{"total":43,"rows":[{"id":"2305.17926","title":"Large Language Models are not Fair Evaluators","created":"2023-05-29","cited_by_count":1085,"area":null},{"id":"2104.14337","title":"Dynabench: Rethinking Benchmarking in NLP","created":"2021-04-07","cited_by_count":459,"area":null},{"id":"2207.10062","title":"DataPerf: Benchmarks for Data-Centric AI Development","created":"2022-07-20","cited_by_count":90,"area":null},{"id":"2206.14754","title":"Distilling Model Failures as Directions in Latent Space","created":"2022-06-29","cited_by_count":82,"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":"2110.01518","title":"Generalization in NLI: Ways (Not) To Go Beyond Simple Heuristics","created":"2021-10-04","cited_by_count":67,"area":null},{"id":"2111.07367","title":"\"Will You Find These Shortcuts?\" A Protocol for Evaluating the Faithfulness of Input Salience Methods for Text Classification","created":"2021-11-14","cited_by_count":66,"area":null},{"id":"2203.12942","title":"Generating Data to Mitigate Spurious Correlations in Natural Language Inference Datasets","created":"2022-03-24","cited_by_count":54,"area":null},{"id":"2106.05469","title":"Variational Information Bottleneck for Effective Low-Resource Fine-Tuning","created":"2021-06-10","cited_by_count":51,"area":null},{"id":"2107.00753","title":"An Investigation of the (In)effectiveness of Counterfactually Augmented Data","created":"2021-07-01","cited_by_count":42,"area":null},{"id":"2210.04692","title":"Language Prior Is Not the Only Shortcut: A Benchmark for Shortcut Learning in VQA","created":"2022-10-10","cited_by_count":30,"area":null},{"id":"2212.10534","title":"DISCO: Distilling Counterfactuals with Large Language Models","created":"2022-12-20","cited_by_count":30,"area":null},{"id":"2104.08142","title":"Supervising Model Attention with Human Explanations for Robust Natural Language Inference","created":"2021-04-16","cited_by_count":29,"area":null},{"id":"2110.01013","title":"Counterfactual Samples Synthesizing and Training for Robust Visual Question Answering","created":"2021-10-03","cited_by_count":22,"area":null},{"id":"2109.04947","title":"Tiered Reasoning for Intuitive Physics: Toward Verifiable Commonsense Language Understanding","created":"2021-09-10","cited_by_count":19,"area":null},{"id":"2106.04605","title":"Check It Again: Progressive Visual Question Answering via Visual Entailment","created":"2021-06-08","cited_by_count":18,"area":null},{"id":"2105.12628","title":"Predict then Interpolate: A Simple Algorithm to Learn Stable Classifiers","created":"2021-05-26","cited_by_count":16,"area":null},{"id":"2204.13749","title":"Learning to Split for Automatic Bias Detection","created":"2022-04-28","cited_by_count":16,"area":null},{"id":"2101.06980","title":"Mitigating the Position Bias of Transformer Models in Passage Re-Ranking","created":"2021-01-18","cited_by_count":10,"area":null},{"id":"2212.05421","title":"Feature-Level Debiased Natural Language Understanding","created":"2022-12-11","cited_by_count":10,"area":null},{"id":"2210.04563","title":"Towards Robust Visual Question Answering: Making the Most of Biased Samples via Contrastive Learning","created":"2022-10-10","cited_by_count":9,"area":null},{"id":"2108.12844","title":"Behind the Scenes: An Exploration of Trigger Biases Problem in Few-Shot Event Classification","created":"2021-08-29","cited_by_count":8,"area":null},{"id":"2112.09237","title":"PECO: Examining Single Sentence Label Leakage in Natural Language Inference Datasets through Progressive Evaluation of Cluster Outliers","created":"2021-12-16","cited_by_count":8,"area":null},{"id":"2106.07847","title":"Learning Stable Classifiers by Transferring Unstable Features","created":"2021-06-15","cited_by_count":6,"area":null},{"id":"2103.09635","title":"SILT: Efficient transformer training for inter-lingual inference","created":"2021-03-17","cited_by_count":5,"area":null},{"id":"2205.10363","title":"Robust Task-Oriented Dialogue Generation with Contrastive Pre-training and Adversarial Filtering","created":"2022-05-20","cited_by_count":4,"area":null},{"id":"2505.20209","title":"Improving the OOD Performance of Closed-Source LLMs on NLI Through Strategic Data Selection","created":"2025-05-26","cited_by_count":4,"area":null},{"id":"2108.14006","title":"A Generative Approach for Mitigating Structural Biases in Natural Language Inference","created":"2021-08-31","cited_by_count":3,"area":null},{"id":"2211.03862","title":"Looking at the Overlooked: An Analysis on the Word-Overlap Bias in Natural Language Inference","created":"2022-11-07","cited_by_count":3,"area":null},{"id":"2306.02190","title":"Stubborn Lexical Bias in Data and Models","created":"2023-06-03","cited_by_count":3,"area":null},{"id":"2307.02849","title":"NatLogAttack: A Framework for Attacking Natural Language Inference Models with Natural Logic","created":"2023-07-06","cited_by_count":3,"area":null},{"id":"2404.13390","title":"Explanation based Bias Decoupling Regularization for Natural Language Inference","created":"2024-04-20","cited_by_count":3,"area":null},{"id":"2504.16188","title":"FinNLI: Novel Dataset for Multi-Genre Financial Natural Language Inference Benchmarking","created":"2025-04-22","cited_by_count":3,"area":null},{"id":"2507.00985","title":"Discourse Heuristics For Paradoxically Moral Self-Correction","created":"2025-07-01","cited_by_count":3,"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":"2502.18798","title":"Choices Speak Louder than Questions","created":"2025-02-26","cited_by_count":2,"area":null},{"id":"2205.09934","title":"Towards Explanation for Unsupervised Graph-Level Representation Learning","created":"2022-05-20","cited_by_count":1,"area":null},{"id":"2305.19650","title":"Adverbs, Surprisingly","created":"2023-05-31","cited_by_count":1,"area":null},{"id":"2309.07009","title":"OYXOY: A Modern NLP Test Suite for Modern Greek","created":"2023-09-13","cited_by_count":1,"area":null},{"id":"2207.00187","title":"An Understanding-Oriented Robust Machine Reading Comprehension Model","created":"2022-07-01","cited_by_count":0,"area":null},{"id":"2210.01734","title":"Text Characterization Toolkit","created":"2022-10-04","cited_by_count":0,"area":null},{"id":"2503.17632","title":"FairFlow: Mitigating Dataset Biases through Undecided Learning","created":"2025-03-22","cited_by_count":0,"area":null},{"id":"2601.22699","title":"Models Know Models Best: Evaluation via Model-Preferred Formats","created":"2026-01-30","cited_by_count":0,"area":null}],"next_cursor":null}