{"total":32,"rows":[{"id":"2103.03098","title":"Accounting for Variance in Machine Learning Benchmarks","created":"2021-03-01","cited_by_count":201,"area":null},{"id":"2109.00725","title":"Causal Inference in Natural Language Processing: Estimation, Prediction, Interpretation and Beyond","created":"2021-09-02","cited_by_count":178,"area":null},{"id":"2107.07002","title":"The Benchmark Lottery","created":"2021-07-14","cited_by_count":136,"area":null},{"id":"2501.10970","title":"The Alternative Annotator Test for LLM-as-a-Judge: How to Statistically Justify Replacing Human Annotators with LLMs","created":"2025-01-19","cited_by_count":74,"area":null},{"id":"2104.00054","title":"A Statistical Analysis of Summarization Evaluation Metrics using Resampling Methods","created":"2021-03-31","cited_by_count":72,"area":null},{"id":"2104.14700","title":"The Zero Resource Speech Challenge 2021: Spoken language modelling","created":"2021-04-29","cited_by_count":47,"area":null},{"id":"2306.11559","title":"The Ecological Fallacy in Annotation: Modelling Human Label Variation goes beyond Sociodemographics","created":"2023-06-20","cited_by_count":46,"area":null},{"id":"2406.14325","title":"Reproducibility in Machine Learning-based Research: Overview, Barriers and Drivers","created":"2024-06-20","cited_by_count":34,"area":null},{"id":"2203.06498","title":"The worst of both worlds: A comparative analysis of errors in learning from data in psychology and machine learning","created":"2022-03-12","cited_by_count":17,"area":null},{"id":"2307.10320","title":"Reproducibility in Machine Learning-Driven Research","created":"2023-07-19","cited_by_count":15,"area":null},{"id":"2211.00922","title":"Dialect-robust Evaluation of Generated Text","created":"2022-11-02","cited_by_count":14,"area":null},{"id":"2102.08655","title":"Decoding EEG Brain Activity for Multi-Modal Natural Language Processing","created":"2021-02-17","cited_by_count":13,"area":null},{"id":"2310.17867","title":"Reproducibility in Multiple Instance Learning: A Case For Algorithmic Unit Tests","created":"2023-10-27","cited_by_count":11,"area":null},{"id":"2204.06251","title":"Experimental Standards for Deep Learning in Natural Language Processing Research","created":"2022-04-13","cited_by_count":10,"area":null},{"id":"2410.24100","title":"Benchmark Data Repositories for Better Benchmarking","created":"2024-10-31","cited_by_count":10,"area":null},{"id":"2311.09006","title":"Data Similarity is Not Enough to Explain Language Model Performance","created":"2023-11-15","cited_by_count":9,"area":null},{"id":"2204.03829","title":"Does the Market of Citations Reward Reproducible Work?","created":"2022-04-08","cited_by_count":8,"area":null},{"id":"2204.04372","title":"A Siren Song of Open Source Reproducibility","created":"2022-04-09","cited_by_count":8,"area":null},{"id":"2302.10086","title":"A Two-Sided Discussion of Preregistration of NLP Research","created":"2023-02-20","cited_by_count":6,"area":null},{"id":"2606.08679","title":"Rank Intervals for Leaderboards: A Hierarchical Framework for Model Evaluation","created":"2026-06-07","cited_by_count":6,"area":null},{"id":"2209.06367","title":"A Review and Roadmap of Deep Learning Causal Discovery in Different Variable Paradigms","created":"2022-09-14","cited_by_count":4,"area":null},{"id":"2302.04054","title":"Towards Inferential Reproducibility of Machine Learning Research","created":"2023-02-08","cited_by_count":4,"area":null},{"id":"2312.15813","title":"Small Effect Sizes in Malware Detection? Make Harder Train/Test Splits!","created":"2023-12-25","cited_by_count":4,"area":null},{"id":"2408.02533","title":"LMEMs for post-hoc analysis of HPO Benchmarking","created":"2024-08-05","cited_by_count":2,"area":null},{"id":"2211.13190","title":"BiasBed -- Rigorous Texture Bias Evaluation","created":"2022-11-23","cited_by_count":1,"area":null},{"id":"2311.00923","title":"A Review and Roadmap of Deep Causal Model from Different Causal Structures and Representations","created":"2023-11-02","cited_by_count":1,"area":null},{"id":"2501.01273","title":"Does a Large Language Model Really Speak in Human-Like Language?","created":"2025-01-02","cited_by_count":1,"area":null},{"id":"2605.28190","title":"The Harder Text Embedding Benchmark (HTEB): Beyond One-dimensional Static Robustness","created":"2026-05-27","cited_by_count":1,"area":null},{"id":"2211.01486","title":"Assessing Resource-Performance Trade-off of Natural Language Models using Data Envelopment Analysis","created":"2022-11-02","cited_by_count":0,"area":null},{"id":"2212.10469","title":"BMX: Boosting Natural Language Generation Metrics with Explainability","created":"2022-12-20","cited_by_count":0,"area":null},{"id":"2312.17254","title":"Faithful Model Evaluation for Model-Based Metrics","created":"2023-12-19","cited_by_count":0,"area":null},{"id":"2606.01811","title":"\"I've Seen How This Goes\": Characterizing Diversity via Progressive Conditional Surprise","created":"2026-06-01","cited_by_count":0,"area":null}],"next_cursor":null}