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

• URL: http://arxiv.org/abs/2605.08462v1
• Date: Fri, 08 May 2026 20:27:44 GMT
• Title: Do Benchmarks Underestimate LLM Performance? Evaluating Hallucination Detection With LLM-First Human-Adjudicated Assessment
• Abstract summary: This study focuses on contextual hallucination detection in summarization tasks.<n>We analyze the QAGS-C and SummEval datasets by comparing original benchmark annotations with reason and span-based predictions.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• NovGauge: A Fine-Grained Benchmark for Diagnosing LLMs' Capability in Paper Novelty Assessment [54.4265627247104]
  Large language models (LLMs) are increasingly used in peer review at major AI conferences.<n>Existing benchmarks assess novelty as a single holistic score.<n>We present NovGauge, a human-anchored benchmark for fine-grained novelty assessment diagnosis.
  arXiv  Detail & Related papers  (2026-09-10T08:34:56Z)
• Putting HUMANS first: Efficient LAM Evaluation with Human Preference Alignment [53.72927532626824]
  We show that subsets of just 50 examples (0.3% of data) can achieve over 0.93 Pearson correlation with full benchmark scores.<n>To better predict preferences, we trained regression models on these selected subsets, achieving 0.98 correlation.<n>This demonstrates that in regression modeling, well-curated subsets outpredict the full benchmark, showing quality over quantity.
  arXiv  Detail & Related papers  (2026-04-20T00:57:31Z)
• Prompt-Based Clarity Evaluation and Topic Detection in Political Question Answering [0.0]
  We study prompt-based clarity evaluation using the CLARITY dataset from the SemEval 2026 shared task.<n>We compare a GPT-3.5 baseline provided with the dataset against GPT-5.2 evaluated under three prompting strategies.<n>Results show that GPT-5.2 consistently outperforms the GPT-3.5 baseline on clarity prediction.
  arXiv  Detail & Related papers  (2026-01-13T03:10:58Z)
• Scheming Ability in LLM-to-LLM Strategic Interactions [4.873362301533824]
  Large language model (LLM) agents are deployed autonomously in diverse contexts.<n>We investigate the ability and propensity of frontier LLM agents through two game-theoretic frameworks.<n>Tests four models (GPT-4o, Gemini-2.5-pro, Claude-3.7-Sonnet, and Llama-3.3-70b)
  arXiv  Detail & Related papers  (2025-10-11T04:42:29Z)
• Signal or Noise? Evaluating Large Language Models in Resume Screening Across Contextual Variations and Human Expert Benchmarks [0.0]
  This study investigates whether large language models (LLMs) exhibit consistent behavior (signal) or random variation (noise) when screening resumes against job descriptions.
  arXiv  Detail & Related papers  (2025-07-08T01:34:21Z)
• Benchmarking Reasoning Robustness in Large Language Models [76.79744000300363]
  We find significant performance degradation on novel or incomplete data.<n>These findings highlight the reliance on recall over rigorous logical inference.<n>This paper introduces a novel benchmark, termed as Math-RoB, that exploits hallucinations triggered by missing information to expose reasoning gaps.
  arXiv  Detail & Related papers  (2025-03-06T15:36:06Z)
• A Comprehensive Evaluation of Large Language Models on Mental Illnesses [0.8458496687170665]
  GPT-4 and Llama 3 exhibited superior performance in binary disorder detection, with accuracies reaching up to 85% on certain datasets. prompt engineering played a crucial role in enhancing model performance. Despite promising results, our analysis identified several challenges, including variability in performance across datasets and the need for careful prompt engineering.
  arXiv  Detail & Related papers  (2024-09-24T02:58:52Z)
• Distortions in Judged Spatial Relations in Large Language Models [45.875801135769585]
  GPT-4 exhibited superior performance with 55 percent accuracy, followed by GPT-3.5 at 47 percent, and Llama-2 at 45 percent. The models identified the nearest cardinal direction in most cases, reflecting their associative learning mechanism.
  arXiv  Detail & Related papers  (2024-01-08T20:08:04Z)
• MR-GSM8K: A Meta-Reasoning Benchmark for Large Language Model Evaluation [60.65820977963331]
  We introduce a novel evaluation paradigm for Large Language Models (LLMs) This paradigm shifts the emphasis from result-oriented assessments, which often neglect the reasoning process, to a more comprehensive evaluation. By applying this paradigm in the GSM8K dataset, we have developed the MR-GSM8K benchmark.
  arXiv  Detail & Related papers  (2023-12-28T15:49:43Z)
• "Knowing When You Don't Know": A Multilingual Relevance Assessment Dataset for Robust Retrieval-Augmented Generation [90.09260023184932]
  Retrieval-Augmented Generation (RAG) grounds Large Language Model (LLM) output by leveraging external knowledge sources to reduce factual hallucinations. NoMIRACL is a human-annotated dataset for evaluating LLM robustness in RAG across 18 typologically diverse languages. We measure relevance assessment using: (i) hallucination rate, measuring model tendency to hallucinate, when the answer is not present in passages in the non-relevant subset, and (ii) error rate, measuring model inaccuracy to recognize relevant passages in the relevant subset.
  arXiv  Detail & Related papers  (2023-12-18T17:18:04Z)
• Split and Merge: Aligning Position Biases in LLM-based Evaluators [22.265542509143756]
  PORTIA is an alignment-based system designed to mimic human comparison strategies to calibrate position bias.<n>Our results show that PORTIA markedly enhances the consistency rates for all the models and comparison forms tested.<n>It rectifies around 80% of the position bias instances within the GPT-4 model, elevating its consistency rate up to 98%.
  arXiv  Detail & Related papers  (2023-09-29T14:38:58Z)
• Revisiting the Gold Standard: Grounding Summarization Evaluation with Robust Human Evaluation [136.16507050034755]
  Existing human evaluation studies for summarization either exhibit a low inter-annotator agreement or have insufficient scale. We propose a modified summarization salience protocol, Atomic Content Units (ACUs), which is based on fine-grained semantic units. We curate the Robust Summarization Evaluation (RoSE) benchmark, a large human evaluation dataset consisting of 22,000 summary-level annotations over 28 top-performing systems.
  arXiv  Detail & Related papers  (2022-12-15T17:26:05Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.