{"total":165,"rows":[{"id":"2101.02235","title":"Did Aristotle Use a Laptop? A Question Answering Benchmark with Implicit Reasoning Strategies","created":"2021-01-06","cited_by_count":743,"area":null},{"id":"2110.05719","title":"Dealing with Disagreements: Looking Beyond the Majority Vote in Subjective Annotations","created":"2021-10-12","cited_by_count":314,"area":null},{"id":"2111.07997","title":"Annotators with Attitudes: How Annotator Beliefs And Identities Bias Toxic Language Detection","created":"2021-11-15","cited_by_count":264,"area":null},{"id":"2305.08283","title":"From Pretraining Data to Language Models to Downstream Tasks: Tracking the Trails of Political Biases Leading to Unfair NLP Models","created":"2023-05-15","cited_by_count":260,"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":"2406.04127","title":"Are We Done with MMLU?","created":"2024-06-06","cited_by_count":194,"area":null},{"id":"2104.06039","title":"MultiModalQA: Complex Question Answering over Text, Tables and Images","created":"2021-04-13","cited_by_count":179,"area":null},{"id":"2209.11326","title":"Towards Faithful Model Explanation in NLP: A Survey","created":"2022-09-22","cited_by_count":130,"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":"2112.08674","title":"Reframing Human-AI Collaboration for Generating Free-Text Explanations","created":"2021-12-16","cited_by_count":125,"area":null},{"id":"2104.06001","title":"Gender Bias in Machine Translation","created":"2021-04-13","cited_by_count":117,"area":null},{"id":"2209.03430","title":"Foundations and Trends in Multimodal Machine Learning: Principles, Challenges, and Open Questions","created":"2022-09-07","cited_by_count":116,"area":null},{"id":"2112.08313","title":"Measure and Improve Robustness in NLP Models: A Survey","created":"2021-12-15","cited_by_count":107,"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":"2104.08646","title":"Competency Problems: On Finding and Removing Artifacts in Language Data","created":"2021-04-17","cited_by_count":91,"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":"2207.10062","title":"DataPerf: Benchmarks for Data-Centric AI Development","created":"2022-07-20","cited_by_count":90,"area":null},{"id":"2109.01653","title":"CREAK: A Dataset for Commonsense Reasoning over Entity Knowledge","created":"2021-09-03","cited_by_count":88,"area":null},{"id":"2210.07700","title":"Language Generation Models Can Cause Harm: So What Can We Do About It? An Actionable Survey","created":"2022-10-14","cited_by_count":80,"area":null},{"id":"2104.08678","title":"Improving Question Answering Model Robustness with Synthetic Adversarial Data Generation","created":"2021-04-18","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":"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":"2202.05433","title":"A Survey on Programmatic Weak Supervision","created":"2022-02-11","cited_by_count":66,"area":null},{"id":"2307.15703","title":"Uncertainty in Natural Language Generation: From Theory to Applications","created":"2023-07-28","cited_by_count":61,"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":"2106.06052","title":"Dynaboard: An Evaluation-As-A-Service Platform for Holistic Next-Generation Benchmarking","created":"2021-05-21","cited_by_count":53,"area":null},{"id":"2105.13947","title":"Changing the World by Changing the Data","created":"2021-05-28","cited_by_count":51,"area":null},{"id":"2206.09917","title":"Multilingual HateCheck: Functional Tests for Multilingual Hate Speech Detection Models","created":"2022-06-20","cited_by_count":51,"area":null},{"id":"2108.06130","title":"Semantic Answer Similarity for Evaluating Question Answering Models","created":"2021-08-13","cited_by_count":47,"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":"2106.06823","title":"Prompting Contrastive Explanations for Commonsense Reasoning Tasks","created":"2021-06-12","cited_by_count":45,"area":null},{"id":"2203.01111","title":"Large-Scale Hate Speech Detection with Cross-Domain Transfer","created":"2022-03-02","cited_by_count":41,"area":null},{"id":"2307.08153","title":"Analyzing Dataset Annotation Quality Management in the Wild","created":"2023-07-16","cited_by_count":41,"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":"2305.14663","title":"You Are What You Annotate: Towards Better Models through Annotator Representations","created":"2023-05-24","cited_by_count":40,"area":null},{"id":"2109.12072","title":"SD-QA: Spoken Dialectal Question Answering for the Real World","created":"2021-09-24","cited_by_count":38,"area":null},{"id":"2405.05860","title":"The Perspectivist Paradigm Shift: Assumptions and Challenges of Capturing Human Labels","created":"2024-05-09","cited_by_count":38,"area":null},{"id":"2110.14375","title":"Perceptual Score: What Data Modalities Does Your Model Perceive?","created":"2021-10-27","cited_by_count":35,"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":"2112.09062","title":"Models in the Loop: Aiding Crowdworkers with Generative Annotation Assistants","created":"2021-12-16","cited_by_count":31,"area":null},{"id":"2310.13486","title":"Mind the instructions: a holistic evaluation of consistency and interactions in prompt-based learning","created":"2023-10-20","cited_by_count":31,"area":null},{"id":"2402.10412","title":"Measuring and Reducing LLM Hallucination without Gold-Standard Answers","created":"2024-02-16","cited_by_count":31,"area":null},{"id":"2410.07991","title":"Human and LLM Biases in Hate Speech Annotations: A Socio-Demographic Analysis of Annotators and Targets","created":"2024-10-10","cited_by_count":31,"area":null},{"id":"2103.09591","title":"Automatic Generation of Contrast Sets from Scene Graphs: Probing the Compositional Consistency of GQA","created":"2021-03-17","cited_by_count":30,"area":null},{"id":"2104.07179","title":"Does Putting a Linguist in the Loop Improve NLU Data Collection?","created":"2021-04-15","cited_by_count":29,"area":null},{"id":"2203.15867","title":"Image Retrieval from Contextual Descriptions","created":"2022-03-29","cited_by_count":26,"area":null},{"id":"2311.11202","title":"Unmasking and Improving Data Credibility: A Study with Datasets for Training Harmless Language Models","created":"2023-11-19","cited_by_count":26,"area":null},{"id":"2312.06861","title":"Disentangling Perceptions of Offensiveness: Cultural and Moral Correlates","created":"2023-12-11","cited_by_count":26,"area":null},{"id":"2105.02590","title":"Reliability Testing for Natural Language Processing Systems","created":"2021-05-06","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":"2305.04990","title":"Explanation-based Finetuning Makes Models More Robust to Spurious Cues","created":"2023-05-08","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":"2205.11930","title":"The Authenticity Gap in Human Evaluation","created":"2022-05-24","cited_by_count":24,"area":null},{"id":"2403.00393","title":"TRUCE: Private Benchmarking to Prevent Contamination and Improve Comparative Evaluation of LLMs","created":"2024-03-01","cited_by_count":24,"area":null},{"id":"2106.00794","title":"What Ingredients Make for an Effective Crowdsourcing Protocol for Difficult NLU Data Collection Tasks?","created":"2021-06-01","cited_by_count":23,"area":null},{"id":"2109.15107","title":"CrossAug: A Contrastive Data Augmentation Method for Debiasing Fact Verification Models","created":"2021-09-30","cited_by_count":23,"area":null},{"id":"2305.08414","title":"What's the Meaning of Superhuman Performance in Today's NLU?","created":"2023-05-15","cited_by_count":23,"area":null},{"id":"2210.14531","title":"Unifying Data Perspectivism and Personalization: An Application to Social Norms","created":"2022-10-26","cited_by_count":22,"area":null},{"id":"2104.07555","title":"Data-QuestEval: A Referenceless Metric for Data-to-Text Semantic Evaluation","created":"2021-04-15","cited_by_count":21,"area":null},{"id":"2306.15261","title":"A Survey on Out-of-Distribution Evaluation of Neural NLP Models","created":"2023-06-27","cited_by_count":20,"area":null},{"id":"2405.14383","title":"Perception of Knowledge Boundary for Large Language Models through Semi-open-ended Question Answering","created":"2024-05-23","cited_by_count":20,"area":null},{"id":"2107.11610","title":"Context-aware Adversarial Training for Name Regularity Bias in Named Entity Recognition","created":"2021-07-24","cited_by_count":19,"area":null},{"id":"2110.04419","title":"Detecting Community Sensitive Norm Violations in Online Conversations","created":"2021-10-09","cited_by_count":18,"area":null},{"id":"2203.08597","title":"Less is More: Summary of Long Instructions is Better for Program Synthesis","created":"2022-03-16","cited_by_count":17,"area":null},{"id":"2205.11963","title":"The Data-Production Dispositif","created":"2022-05-24","cited_by_count":16,"area":null},{"id":"2310.13850","title":"Ecologically Valid Explanations for Label Variation in NLI","created":"2023-10-20","cited_by_count":16,"area":null},{"id":"2103.01242","title":"Cryptonite: A Cryptic Crossword Benchmark for Extreme Ambiguity in Language","created":"2021-03-01","cited_by_count":15,"area":null},{"id":"2402.16102","title":"Interpreting Predictive Probabilities: Model Confidence or Human Label Variation?","created":"2024-02-25","cited_by_count":15,"area":null},{"id":"2502.01523","title":"CondAmbigQA: A Benchmark and Dataset for Conditional Ambiguous Question Answering","created":"2025-02-03","cited_by_count":15,"area":null},{"id":"2109.06838","title":"ePiC: Employing Proverbs in Context as a Benchmark for Abstract Language Understanding","created":"2021-09-14","cited_by_count":14,"area":null},{"id":"2110.08038","title":"Toward Annotator Group Bias in Crowdsourcing","created":"2021-10-08","cited_by_count":14,"area":null},{"id":"2311.14212","title":"Annotation Sensitivity: Training Data Collection Methods Affect Model Performance","created":"2023-11-23","cited_by_count":14,"area":null},{"id":"2102.11573","title":"Automated Quality Assessment of Cognitive Behavioral Therapy Sessions Through Highly Contextualized Language Representations","created":"2021-02-23","cited_by_count":13,"area":null},{"id":"2112.04895","title":"Latent Space Explanation by Intervention","created":"2021-12-09","cited_by_count":13,"area":null},{"id":"2601.09065","title":"Beyond Consensus: Perspectivist Modeling and Evaluation of Annotator Disagreement in NLP","created":"2026-01-14","cited_by_count":13,"area":null},{"id":"2112.07475","title":"Two Contrasting Data Annotation Paradigms for Subjective NLP Tasks","created":"2021-12-14","cited_by_count":12,"area":null},{"id":"2304.05967","title":"Angler: Helping Machine Translation Practitioners Prioritize Model Improvements","created":"2023-04-12","cited_by_count":12,"area":null},{"id":"2109.08131","title":"Studying Up Machine Learning Data: Why Talk About Bias When We Mean Power?","created":"2021-09-16","cited_by_count":11,"area":null},{"id":"2112.03529","title":"Ground-Truth, Whose Truth? -- Examining the Challenges with Annotating Toxic Text Datasets","created":"2021-12-07","cited_by_count":11,"area":null},{"id":"2404.10857","title":"D3CODE: Disentangling Disagreements in Data across Cultures on Offensiveness Detection and Evaluation","created":"2024-04-16","cited_by_count":11,"area":null},{"id":"2407.18078","title":"PEFT-U: Parameter-Efficient Fine-Tuning for User Personalization","created":"2024-07-25","cited_by_count":11,"area":null},{"id":"2305.12710","title":"Beyond Labels: Empowering Human Annotators with Natural Language Explanations through a Novel Active-Learning Architecture","created":"2023-05-22","cited_by_count":10,"area":null},{"id":"2106.09775","title":"An Information Retrieval Approach to Building Datasets for Hate Speech Detection","created":"2021-06-17","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":"2306.05115","title":"Closing the Loop: Testing ChatGPT to Generate Model Explanations to Improve Human Labelling of Sponsored Content on Social Media","created":"2023-06-08","cited_by_count":9,"area":null},{"id":"2106.02382","title":"Annotation Curricula to Implicitly Train Non-Expert Annotators","created":"2021-06-04","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":"2302.07371","title":"BiasTestGPT: Using ChatGPT for Social Bias Testing of Language Models","created":"2023-02-14","cited_by_count":8,"area":null},{"id":"2402.06811","title":"Discipline and Label: A WEIRD Genealogy and Social Theory of Data Annotation","created":"2024-02-09","cited_by_count":8,"area":null},{"id":"2408.08411","title":"Rater Cohesion and Quality from a Vicarious Perspective","created":"2024-08-15","cited_by_count":8,"area":null},{"id":"2501.00962","title":"OASIS Uncovers: High-Quality T2I Models, Same Old Stereotypes","created":"2025-01-01","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":"2203.12913","title":"k-Rater Reliability: The Correct Unit of Reliability for Aggregated Human Annotations","created":"2022-03-24","cited_by_count":7,"area":null},{"id":"2210.04573","title":"HumSet: Dataset of Multilingual Information Extraction and Classification for Humanitarian Crisis Response","created":"2022-10-10","cited_by_count":7,"area":null},{"id":"2404.12145","title":"From Form(s) to Meaning: Probing the Semantic Depths of Language Models Using Multisense Consistency","created":"2024-04-18","cited_by_count":7,"area":null},{"id":"2211.11513","title":"DSLOB: A Synthetic Limit Order Book Dataset for Benchmarking Forecasting Algorithms under Distributional Shift","created":"2022-11-17","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":"2305.18034","title":"A Corpus for Sentence-level Subjectivity Detection on English News Articles","created":"2023-05-29","cited_by_count":6,"area":null},{"id":"2104.10130","title":"Hidden Biases in Unreliable News Detection Datasets","created":"2021-04-20","cited_by_count":5,"area":null}],"next_cursor":"100"}