicators. Following this re-evaluation, triple agreement (between human, GPT, and Gemini) increased by 6.38% for QAGS-C and 7.62% for SummEval. Similarly, model accuracy improved, with GPT increasing by 4.25% on QAGS-C and 2.34% on SummEval, while Gemini showed gains of 8.51% and 3.80%, respectively. Notably, adjudicators frequently sided with the models' judgments over original human annotations when LLMs provided explicit reasoning. Overall human adjudicator agreement ranged between 83% and 87%. These findings suggest that for ambiguity-prone tasks, single-pass annotations may be insufficient, and model-assisted re-evaluation yields more reliable benchmarks.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Medical and scientific domain agents, one of 16 directions in LLM agents and tool use. Builds on 13 of its 16 references that are in the map. First posted on arXiv 8 May 2026.

Builds on

13 of 16 references.

References · 13

  1. 2023GPT-4 Technical Reportcited by 18,396
  2. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,695
  3. 2022Survey of Hallucination in Natural Language Generationcited by 2,075
  4. 2020On Faithfulness and Factuality in Abstractive Summarizationcited by 900
  5. 2020SummEval: Re-evaluating Summarization Evaluationcited by 674
  6. 2019Evaluating the Factual Consistency of Abstractive Text Summarizationcited by 584
  7. 2021SummaC: Re-Visiting NLI-based Models for Inconsistency Detection in Summarizationcited by 407
  8. 2020Asking and Answering Questions to Evaluate the Factual Consistency of Summariescited by 378
  9. 2020FEQA: A Question Answering Evaluation Framework for Faithfulness Assessment in Abstractive Summarizationcited by 293
  10. 2023RAGTruth: A Hallucination Corpus for Developing Trustworthy Retrieval-Augmented Language Modelscited by 283
  11. 2023TrueTeacher: Learning Factual Consistency Evaluation with Large Language Modelscited by 83
  12. 2025LettuceDetect: A Hallucination Detection Framework for RAG Applicationscited by 34
1 more
  1. 2024Are LLMs Better than Reported? Detecting Label Errors and Mitigating Their Effect on Model Performancecited by 20

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2024FaithBench: A Diverse Hallucination Benchmark for Summarization by Modern LLMs
  2. 2025Benchmarking LLM Faithfulness in RAG with Evolving Leaderboards
  3. 2023HaluEval: A Large-Scale Hallucination Evaluation Benchmark for Large Language Models
  4. 2025Theoretical Foundations and Mitigation of Hallucination in Large Language Models
  5. 2025OnionEval: An Unified Evaluation of Fact-conflicting Hallucination for Small-Large Language Models
  6. 2026Rethinking Evaluation for LLM Hallucination Detection: A Desiderata, A New RAG-based Benchmark, New Insights
  7. 2023A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions
  8. 2024A review of faithfulness metrics for hallucination assessment in Large Language Models