Position: Science of AI Evaluation Requires Item-level Benchmark Data

• URL: http://arxiv.org/abs/2604.03244v1
• Date: Fri, 27 Feb 2026 04:31:30 GMT
• Title: Position: Science of AI Evaluation Requires Item-level Benchmark Data
• Abstract summary: We argue that item-level AI benchmark data is essential for establishing a rigorous science of AI evaluation.<n>To catalyze community-wide adoption, we introduce OpenEval, a growing repository of item-level benchmark data.
• Score: 42.82377343454172
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: AI evaluations have become the primary evidence for deploying generative AI systems across high-stakes domains. However, current evaluation paradigms often exhibit systemic validity failures. These issues, ranging from unjustified design choices to misaligned metrics, remain intractable without a principled framework for gathering validity evidence and conducting granular diagnostic analysis. In this position paper, we argue that item-level AI benchmark data is essential for establishing a rigorous science of AI evaluation. Item-level analysis enables fine-grained diagnostics and principled validation of benchmarks. We substantiate this position by dissecting current validity failures and revisiting evaluation paradigms across computer science and psychometrics. Through illustrative analyses of item properties and latent constructs, we demonstrate the unique insights afforded by item-level data. To catalyze community-wide adoption, we introduce OpenEval, a growing repository of item-level benchmark data designed supporting evidence-centered AI evaluation.

Related papers

• LLM-Based Scientific Peer Review: Methods, Benchmarks, and Reliability Challenges [4.655159257282136]
  This survey offers a systems-level analysis of large language models (LLMs)-based scientific peer review.<n>We focus on two core evaluative functions: critique generation and score prediction.<n>We identify emerging risks, including prompt injection, data poisoning, retrieval vulnerabilities, and reward hacking.
  arXiv  Detail & Related papers  (2026-06-23T18:12:39Z)
• Generative Responsible AI Data Evaluation Schema (GRAIDES) for AI Assurance in Local Government [0.0]
  We introduce the Generative Responsible Data Evaluation (GRAIDES) as a lightweight open-source data model for centralising AI observability across popular vendors.<n> Practical blueprints for code, architecture and statistical evaluation are shared as guidance about how to approach generative system assurance.
  arXiv  Detail & Related papers  (2026-06-18T22:00:25Z)
• Interactive Evaluation Requires a Design Science [90.62695599188204]
  Large language models (LLMs) are increasingly deployed as systems that act over time through tools, environments, users, and other agents.<n>The field has begun to build interactive benchmarks, but the resulting landscape is fragmented.<n>This position paper argues that interactive evaluation should be treated as a principled evaluation paradigm.
  arXiv  Detail & Related papers  (2026-05-18T04:03:18Z)
• Beyond Rating: A Comprehensive Evaluation and Benchmark for AI Reviews [69.66583722746904]
  We introduce Beyond Rating, a holistic evaluation framework that assesses AI reviewers across five dimensions.<n>We propose a Max-Recall strategy to accommodate valid expert disagreement and introduce a curated dataset of paper with high-confidence reviews.<n>Our proposed text-centric metrics--particularly the recall of weakness arguments--correlate strongly with rating accuracy.
  arXiv  Detail & Related papers  (2026-04-21T14:21:15Z)
• DREAM: Deep Research Evaluation with Agentic Metrics [21.555357444628044]
  We propose DREAM (Deep Research Evaluation with Agentic Metrics), a framework that makes evaluation itself agentic.<n> DREAM structures assessment through an evaluation protocol combining query-agnostic metrics with adaptive metrics generated by a tool-calling agent.<n>Controlled evaluations demonstrate DREAM is significantly more sensitive to factual and temporal decay than existing benchmarks.
  arXiv  Detail & Related papers  (2026-02-21T19:14:31Z)
• Identity Card Presentation Attack Detection: A Systematic Review [7.7489419818764596]
  Deep Learning has driven advances in Presentation Attack Detection.<n>The field is fundamentally limited by a lack of data and the poor generalisation of models.<n>This review consolidates our findings, identifies critical research gaps, and outlines a prescriptive roadmap for future research.
  arXiv  Detail & Related papers  (2025-11-08T15:55:37Z)
• Garbage In, Reasoning Out? Why Benchmark Scores are Unreliable and What to Do About It [1.6261897792391753]
  We conduct a systematic audit of three widely used reasoning benchmarks, SocialIQa, FauxPas-EAI, and ToMi.<n>We uncover pervasive flaws in both benchmark items and evaluation methodology.
  arXiv  Detail & Related papers  (2025-06-30T13:57:28Z)
• SEOE: A Scalable and Reliable Semantic Evaluation Framework for Open Domain Event Detection [70.23196257213829]
  We propose a scalable and reliable Semantic-level Evaluation framework for Open domain Event detection.<n>Our proposed framework first constructs a scalable evaluation benchmark that currently includes 564 event types covering 7 major domains.<n>We then leverage large language models (LLMs) as automatic evaluation agents to compute a semantic F1-score, incorporating fine-grained definitions of semantically similar labels.
  arXiv  Detail & Related papers  (2025-03-05T09:37:05Z)
• A Backdoor-based Explainable AI Benchmark for High Fidelity Evaluation of Attributions [60.06461883533697]
  We first identify a set of fidelity criteria that reliable benchmarks for attribution methods are expected to fulfill.<n>We then introduce a Backdoor-based eXplainable AI benchmark (BackX) that adheres to the desired fidelity criteria.<n>Our analysis also offers insights into defending against neural Trojans by utilizing the attributions.
  arXiv  Detail & Related papers  (2024-05-02T13:48:37Z)
• A Literature Review of Literature Reviews in Pattern Analysis and Machine Intelligence [51.26815896167173]
  We present a comprehensive tertiary analysis of PAMI reviews along three complementary dimensions.<n>Our analyses reveal distinctive organizational patterns as well as persistent gaps in current review practices.<n>Finally, our evaluation of state-of-the-art AI-generated reviews indicates encouraging advances in coherence and organization.
  arXiv  Detail & Related papers  (2024-02-20T11:28:50Z)
• Position: AI Evaluation Should Learn from How We Test Humans [65.36614996495983]
  We argue that psychometrics, a theory originating in the 20th century for human assessment, could be a powerful solution to the challenges in today's AI evaluations.
  arXiv  Detail & Related papers  (2023-06-18T09:54:33Z)

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.