{"total":134,"rows":[{"id":"2104.14337","title":"Dynabench: Rethinking Benchmarking in NLP","created":"2021-04-07","cited_by_count":459,"area":null},{"id":"2105.03075","title":"A Survey of Data Augmentation Approaches for NLP","created":"2021-05-07","cited_by_count":409,"area":null},{"id":"2101.00288","title":"Polyjuice: Generating Counterfactuals for Explaining, Evaluating, and Improving Models","created":"2021-01-01","cited_by_count":222,"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":"2305.14763","title":"Clever Hans or Neural Theory of Mind? Stress Testing Social Reasoning in Large Language Models","created":"2023-05-24","cited_by_count":163,"area":"lr"},{"id":"2105.09680","title":"KLUE: Korean Language Understanding Evaluation","created":"2021-05-20","cited_by_count":114,"area":null},{"id":"2101.04840","title":"Robustness Gym: Unifying the NLP Evaluation Landscape","created":"2021-01-13","cited_by_count":108,"area":null},{"id":"2307.06908","title":"Generating Benchmarks for Factuality Evaluation of Language Models","created":"2023-07-13","cited_by_count":105,"area":null},{"id":"2210.03050","title":"State-of-the-art generalisation research in NLP: A taxonomy and review","created":"2022-10-06","cited_by_count":98,"area":null},{"id":"2312.14033","title":"T-Eval: Evaluating the Tool Utilization Capability of Large Language Models Step by Step","created":"2023-12-21","cited_by_count":93,"area":null},{"id":"2205.12404","title":"FLUTE: Figurative Language Understanding through Textual Explanations","created":"2022-05-24","cited_by_count":79,"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":"2203.00211","title":"Investigating Selective Prediction Approaches Across Several Tasks in IID, OOD, and Adversarial Settings","created":"2022-03-01","cited_by_count":66,"area":null},{"id":"2205.12411","title":"Linear Connectivity Reveals Generalization Strategies","created":"2022-05-24","cited_by_count":56,"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":"2202.05834","title":"Predicting Out-of-Distribution Error with the Projection Norm","created":"2022-02-11","cited_by_count":50,"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":"2405.00722","title":"LLMs for Generating and Evaluating Counterfactuals: A Comprehensive Study","created":"2024-04-26","cited_by_count":31,"area":null},{"id":"2212.10534","title":"DISCO: Distilling Counterfactuals with Large Language Models","created":"2022-12-20","cited_by_count":30,"area":null},{"id":"2105.05541","title":"Evaluating Gender Bias in Natural Language Inference","created":"2021-05-12","cited_by_count":27,"area":null},{"id":"2110.03212","title":"Influence Tuning: Demoting Spurious Correlations via Instance Attribution and Instance-Driven Updates","created":"2021-10-07","cited_by_count":27,"area":null},{"id":"2106.01195","title":"Figurative Language in Recognizing Textual Entailment","created":"2021-06-02","cited_by_count":26,"area":null},{"id":"2102.08345","title":"NoiseQA: Challenge Set Evaluation for User-Centric Question Answering","created":"2021-02-16","cited_by_count":25,"area":null},{"id":"2105.14167","title":"NeuralLog: Natural Language Inference with Joint Neural and Logical Reasoning","created":"2021-05-29","cited_by_count":25,"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":"2210.04873","title":"CORE: A Retrieve-then-Edit Framework for Counterfactual Data Generation","created":"2022-10-10","cited_by_count":24,"area":null},{"id":"2305.17075","title":"CREST: A Joint Framework for Rationalization and Counterfactual Text Generation","created":"2023-05-26","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":"2203.07653","title":"Generalized but not Robust? Comparing the Effects of Data Modification Methods on Out-of-Domain Generalization and Adversarial Robustness","created":"2022-03-15","cited_by_count":23,"area":null},{"id":"2210.12365","title":"NeuroCounterfactuals: Beyond Minimal-Edit Counterfactuals for Richer Data Augmentation","created":"2022-10-22","cited_by_count":23,"area":null},{"id":"2109.05925","title":"Adversarial Examples for Evaluating Math Word Problem Solvers","created":"2021-09-13","cited_by_count":20,"area":null},{"id":"2109.08994","title":"ReaSCAN: Compositional Reasoning in Language Grounding","created":"2021-09-18","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":"2101.10713","title":"Exploring Transitivity in Neural NLI Models through Veridicality","created":"2021-01-26","cited_by_count":15,"area":null},{"id":"2104.08809","title":"SciCo: Hierarchical Cross-Document Coreference for Scientific Concepts","created":"2021-04-18","cited_by_count":14,"area":null},{"id":"2208.04826","title":"Compositional Evaluation on Japanese Textual Entailment and Similarity","created":"2022-08-09","cited_by_count":14,"area":null},{"id":"2208.08176","title":"Visual Comparison of Language Model Adaptation","created":"2022-08-17","cited_by_count":14,"area":null},{"id":"2401.14440","title":"Semantic Sensitivities and Inconsistent Predictions: Measuring the Fragility of NLI Models","created":"2024-01-25","cited_by_count":14,"area":null},{"id":"2204.05151","title":"Metaethical Perspectives on 'Benchmarking' AI Ethics","created":"2022-04-11","cited_by_count":12,"area":null},{"id":"2407.01992","title":"Is Your Large Language Model Knowledgeable or a Choices-Only Cheater?","created":"2024-07-02","cited_by_count":12,"area":null},{"id":"2201.00768","title":"Robust Natural Language Processing: Recent Advances, Challenges, and Future Directions","created":"2022-01-03","cited_by_count":11,"area":null},{"id":"2305.13654","title":"Understanding and Mitigating Spurious Correlations in Text Classification with Neighborhood Analysis","created":"2023-05-23","cited_by_count":11,"area":null},{"id":"2405.12434","title":"Resolving Word Vagueness with Scenario-guided Adapter for Natural Language Inference","created":"2024-05-21","cited_by_count":11,"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":"2106.07285","title":"Probing Pre-Trained Language Models for Disease Knowledge","created":"2021-06-14","cited_by_count":10,"area":null},{"id":"2212.00921","title":"AGRO: Adversarial Discovery of Error-prone groups for Robust Optimization","created":"2022-12-02","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":"2102.05331","title":"Language Models for Lexical Inference in Context","created":"2021-02-10","cited_by_count":9,"area":null},{"id":"2108.00578","title":"Is My Model Using The Right Evidence? Systematic Probes for Examining Evidence-Based Tabular Reasoning","created":"2021-08-02","cited_by_count":9,"area":null},{"id":"2110.07165","title":"Semantically Distributed Robust Optimization for Vision-and-Language Inference","created":"2021-10-14","cited_by_count":9,"area":null},{"id":"2310.14508","title":"EXPLAIN, EDIT, GENERATE: Rationale-Sensitive Counterfactual Data Augmentation for Multi-hop Fact Verification","created":"2023-10-23","cited_by_count":9,"area":null},{"id":"2107.07229","title":"Trusting RoBERTa over BERT: Insights from CheckListing the Natural Language Inference Task","created":"2021-07-15","cited_by_count":8,"area":null},{"id":"2110.07428","title":"Understanding Model Robustness to User-generated Noisy Texts","created":"2021-10-14","cited_by_count":8,"area":null},{"id":"2206.14729","title":"longhorns at DADC 2022: How many linguists does it take to fool a Question Answering model? A systematic approach to adversarial attacks","created":"2022-06-29","cited_by_count":8,"area":null},{"id":"2211.00609","title":"A Simple, Yet Effective Approach to Finding Biases in Code Generation","created":"2022-10-31","cited_by_count":8,"area":null},{"id":"2211.05417","title":"Can Transformers Reason in Fragments of Natural Language?","created":"2022-11-10","cited_by_count":8,"area":"lr"},{"id":"2411.05034","title":"Eguard: Defending LLM Embeddings Against Inversion Attacks via Text Mutual Information Optimization","created":"2024-11-06","cited_by_count":8,"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":"2110.08438","title":"Unsupervised Natural Language Inference Using PHL Triplet Generation","created":"2021-10-16","cited_by_count":6,"area":null},{"id":"2112.01753","title":"Probing Linguistic Information For Logical Inference In Pre-trained Language Models","created":"2021-12-03","cited_by_count":6,"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":"2311.08662","title":"Evaluating Concurrent Robustness of Language Models Across Diverse Challenge Sets","created":"2023-11-15","cited_by_count":6,"area":null},{"id":"2508.00965","title":"VAULT: Vigilant Adversarial Updates via LLM-Driven Retrieval-Augmented Generation for NLI","created":"2025-08-01","cited_by_count":6,"area":"rag"},{"id":"2108.13140","title":"DuTrust: A Sentiment Analysis Dataset for Trustworthiness Evaluation","created":"2021-08-30","cited_by_count":5,"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":"2204.12316","title":"Systematicity, Compositionality and Transitivity of Deep NLP Models: a Metamorphic Testing Perspective","created":"2022-04-26","cited_by_count":5,"area":null},{"id":"2305.18917","title":"Fighting Bias with Bias: Promoting Model Robustness by Amplifying Dataset Biases","created":"2023-05-30","cited_by_count":5,"area":null},{"id":"2311.04449","title":"Recursion in Recursion: Two-Level Nested Recursion for Length Generalization with Scalability","created":"2023-11-08","cited_by_count":5,"area":null},{"id":"2404.11717","title":"How often are errors in natural language reasoning due to paraphrastic variability?","created":"2024-04-17","cited_by_count":5,"area":"lr"},{"id":"2104.04751","title":"NLI Data Sanity Check: Assessing the Effect of Data Corruption on Model Performance","created":"2021-04-10","cited_by_count":4,"area":null},{"id":"2106.03983","title":"Investigating Transfer Learning in Multilingual Pre-trained Language Models through Chinese Natural Language Inference","created":"2021-06-07","cited_by_count":4,"area":null},{"id":"2109.05696","title":"How to Select One Among All? An Extensive Empirical Study Towards the Robustness of Knowledge Distillation in Natural Language Understanding","created":"2021-09-13","cited_by_count":4,"area":"distill"},{"id":"2201.02734","title":"Building Human-like Communicative Intelligence: A Grounded Perspective","created":"2022-01-02","cited_by_count":4,"area":null},{"id":"2210.12795","title":"Realistic Data Augmentation Framework for Enhancing Tabular Reasoning","created":"2022-10-23","cited_by_count":4,"area":null},{"id":"2211.16202","title":"AutoCAD: Automatically Generating Counterfactuals for Mitigating Shortcut Learning","created":"2022-11-29","cited_by_count":4,"area":null},{"id":"2305.15045","title":"SETI: Systematicity Evaluation of Textual Inference","created":"2023-05-24","cited_by_count":4,"area":null},{"id":"2306.10452","title":"MISMATCH: Fine-grained Evaluation of Machine-generated Text with Mismatch Error Types","created":"2023-06-18","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":"2307.10779","title":"Efficient Beam Tree Recursion","created":"2023-07-20","cited_by_count":4,"area":null},{"id":"2404.00748","title":"Benchmark Transparency: Measuring the Impact of Data on Evaluation","created":"2024-03-31","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":"2109.03695","title":"Continuous Entailment Patterns for Lexical Inference in Context","created":"2021-09-08","cited_by_count":3,"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":"2112.02333","title":"LoNLI: An Extensible Framework for Testing Diverse Logical Reasoning Capabilities for NLI","created":"2021-12-04","cited_by_count":3,"area":null},{"id":"2203.10483","title":"Entailment Relation Aware Paraphrase Generation","created":"2022-03-20","cited_by_count":3,"area":null},{"id":"2203.10693","title":"Leveraging Expert Guided Adversarial Augmentation For Improving Generalization in Named Entity Recognition","created":"2022-03-21","cited_by_count":3,"area":null},{"id":"2204.06283","title":"Curriculum: A Broad-Coverage Benchmark for Linguistic Phenomena in Natural Language Understanding","created":"2022-04-13","cited_by_count":3,"area":null},{"id":"2210.03068","title":"InferES : A Natural Language Inference Corpus for Spanish Featuring Negation-Based Contrastive and Adversarial Examples","created":"2022-10-06","cited_by_count":3,"area":null},{"id":"2210.12259","title":"Enhancing Tabular Reasoning with Pattern Exploiting Training","created":"2022-10-21","cited_by_count":3,"area":"lr"},{"id":"2306.11386","title":"Did the Models Understand Documents? Benchmarking Models for Language Understanding in Document-Level Relation Extraction","created":"2023-06-20","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":"2308.08778","title":"Environment Diversification with Multi-head Neural Network for Invariant Learning","created":"2023-08-17","cited_by_count":3,"area":null},{"id":"2502.09188","title":"Matina: A Large-Scale 73B Token Persian Text Corpus","created":"2025-02-13","cited_by_count":3,"area":null},{"id":"2108.00603","title":"TabPert: An Effective Platform for Tabular Perturbation","created":"2021-08-02","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}],"next_cursor":"100"}