{"total":30,"rows":[{"id":"2206.01861","title":"ZeroQuant: Efficient and Affordable Post-Training Quantization for Large-Scale Transformers","created":"2022-06-04","cited_by_count":526,"area":null},{"id":"2210.10045","title":"SafeText: A Benchmark for Exploring Physical Safety in Language Models","created":"2022-10-18","cited_by_count":41,"area":null},{"id":"2110.08300","title":"The Dangers of Underclaiming: Reasons for Caution When Reporting How NLP Systems Fail","created":"2021-10-15","cited_by_count":38,"area":null},{"id":"2106.00872","title":"On the Efficacy of Adversarial Data Collection for Question Answering: Results from a Large-Scale Randomized Study","created":"2021-06-02","cited_by_count":31,"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":"2209.03392","title":"Investigating Reasons for Disagreement in Natural Language Inference","created":"2022-09-07","cited_by_count":29,"area":null},{"id":"2406.05183","title":"The Factorization Curse: Which Tokens You Predict Underlie the Reversal Curse and More","created":"2024-06-07","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":"2203.06414","title":"A Survey of Adversarial Defences and Robustness in NLP","created":"2022-03-12","cited_by_count":23,"area":null},{"id":"2402.09394","title":"Long-form evaluation of model editing","created":"2024-02-14","cited_by_count":23,"area":null},{"id":"2204.01906","title":"Dynatask: A Framework for Creating Dynamic AI Benchmark Tasks","created":"2022-04-05","cited_by_count":16,"area":null},{"id":"2506.07371","title":"ARGUS: Hallucination and Omission Evaluation in Video-LLMs","created":"2025-06-09","cited_by_count":16,"area":null},{"id":"2107.00807","title":"He Thinks He Knows Better than the Doctors: BERT for Event Factuality Fails on Pragmatics","created":"2021-07-02","cited_by_count":12,"area":null},{"id":"2111.08181","title":"Adversarially Constructed Evaluation Sets Are More Challenging, but May Not Be Fair","created":"2021-11-16","cited_by_count":12,"area":null},{"id":"2203.06342","title":"What Makes Reading Comprehension Questions Difficult?","created":"2022-03-12","cited_by_count":11,"area":null},{"id":"2211.11586","title":"Random-LTD: Random and Layerwise Token Dropping Brings Efficient Training for Large-scale Transformers","created":"2022-11-17","cited_by_count":11,"area":null},{"id":"2212.03419","title":"JamPatoisNLI: A Jamaican Patois Natural Language Inference Dataset","created":"2022-12-07","cited_by_count":11,"area":null},{"id":"2505.01595","title":"Always Tell Me The Odds: Fine-grained Conditional Probability Estimation","created":"2025-05-02","cited_by_count":9,"area":null},{"id":"2204.10615","title":"Generalized Quantifiers as a Source of Error in Multilingual NLU Benchmarks","created":"2022-04-22","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":"2304.05511","title":"Training Large Language Models Efficiently with Sparsity and Dataflow","created":"2023-04-11","cited_by_count":7,"area":null},{"id":"2109.09057","title":"Knowledge-Enhanced Evidence Retrieval for Counterargument Generation","created":"2021-09-19","cited_by_count":6,"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":"2210.14606","title":"Analyzing Multi-Task Learning for Abstractive Text Summarization","created":"2022-10-26","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":"2304.11257","title":"Who's the Best Detective? LLMs vs. MLs in Detecting Incoherent Fourth Grade Math Answers","created":"2023-04-21","cited_by_count":3,"area":null},{"id":"2306.04925","title":"Prefer to Classify: Improving Text Classifiers via Auxiliary Preference Learning","created":"2023-06-08","cited_by_count":2,"area":null},{"id":"2310.12467","title":"Contrastive Learning for Inference in Dialogue","created":"2023-10-19","cited_by_count":0,"area":null},{"id":"2409.13735","title":"Analysis of Socially Unacceptable Discourse with Zero-shot Learning","created":"2024-09-10","cited_by_count":0,"area":null}],"next_cursor":null}