{"total":142,"rows":[{"id":"2104.08718","title":"CLIPScore: A Reference-free Evaluation Metric for Image Captioning","created":"2021-04-18","cited_by_count":2424,"area":null},{"id":"2104.14337","title":"Dynabench: Rethinking Benchmarking in NLP","created":"2021-04-07","cited_by_count":459,"area":null},{"id":"2209.12356","title":"News Summarization and Evaluation in the Era of GPT-3","created":"2022-09-26","cited_by_count":327,"area":null},{"id":"2107.00061","title":"All That's 'Human' Is Not Gold: Evaluating Human Evaluation of Generated Text","created":"2021-06-30","cited_by_count":287,"area":null},{"id":"2104.02145","title":"What Will it Take to Fix Benchmarking in Natural Language Understanding?","created":"2021-04-05","cited_by_count":203,"area":null},{"id":"2405.14782","title":"Lessons from the Trenches on Reproducible Evaluation of Language Models","created":"2024-05-23","cited_by_count":179,"area":null},{"id":"2202.06935","title":"Repairing the Cracked Foundation: A Survey of Obstacles in Evaluation Practices for Generated Text","created":"2022-02-14","cited_by_count":155,"area":null},{"id":"2212.07981","title":"Revisiting the Gold Standard: Grounding Summarization Evaluation with Robust Human Evaluation","created":"2022-12-15","cited_by_count":142,"area":null},{"id":"2109.06835","title":"The Perils of Using Mechanical Turk to Evaluate Open-Ended Text Generation","created":"2021-09-14","cited_by_count":97,"area":null},{"id":"2302.11520","title":"Guiding Large Language Models via Directional Stimulus Prompting","created":"2023-02-22","cited_by_count":95,"area":null},{"id":"2504.07086","title":"A Sober Look at Progress in Language Model Reasoning: Pitfalls and Paths to Reproducibility","created":"2025-04-09","cited_by_count":93,"area":"lr"},{"id":"2106.16163","title":"The MultiBERTs: BERT Reproductions for Robustness Analysis","created":"2021-06-30","cited_by_count":92,"area":null},{"id":"2304.02210","title":"Document-Level Machine Translation with Large Language Models","created":"2023-04-05","cited_by_count":90,"area":null},{"id":"2107.01294","title":"Is GPT-3 Text Indistinguishable from Human Text? Scarecrow: A Framework for Scrutinizing Machine Text","created":"2021-07-02","cited_by_count":89,"area":null},{"id":"2309.08638","title":"Anchor Points: Benchmarking Models with Much Fewer Examples","created":"2023-09-14","cited_by_count":86,"area":null},{"id":"2107.02173","title":"Is Automated Topic Model Evaluation Broken?: The Incoherence of Coherence","created":"2021-07-05","cited_by_count":74,"area":null},{"id":"2212.06801","title":"A fine-grained comparison of pragmatic language understanding in humans and language models","created":"2022-12-13","cited_by_count":70,"area":null},{"id":"2107.07170","title":"FLEX: Unifying Evaluation for Few-Shot NLP","created":"2021-07-15","cited_by_count":67,"area":null},{"id":"2106.06052","title":"Dynaboard: An Evaluation-As-A-Service Platform for Holistic Next-Generation Benchmarking","created":"2021-05-21","cited_by_count":53,"area":null},{"id":"2104.08726","title":"AmericasNLI: Evaluating Zero-shot Natural Language Understanding of Pretrained Multilingual Models in Truly Low-resource Languages","created":"2021-04-18","cited_by_count":50,"area":null},{"id":"2408.15204","title":"Can Unconfident LLM Annotations Be Used for Confident Conclusions?","created":"2024-08-27","cited_by_count":49,"area":null},{"id":"2110.03036","title":"The Low-Resource Double Bind: An Empirical Study of Pruning for Low-Resource Machine Translation","created":"2021-10-06","cited_by_count":47,"area":null},{"id":"2108.12463","title":"Automatic Text Evaluation through the Lens of Wasserstein Barycenters","created":"2021-08-27","cited_by_count":38,"area":null},{"id":"2110.08300","title":"The Dangers of Underclaiming: Reasons for Caution When Reporting How NLP Systems Fail","created":"2021-10-15","cited_by_count":38,"area":null},{"id":"2210.03568","title":"How Large Language Models are Transforming Machine-Paraphrased Plagiarism","created":"2022-10-07","cited_by_count":38,"area":null},{"id":"2406.19371","title":"Suri: Multi-constraint Instruction Following for Long-form Text Generation","created":"2024-06-27","cited_by_count":34,"area":"alignment"},{"id":"2204.07610","title":"Sources of Irreproducibility in Machine Learning: A Review","created":"2022-04-15","cited_by_count":32,"area":null},{"id":"2204.06815","title":"deep-significance - Easy and Meaningful Statistical Significance Testing in the Age of Neural Networks","created":"2022-04-14","cited_by_count":28,"area":null},{"id":"2407.11417","title":"SPINACH: SPARQL-Based Information Navigation for Challenging Real-World Questions","created":"2024-07-16","cited_by_count":27,"area":null},{"id":"2508.13144","title":"Signal and Noise: A Framework for Reducing Uncertainty in Language Model Evaluation","created":"2025-08-18","cited_by_count":26,"area":null},{"id":"2205.11930","title":"The Authenticity Gap in Human Evaluation","created":"2022-05-24","cited_by_count":24,"area":null},{"id":"2406.06369","title":"Annotation alignment: Comparing LLM and human annotations of conversational safety","created":"2024-06-10","cited_by_count":23,"area":null},{"id":"2102.01065","title":"Do Question Answering Modeling Improvements Hold Across Benchmarks?","created":"2021-02-01","cited_by_count":20,"area":null},{"id":"2502.01926","title":"Fairness through Difference Awareness: Measuring Desired Group Discrimination in LLMs","created":"2025-02-04","cited_by_count":20,"area":null},{"id":"2103.09710","title":"The Human Evaluation Datasheet 1.0: A Template for Recording Details of Human Evaluation Experiments in NLP","created":"2021-03-17","cited_by_count":19,"area":null},{"id":"2108.01182","title":"Underreporting of errors in NLG output, and what to do about it","created":"2021-08-02","cited_by_count":19,"area":null},{"id":"2204.12708","title":"On the Limitations of Dataset Balancing: The Lost Battle Against Spurious Correlations","created":"2022-04-27","cited_by_count":19,"area":null},{"id":"2105.12437","title":"The statistical advantage of automatic NLG metrics at the system level","created":"2021-05-26","cited_by_count":18,"area":null},{"id":"2406.03339","title":"The Challenges of Evaluating LLM Applications: An Analysis of Automated, Human, and LLM-Based Approaches","created":"2024-06-05","cited_by_count":18,"area":null},{"id":"2108.03405","title":"Controllable Summarization with Constrained Markov Decision Process","created":"2021-08-07","cited_by_count":17,"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":"2506.21521","title":"Potemkin Understanding in Large Language Models","created":"2025-06-26","cited_by_count":15,"area":null},{"id":"2210.05043","title":"Multi-CLS BERT: An Efficient Alternative to Traditional Ensembling","created":"2022-10-10","cited_by_count":14,"area":null},{"id":"2306.00539","title":"A Call for Standardization and Validation of Text Style Transfer Evaluation","created":"2023-06-01","cited_by_count":14,"area":null},{"id":"2311.18807","title":"Pre-registration for Predictive Modeling","created":"2023-11-30","cited_by_count":13,"area":null},{"id":"2108.13751","title":"A Search Engine for Discovery of Scientific Challenges and Directions","created":"2021-08-31","cited_by_count":12,"area":null},{"id":"2208.13081","title":"Textwash -- automated open-source text anonymisation","created":"2022-08-27","cited_by_count":11,"area":null},{"id":"2506.06842","title":"PCoT: Persuasion-Augmented Chain of Thought for Detecting Fake News and Social Media Disinformation","created":"2025-06-07","cited_by_count":11,"area":null},{"id":"2508.12461","title":"Is GPT-OSS Good? A Comprehensive Evaluation of OpenAI's Latest Open Source Models","created":"2025-08-17","cited_by_count":11,"area":"moe"},{"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":"2212.10397","title":"Needle in a Haystack: An Analysis of High-Agreement Workers on MTurk for Summarization","created":"2022-12-20","cited_by_count":10,"area":null},{"id":"2604.16706","title":"Auditing Automated Evaluation, Error Propagation, and Runtime Mitigation in Tool-Using Language Agents","created":"2026-04-17","cited_by_count":10,"area":"agents"},{"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":"2504.07971","title":"SPHERE: An Evaluation Card for Human-AI Systems","created":"2025-03-24","cited_by_count":9,"area":null},{"id":"2510.08730","title":"How Reliable is Language Model Micro-Benchmarking?","created":"2025-10-09","cited_by_count":9,"area":null},{"id":"2104.05146","title":"Assessing Reference-Free Peer Evaluation for Machine Translation","created":"2021-04-12","cited_by_count":8,"area":null},{"id":"2410.22211","title":"ProMQA: Question Answering Dataset for Multimodal Procedural Activity Understanding","created":"2024-10-29","cited_by_count":8,"area":null},{"id":"2502.11910","title":"Adversarial Alignment for LLMs Requires Simpler, Reproducible, and More Measurable Objectives","created":"2025-02-17","cited_by_count":8,"area":null},{"id":"2101.11298","title":"How to Evaluate a Summarizer: Study Design and Statistical Analysis for Manual Linguistic Quality Evaluation","created":"2021-01-27","cited_by_count":7,"area":null},{"id":"2512.21326","title":"Measuring all the noises of LLM Evals","created":"2025-12-24","cited_by_count":7,"area":null},{"id":"2605.30315","title":"Resolution Diagnostics for Paired LLM Evaluation","created":"2026-05-28","cited_by_count":7,"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":"2209.07353","title":"Measuring Geographic Performance Disparities of Offensive Language Classifiers","created":"2022-09-15","cited_by_count":5,"area":null},{"id":"2406.12165","title":"Statistical Uncertainty in Word Embeddings: GloVe-V","created":"2024-06-18","cited_by_count":5,"area":null},{"id":"2504.08024","title":"Summarizing Speech: A Comprehensive Survey","created":"2025-04-10","cited_by_count":5,"area":null},{"id":"2608.12875","title":"The Embedder's Dilemma: LLMs Are Better, but at What Cost?","created":"2026-08-13","cited_by_count":5,"area":"lr"},{"id":"2202.12801","title":"On the data requirements of probing","created":"2022-02-25","cited_by_count":4,"area":null},{"id":"2205.10696","title":"Life after BERT: What do Other Muppets Understand about Language?","created":"2022-05-21","cited_by_count":4,"area":null},{"id":"2210.13025","title":"On the Effectiveness of Automated Metrics for Text Generation Systems","created":"2022-10-24","cited_by_count":4,"area":null},{"id":"2404.13020","title":"Stronger Random Baselines for In-Context Learning","created":"2024-04-19","cited_by_count":4,"area":null},{"id":"2406.07967","title":"Better than Random: Reliable NLG Human Evaluation with Constrained Active Sampling","created":"2024-06-12","cited_by_count":4,"area":null},{"id":"2410.23902","title":"Responsible Retrieval Augmented Generation for Climate Decision Making from Documents","created":"2024-10-31","cited_by_count":4,"area":"rag"},{"id":"2605.18229","title":"Are Sparse Autoencoder Benchmarks Reliable?","created":"2026-05-18","cited_by_count":4,"area":"mechinterp"},{"id":"2108.06896","title":"Challenges for cognitive decoding using deep learning methods","created":"2021-08-16","cited_by_count":3,"area":null},{"id":"2210.11612","title":"Searching for a higher power in the human evaluation of MT","created":"2022-10-20","cited_by_count":3,"area":null},{"id":"2210.12206","title":"Probing with Noise: Unpicking the Warp and Weft of Embeddings","created":"2022-10-21","cited_by_count":3,"area":null},{"id":"2303.16445","title":"Larger Probes Tell a Different Story: Extending Psycholinguistic Datasets Via In-Context Learning","created":"2023-03-29","cited_by_count":3,"area":null},{"id":"2306.03866","title":"Correction of Errors in Preference Ratings from Automated Metrics for Text Generation","created":"2023-06-06","cited_by_count":3,"area":null},{"id":"2402.18756","title":"How Much Annotation is Needed to Compare Summarization Models?","created":"2024-02-28","cited_by_count":3,"area":null},{"id":"2506.12339","title":"SheetMind: Actions Set Accuracy, Agents Set the Failure Mode","created":"2025-06-14","cited_by_count":3,"area":"agents"},{"id":"2603.14525","title":"MALicious INTent Dataset and Inoculating LLMs for Enhanced Disinformation Detection","created":"2026-03-15","cited_by_count":3,"area":null},{"id":"2604.10733","title":"Too Nice to Tell the Truth: Quantifying Agreeableness-Driven Sycophancy in Role-Playing Language Models","created":"2026-04-12","cited_by_count":3,"area":null},{"id":"2608.13867","title":"Engineering Reliable Coding Agents: Evaluating and Operating the System Around the Model","created":"2026-08-14","cited_by_count":3,"area":"agents"},{"id":"2112.08048","title":"Dynamic Human Evaluation for Relative Model Comparisons","created":"2021-12-15","cited_by_count":2,"area":null},{"id":"2201.01845","title":"Data-driven Model Generalizability in Crosslinguistic Low-resource Morphological Segmentation","created":"2022-01-05","cited_by_count":2,"area":null},{"id":"2312.03912","title":"Collaboration or Corporate Capture? Quantifying NLP's Reliance on Industry Artifacts and Contributions","created":"2023-12-06","cited_by_count":2,"area":null},{"id":"2409.19507","title":"A Critical Look at Meta-evaluating Summarisation Evaluation Metrics","created":"2024-09-29","cited_by_count":2,"area":null},{"id":"2411.13779","title":"NewsInterview: a Dataset and a Playground to Evaluate LLMs' Ground Gap via Informational Interviews","created":"2024-11-21","cited_by_count":2,"area":null},{"id":"2509.25664","title":"QFrBLiMP: a Quebec-French Benchmark of Linguistic Minimal Pairs","created":"2025-09-30","cited_by_count":2,"area":null},{"id":"2607.13075","title":"The Entanglement Wall: Activation-Space Probes as Risk Detectors, Not Context Adjudicators","created":"2026-07-12","cited_by_count":2,"area":"safety"},{"id":"2609.04518","title":"Multi-Harness Reinforcement Learning for Coding Agents: Training Gains and Harness Dependence","created":"2026-09-03","cited_by_count":2,"area":"lr"},{"id":"2609.17989","title":"Whom Do AI Agents Work For? Role Assignment Induces Sponsorship Bias in LLM Recommenders","created":"2026-09-16","cited_by_count":2,"area":"agents"},{"id":"2204.14213","title":"Modular Domain Adaptation","created":"2022-04-26","cited_by_count":1,"area":null},{"id":"2206.04039","title":"Resolving the Human Subjects Status of Machine Learning's Crowdworkers","created":"2022-06-08","cited_by_count":1,"area":null},{"id":"2210.05038","title":"Fighting FIRe with FIRE: Assessing the Validity of Text-to-Video Retrieval Benchmarks","created":"2022-10-10","cited_by_count":1,"area":null},{"id":"2305.15130","title":"On Degrees of Freedom in Defining and Testing Natural Language Understanding","created":"2023-05-24","cited_by_count":1,"area":null},{"id":"2310.10955","title":"A State-Vector Framework for Dataset Effects","created":"2023-10-17","cited_by_count":1,"area":null},{"id":"2410.04292","title":"Efficiently Identifying Low-Quality Language Subsets in Multilingual Datasets: A Case Study on a Large-Scale Multilingual Audio Dataset","created":"2024-10-05","cited_by_count":1,"area":null},{"id":"2410.18218","title":"Optimizing the role of human evaluation in LLM-based spoken document summarization systems","created":"2024-10-23","cited_by_count":1,"area":null},{"id":"2601.03988","title":"Using Small Language Models to Reverse-Engineer Machine Learning Pipelines Structures","created":"2026-01-07","cited_by_count":1,"area":null}],"next_cursor":"100"}