{"total":34,"rows":[{"id":"2309.10621","title":"Large language models can accurately predict searcher preferences","created":"2023-09-19","cited_by_count":131,"area":null},{"id":"2205.05256","title":"Evaluation Gaps in Machine Learning Practice","created":"2022-05-11","cited_by_count":49,"area":null},{"id":"2207.00810","title":"Eliciting and Learning with Soft Labels from Every Annotator","created":"2022-07-02","cited_by_count":43,"area":null},{"id":"2505.18893","title":"Reality Check: A New Evaluation Ecosystem Is Necessary to Understand AI's Real World Effects","created":"2025-05-24","cited_by_count":19,"area":null},{"id":"2210.16494","title":"Aligning Offline Metrics and Human Judgments of Value for Code Generation Models","created":"2022-10-29","cited_by_count":14,"area":null},{"id":"2402.01656","title":"Promises and pitfalls of artificial intelligence for legal applications","created":"2024-01-10","cited_by_count":14,"area":null},{"id":"2307.03201","title":"Scaling Laws Do Not Scale","created":"2023-07-05","cited_by_count":13,"area":null},{"id":"2410.24100","title":"Benchmark Data Repositories for Better Benchmarking","created":"2024-10-31","cited_by_count":10,"area":null},{"id":"2411.00308","title":"GPT for Games: An Updated Scoping Review (2020-2024)","created":"2024-11-01","cited_by_count":10,"area":null},{"id":"2310.06167","title":"Predictable Artificial Intelligence","created":"2023-10-09","cited_by_count":8,"area":null},{"id":"2310.18244","title":"A Review of the Evidence for Existential Risk from AI via Misaligned Power-Seeking","created":"2023-10-27","cited_by_count":8,"area":null},{"id":"2509.19364","title":"The Inadequacy of Offline LLM Evaluations: A Need to Account for Personalization in Model Behavior","created":"2025-09-18","cited_by_count":8,"area":null},{"id":"2403.13969","title":"\"This is not a data problem\": Algorithms and Power in Public Higher Education in Canada","created":"2024-03-20","cited_by_count":6,"area":null},{"id":"2207.01059","title":"Identifying the Context Shift between Test Benchmarks and Production Data","created":"2022-07-03","cited_by_count":5,"area":null},{"id":"2209.06317","title":"Quantitative AI Risk Assessments: Opportunities and Challenges","created":"2022-09-13","cited_by_count":4,"area":null},{"id":"2504.06791","title":"Beware of \"Explanations\" of AI","created":"2025-04-09","cited_by_count":3,"area":null},{"id":"2606.19624","title":"MassSpecGym in the Wild: Uncovering and Correcting Evaluation Pitfalls in AI-Driven Molecule Discovery","created":"2026-06-17","cited_by_count":3,"area":null},{"id":"2306.05036","title":"Mapping the Challenges of HCI: An Application and Evaluation of ChatGPT for Mining Insights at Scale","created":"2023-06-08","cited_by_count":2,"area":null},{"id":"2505.12556","title":"Beyond Accuracy: EcoL2 Metric for Sustainable Neural PDE Solvers","created":"2025-05-18","cited_by_count":2,"area":null},{"id":"2505.23445","title":"The Strong, Weak and Benign Goodhart's law. An independence-free and paradigm-agnostic formalisation","created":"2025-05-29","cited_by_count":2,"area":null},{"id":"2206.03225","title":"The Different Faces of AI Ethics Across the World: A Principle-Implementation Gap Analysis","created":"2022-05-12","cited_by_count":1,"area":null},{"id":"2210.07126","title":"Challenges in Explanation Quality Evaluation","created":"2022-10-13","cited_by_count":1,"area":null},{"id":"2304.12241","title":"Positive AI: Key Challenges in Designing Artificial Intelligence for Wellbeing","created":"2023-04-12","cited_by_count":1,"area":null},{"id":"2507.10502","title":"Benchmarking and Evaluation of AI Models in Biology: Outcomes and Recommendations from the CZI Virtual Cells Workshop","created":"2025-07-14","cited_by_count":1,"area":null},{"id":"2606.23597","title":"Against Proxy Optimization","created":"2026-06-22","cited_by_count":1,"area":null},{"id":"2608.04365","title":"Manipulation-Proof Oblivious Audits against Deceptive Model Providers","created":"2026-08-05","cited_by_count":1,"area":null},{"id":"2509.26632","title":"Branching Out: Broadening AI Measurement and Evaluation with Measurement Trees","created":"2025-09-30","cited_by_count":0,"area":null},{"id":"2602.19620","title":"Rules or Weights? Comparing User Understanding of Explainable AI Techniques with the Cognitive XAI-Adaptive Model","created":"2026-02-23","cited_by_count":0,"area":null},{"id":"2603.13294","title":"Real-World AI Evaluation: How FRAME Generates Systematic Evidence to Resolve the Decision-Maker's Dilemma","created":"2026-02-28","cited_by_count":0,"area":null},{"id":"2605.13318","title":"VERA-MH: Validation of Ethical and Responsible AI in Mental Health","created":"2026-05-13","cited_by_count":0,"area":null},{"id":"2605.17273","title":"Position: State-of-the-Art Claims Require State-of-the-Art Evidence","created":"2026-05-17","cited_by_count":0,"area":null},{"id":"2605.30916","title":"Welfare, Improvability, and Variance: A Principal-Agent Approach to Optimal Benchmark Item Aggregation","created":"2026-05-29","cited_by_count":0,"area":null},{"id":"2608.18117","title":"Position: AI Leaderboards Are Underserving the Global South: A Case Study from India","created":"2026-07-04","cited_by_count":0,"area":null},{"id":"2608.24056","title":"PhysicsBench: A Unified Leaderboard for Generative and Predictive Models in Engineering Design and Simulation","created":"2026-08-25","cited_by_count":0,"area":null}],"next_cursor":null}