{"total":43,"rows":[{"id":"2104.14337","title":"Dynabench: Rethinking Benchmarking in NLP","created":"2021-04-07","cited_by_count":459,"area":null},{"id":"2111.15366","title":"AI and the Everything in the Whole Wide World Benchmark","created":"2021-11-26","cited_by_count":349,"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":"2201.05955","title":"WANLI: Worker and AI Collaboration for Natural Language Inference Dataset Creation","created":"2022-01-16","cited_by_count":202,"area":null},{"id":"2107.12708","title":"QA Dataset Explosion: A Taxonomy of NLP Resources for Question Answering and Reading Comprehension","created":"2021-07-27","cited_by_count":91,"area":null},{"id":"2402.12483","title":"Artifacts or Abduction: How Do LLMs Answer Multiple-Choice Questions Without the Question?","created":"2024-02-19","cited_by_count":71,"area":null},{"id":"2212.10020","title":"On the Blind Spots of Model-Based Evaluation Metrics for Text Generation","created":"2022-12-20","cited_by_count":49,"area":null},{"id":"2106.01024","title":"Why Machine Reading Comprehension Models Learn Shortcuts?","created":"2021-06-02","cited_by_count":40,"area":null},{"id":"2211.15458","title":"Validating Large Language Models with ReLM","created":"2022-11-21","cited_by_count":33,"area":null},{"id":"2305.09022","title":"It Takes Two to Tango: Navigating Conceptualizations of NLP Tasks and Measurements of Performance","created":"2023-05-15","cited_by_count":26,"area":null},{"id":"2103.03872","title":"Rissanen Data Analysis: Examining Dataset Characteristics via Description Length","created":"2021-03-05","cited_by_count":22,"area":null},{"id":"2207.02463","title":"Gender Biases and Where to Find Them: Exploring Gender Bias in Pre-Trained Transformer-based Language Models Using Movement Pruning","created":"2022-07-06","cited_by_count":21,"area":null},{"id":"2410.20245","title":"Improving Model Evaluation using SMART Filtering of Benchmark Datasets","created":"2024-10-26","cited_by_count":21,"area":null},{"id":"2110.04374","title":"A Few More Examples May Be Worth Billions of Parameters","created":"2021-10-08","cited_by_count":19,"area":null},{"id":"2110.08555","title":"On the Robustness of Reading Comprehension Models to Entity Renaming","created":"2021-10-16","cited_by_count":17,"area":null},{"id":"2305.14341","title":"APPLS: Evaluating Evaluation Metrics for Plain Language Summarization","created":"2023-05-23","cited_by_count":15,"area":null},{"id":"2209.07430","title":"Machine Reading, Fast and Slow: When Do Models \"Understand\" Language?","created":"2022-09-15","cited_by_count":13,"area":null},{"id":"2109.14017","title":"Shaking Syntactic Trees on the Sesame Street: Multilingual Probing with Controllable Perturbations","created":"2021-09-28","cited_by_count":10,"area":null},{"id":"2211.16220","title":"Which Shortcut Solution Do Question Answering Models Prefer to Learn?","created":"2022-11-29","cited_by_count":9,"area":null},{"id":"2410.11672","title":"Leaving the barn door open for Clever Hans: Simple features predict LLM benchmark answers","created":"2024-10-15","cited_by_count":9,"area":null},{"id":"2203.11400","title":"VLSP 2021 - ViMRC Challenge: Vietnamese Machine Reading Comprehension","created":"2022-03-22","cited_by_count":7,"area":null},{"id":"2211.07040","title":"World Knowledge in Multiple Choice Reading Comprehension","created":"2022-11-13","cited_by_count":6,"area":null},{"id":"2105.10334","title":"Fact-driven Logical Reasoning for Machine Reading Comprehension","created":"2021-05-21","cited_by_count":4,"area":null},{"id":"2209.01824","title":"A Survey on Measuring and Mitigating Reasoning Shortcuts in Machine Reading Comprehension","created":"2022-09-05","cited_by_count":4,"area":null},{"id":"2302.00094","title":"The Impacts of Unanswerable Questions on the Robustness of Machine Reading Comprehension Models","created":"2023-01-31","cited_by_count":4,"area":null},{"id":"2307.01076","title":"Analyzing Multiple-Choice Reading and Listening Comprehension Tests","created":"2023-07-03","cited_by_count":4,"area":null},{"id":"2203.02753","title":"Feeding What You Need by Understanding What You Learned","created":"2022-03-05","cited_by_count":3,"area":null},{"id":"2109.07102","title":"Can Edge Probing Tasks Reveal Linguistic Knowledge in QA Models?","created":"2021-09-15","cited_by_count":2,"area":null},{"id":"2208.13518","title":"LogicRank: Logic Induced Reranking for Generative Text-to-Image Systems","created":"2022-08-29","cited_by_count":2,"area":null},{"id":"2212.09272","title":"Statistical Dataset Evaluation: Reliability, Difficulty, and Validity","created":"2022-12-19","cited_by_count":2,"area":null},{"id":"2302.14413","title":"SMoA: Sparse Mixture of Adapters to Mitigate Multiple Dataset Biases","created":"2023-02-28","cited_by_count":2,"area":null},{"id":"2105.01192","title":"Unreasonable Effectiveness of Rule-Based Heuristics in Solving Russian SuperGLUE Tasks","created":"2021-05-03","cited_by_count":1,"area":null},{"id":"2105.05999","title":"Designing Multimodal Datasets for NLP Challenges","created":"2021-05-12","cited_by_count":1,"area":null},{"id":"2203.10482","title":"DEIM: An effective deep encoding and interaction model for sentence matching","created":"2022-03-20","cited_by_count":1,"area":null},{"id":"2203.12264","title":"ECO v1: Towards Event-Centric Opinion Mining","created":"2022-03-23","cited_by_count":1,"area":null},{"id":"2302.13241","title":"Cross-Lingual Question Answering over Knowledge Base as Reading Comprehension","created":"2023-02-26","cited_by_count":1,"area":null},{"id":"2305.14104","title":"Out-of-Distribution Generalization in Text Classification: Past, Present, and Future","created":"2023-05-23","cited_by_count":1,"area":null},{"id":"2402.00978","title":"An Information-Theoretic Approach to Analyze NLP Classification Tasks","created":"2024-02-01","cited_by_count":1,"area":null},{"id":"2207.08943","title":"MRCLens: an MRC Dataset Bias Detection Toolkit","created":"2022-07-18","cited_by_count":0,"area":null},{"id":"2211.16093","title":"Penalizing Confident Predictions on Largely Perturbed Inputs Does Not Improve Out-of-Distribution Generalization in Question Answering","created":"2022-11-29","cited_by_count":0,"area":null},{"id":"2308.06235","title":"KETM:A Knowledge-Enhanced Text Matching method","created":"2023-08-11","cited_by_count":0,"area":null},{"id":"2403.00126","title":"FAC$^2$E: Better Understanding Large Language Model Capabilities by Dissociating Language and Cognition","created":"2024-02-29","cited_by_count":0,"area":null},{"id":"2408.05023","title":"Investigating a Benchmark for Training-set free Evaluation of Linguistic Capabilities in Machine Reading Comprehension","created":"2024-08-09","cited_by_count":0,"area":null}],"next_cursor":null}