{"total":21,"rows":[{"id":"2108.00573","title":"MuSiQue: Multihop Questions via Single-hop Question Composition","created":"2021-08-02","cited_by_count":916,"area":null},{"id":"2101.04840","title":"Robustness Gym: Unifying the NLP Evaluation Landscape","created":"2021-01-13","cited_by_count":108,"area":null},{"id":"2105.05612","title":"Evading the Simplicity Bias: Training a Diverse Set of Models Discovers Solutions with Superior OOD Generalization","created":"2021-05-12","cited_by_count":83,"area":null},{"id":"2108.06688","title":"Complex Knowledge Base Question Answering: A Survey","created":"2021-08-15","cited_by_count":52,"area":null},{"id":"2104.08731","title":"Can NLI Models Verify QA Systems' Predictions?","created":"2021-04-18","cited_by_count":46,"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":"2105.05541","title":"Evaluating Gender Bias in Natural Language Inference","created":"2021-05-12","cited_by_count":27,"area":null},{"id":"2207.02598","title":"Predicting is not Understanding: Recognizing and Addressing Underspecification in Machine Learning","created":"2022-07-06","cited_by_count":26,"area":null},{"id":"2308.07120","title":"Position: Key Claims in LLM Research Have a Long Tail of Footnotes","created":"2023-08-14","cited_by_count":20,"area":null},{"id":"2302.10914","title":"GLUECons: A Generic Benchmark for Learning Under Constraints","created":"2023-02-16","cited_by_count":9,"area":null},{"id":"2201.06384","title":"Cyberbullying Classifiers are Sensitive to Model-Agnostic Perturbations","created":"2022-01-17","cited_by_count":5,"area":null},{"id":"2201.02734","title":"Building Human-like Communicative Intelligence: A Grounded Perspective","created":"2022-01-02","cited_by_count":4,"area":null},{"id":"2110.08931","title":"Quantifying the Task-Specific Information in Text-Based Classifications","created":"2021-10-17","cited_by_count":3,"area":null},{"id":"2201.09639","title":"Question Generation for Evaluating Cross-Dataset Shifts in Multi-modal Grounding","created":"2022-01-24","cited_by_count":3,"area":null},{"id":"2209.01352","title":"Improving Compositional Generalization in Math Word Problem Solving","created":"2022-09-03","cited_by_count":3,"area":null},{"id":"2102.03016","title":"Model Agnostic Answer Reranking System for Adversarial Question Answering","created":"2021-02-05","cited_by_count":2,"area":null},{"id":"2203.06404","title":"A Proposal to Study \"Is High Quality Data All We Need?\"","created":"2022-03-12","cited_by_count":2,"area":null},{"id":"2404.01569","title":"Evaluating Large Language Models Using Contrast Sets: An Experimental Approach","created":"2024-04-02","cited_by_count":2,"area":null},{"id":"2210.07566","title":"A Survey of Parameters Associated with the Quality of Benchmarks in NLP","created":"2022-10-14","cited_by_count":1,"area":null},{"id":"2305.13535","title":"Improving Classifier Robustness through Active Generation of Pairwise Counterfactuals","created":"2023-05-22","cited_by_count":1,"area":null},{"id":"2308.07973","title":"\"Beware of deception\": Detecting Half-Truth and Debunking it through Controlled Claim Editing","created":"2023-08-15","cited_by_count":1,"area":null}],"next_cursor":null}