{"total":53,"rows":[{"id":"2104.14337","title":"Dynabench: Rethinking Benchmarking in NLP","created":"2021-04-07","cited_by_count":459,"area":null},{"id":"2103.08541","title":"Get Your Vitamin C! Robust Fact Verification with Contrastive Evidence","created":"2021-03-15","cited_by_count":225,"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":"2104.06644","title":"Masked Language Modeling and the Distributional Hypothesis: Order Word Matters Pre-training for Little","created":"2021-04-14","cited_by_count":177,"area":null},{"id":"2102.12060","title":"Teach Me to Explain: A Review of Datasets for Explainable Natural Language Processing","created":"2021-02-24","cited_by_count":126,"area":null},{"id":"2207.10062","title":"DataPerf: Benchmarks for Data-Centric AI Development","created":"2022-07-20","cited_by_count":90,"area":null},{"id":"2106.09449","title":"DocNLI: A Large-scale Dataset for Document-level Natural Language Inference","created":"2021-06-17","cited_by_count":75,"area":null},{"id":"2207.14251","title":"Measuring Causal Effects of Data Statistics on Language Model's `Factual' Predictions","created":"2022-07-28","cited_by_count":57,"area":null},{"id":"2104.04725","title":"Fool Me Twice: Entailment from Wikipedia Gamification","created":"2021-04-10","cited_by_count":50,"area":null},{"id":"2205.00415","title":"Don't Blame the Annotator: Bias Already Starts in the Annotation Instructions","created":"2022-05-01","cited_by_count":47,"area":null},{"id":"2106.00969","title":"COM2SENSE: A Commonsense Reasoning Benchmark with Complementary Sentences","created":"2021-06-02","cited_by_count":40,"area":null},{"id":"2104.08161","title":"Back to Square One: Artifact Detection, Training and Commonsense Disentanglement in the Winograd Schema","created":"2021-04-16","cited_by_count":32,"area":null},{"id":"2304.09138","title":"Exploring the Trade-Offs: Unified Large Language Models vs Local Fine-Tuned Models for Highly-Specific Radiology NLI Task","created":"2023-04-18","cited_by_count":32,"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":"2205.01376","title":"Textual Entailment for Event Argument Extraction: Zero- and Few-Shot with Multi-Source Learning","created":"2022-05-03","cited_by_count":25,"area":null},{"id":"2110.08514","title":"Analyzing Dynamic Adversarial Training Data in the Limit","created":"2021-10-16","cited_by_count":24,"area":null},{"id":"2110.14566","title":"IndoNLI: A Natural Language Inference Dataset for Indonesian","created":"2021-10-27","cited_by_count":24,"area":null},{"id":"2109.04144","title":"Avoiding Inference Heuristics in Few-shot Prompt-based Finetuning","created":"2021-09-09","cited_by_count":23,"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":"2404.04963","title":"SemEval-2024 Task 2: Safe Biomedical Natural Language Inference for Clinical Trials","created":"2024-04-07","cited_by_count":20,"area":null},{"id":"2305.03598","title":"NLI4CT: Multi-Evidence Natural Language Inference for Clinical Trial Reports","created":"2023-05-05","cited_by_count":18,"area":null},{"id":"2106.01491","title":"MedNLI Is Not Immune: Natural Language Inference Artifacts in the Clinical Domain","created":"2021-06-02","cited_by_count":17,"area":null},{"id":"2101.10713","title":"Exploring Transitivity in Neural NLI Models through Veridicality","created":"2021-01-26","cited_by_count":15,"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":"2106.01077","title":"SyGNS: A Systematic Generalization Testbed Based on Natural Language Semantics","created":"2021-06-02","cited_by_count":7,"area":null},{"id":"2205.12181","title":"Partial-input baselines show that NLI models can ignore context, but they don't","created":"2022-05-24","cited_by_count":6,"area":null},{"id":"2212.03222","title":"LawngNLI: A Long-Premise Benchmark for In-Domain Generalization from Short to Long Contexts and for Implication-Based Retrieval","created":"2022-12-06","cited_by_count":6,"area":null},{"id":"2302.06976","title":"Investigating Multi-source Active Learning for Natural Language Inference","created":"2023-02-14","cited_by_count":6,"area":null},{"id":"2506.12379","title":"Training-free LLM Merging for Multi-task Learning","created":"2025-06-14","cited_by_count":6,"area":null},{"id":"2109.11888","title":"Robustness and Sensitivity of BERT Models Predicting Alzheimer's Disease from Text","created":"2021-09-24","cited_by_count":5,"area":null},{"id":"2306.01907","title":"A Simple yet Effective Self-Debiasing Framework for Transformer Models","created":"2023-06-02","cited_by_count":4,"area":null},{"id":"2307.02269","title":"SpaceNLI: Evaluating the Consistency of Predicting Inferences in Space","created":"2023-07-05","cited_by_count":4,"area":null},{"id":"2410.03429","title":"How Hard is this Test Set? NLI Characterization by Exploiting Training Dynamics","created":"2024-10-04","cited_by_count":4,"area":null},{"id":"2106.07353","title":"Posthoc Verification and the Fallibility of the Ground Truth","created":"2021-06-02","cited_by_count":3,"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":"2306.02190","title":"Stubborn Lexical Bias in Data and Models","created":"2023-06-03","cited_by_count":3,"area":null},{"id":"2404.06996","title":"XNLIeu: a dataset for cross-lingual NLI in Basque","created":"2024-04-10","cited_by_count":3,"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":"2203.12865","title":"Multilingual CheckList: Generation and Evaluation","created":"2022-03-24","cited_by_count":2,"area":null},{"id":"2209.05286","title":"DECK: Behavioral Tests to Improve Interpretability and Generalizability of BERT Models Detecting Depression from Text","created":"2022-09-12","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":"2503.05047","title":"Biases in Large Language Model-Elicited Text: A Case Study in Natural Language Inference","created":"2025-03-06","cited_by_count":1,"area":null},{"id":"2110.03323","title":"A Logic-Based Framework for Natural Language Inference in Dutch","created":"2021-10-07","cited_by_count":0,"area":null},{"id":"2210.01734","title":"Text Characterization Toolkit","created":"2022-10-04","cited_by_count":0,"area":null},{"id":"2311.09605","title":"Measuring and Improving Attentiveness to Partial Inputs with Counterfactuals","created":"2023-11-16","cited_by_count":0,"area":null},{"id":"2312.08747","title":"Dissecting vocabulary biases datasets through statistical testing and automated data augmentation for artifact mitigation in Natural Language Inference","created":"2023-12-14","cited_by_count":0,"area":null},{"id":"2405.00321","title":"DFKI-NLP at SemEval-2024 Task 2: Towards Robust LLMs Using Data Perturbations and MinMax Training","created":"2024-05-01","cited_by_count":0,"area":null},{"id":"2410.08996","title":"Hypothesis-only Biases in Large Language Model-Elicited Natural Language Inference","created":"2024-10-11","cited_by_count":0,"area":null},{"id":"2410.18764","title":"Task Calibration: Calibrating Large Language Models on Inference Tasks","created":"2024-10-24","cited_by_count":0,"area":null},{"id":"2506.21574","title":"Digital Gatekeepers: Exploring Large Language Model's Role in Immigration Decisions","created":"2025-06-15","cited_by_count":0,"area":null},{"id":"2510.24295","title":"MERGE: Minimal Expression-Replacement GEneralization Test for Natural Language Inference","created":"2025-10-28","cited_by_count":0,"area":null}],"next_cursor":null}