{"list":"other","total":87,"rows":[{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"id":"1804.07461","title":"GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding","created":"2018-04-20","cited_by_count":4899},{"id":"2305.20050","title":"Let's Verify Step by Step","created":"2023-05-31","cited_by_count":3789},{"id":"1704.05426","title":"A Broad-Coverage Challenge Corpus for Sentence Understanding through Inference","created":"2017-04-18","cited_by_count":2682},{"id":"2006.03654","title":"DeBERTa: Decoding-enhanced BERT with Disentangled Attention","created":"2020-06-05","cited_by_count":2181},{"id":"1508.05326","title":"A large annotated corpus for learning natural language inference","created":"2015-08-21","cited_by_count":1847},{"id":"2206.14858","title":"Solving Quantitative Reasoning Problems with Language Models","created":"2022-06-29","cited_by_count":1392},{"id":"1803.05355","title":"FEVER: a large-scale dataset for Fact Extraction and VERification","created":"2018-03-14","cited_by_count":1375},{"id":"2111.09543","title":"DeBERTaV3: Improving DeBERTa using ELECTRA-Style Pre-Training with Gradient-Disentangled Embedding Sharing","created":"2021-11-18","cited_by_count":1254},{"id":"2402.14008","title":"OlympiadBench: A Challenging Benchmark for Promoting AGI with Olympiad-Level Bilingual Multimodal Scientific Problems","created":"2024-02-21","cited_by_count":1136},{"id":"2409.12122","title":"Qwen2.5-Math Technical Report: Toward Mathematical Expert Model via Self-Improvement","created":"2024-09-18","cited_by_count":1090},{"id":"1902.01007","title":"Right for the Wrong Reasons: Diagnosing Syntactic Heuristics in Natural Language Inference","created":"2019-02-04","cited_by_count":876},{"id":"2303.15056","title":"ChatGPT Outperforms Crowd-Workers for Text-Annotation Tasks","created":"2023-03-27","cited_by_count":870},{"id":"1910.14599","title":"Adversarial NLI: A New Benchmark for Natural Language Understanding","created":"2019-10-31","cited_by_count":807},{"id":"1803.02324","title":"Annotation Artifacts in Natural Language Inference Data","created":"2018-03-06","cited_by_count":671},{"id":"1705.04146","title":"Program Induction by Rationale Generation : Learning to Solve and Explain Algebraic Word Problems","created":"2017-05-11","cited_by_count":650},{"id":"2412.13663","title":"Smarter, Better, Faster, Longer: A Modern Bidirectional Encoder for Fast, Memory Efficient, and Long Context Finetuning and Inference","created":"2024-12-18","cited_by_count":554},{"id":"2107.09044","title":"Just Train Twice: Improving Group Robustness without Training Group Information","created":"2021-07-19","cited_by_count":523},{"id":"1812.01193","title":"e-SNLI: Natural Language Inference with Natural Language Explanations","created":"2018-12-04","cited_by_count":468},{"id":"1909.12434","title":"Learning the Difference that Makes a Difference with Counterfactually-Augmented Data","created":"2019-09-26","cited_by_count":439},{"id":"2009.10795","title":"Dataset Cartography: Mapping and Diagnosing Datasets with Training Dynamics","created":"2020-09-22","cited_by_count":425},{"id":"1805.01042","title":"Hypothesis Only Baselines in Natural Language Inference","created":"2018-05-02","cited_by_count":295},{"id":"1909.03683","title":"Don't Take the Easy Way Out: Ensemble Based Methods for Avoiding Known Dataset Biases","created":"2019-09-09","cited_by_count":280},{"id":"2201.05955","title":"WANLI: Worker and AI Collaboration for Natural Language Inference Dataset Creation","created":"2022-01-16","cited_by_count":202},{"id":"2110.14503","title":"Simple data balancing achieves competitive worst-group-accuracy","created":"2021-10-27","cited_by_count":178},{"id":"2002.04108","title":"Adversarial Filters of Dataset Biases","created":"2020-02-10","cited_by_count":160},{"id":"2305.16938","title":"Few-shot Fine-tuning vs. In-context Learning: A Fair Comparison and Evaluation","created":"2023-05-26","cited_by_count":136},{"id":"2007.06778","title":"An Empirical Study on Robustness to Spurious Correlations using Pre-trained Language Models","created":"2020-07-14","cited_by_count":134},{"id":"1909.06321","title":"End-to-End Bias Mitigation by Modelling Biases in Corpora","created":"2019-09-13","cited_by_count":128},{"id":"1811.07039","title":"Combining Fact Extraction and Verification with Neural Semantic Matching Networks","created":"2018-11-16","cited_by_count":120},{"id":"1908.10763","title":"Unlearn Dataset Bias in Natural Language Inference by Fitting the Residual","created":"2019-08-28","cited_by_count":119},{"id":"2009.12303","title":"Towards Debiasing NLU Models from Unknown Biases","created":"2020-09-25","cited_by_count":116},{"id":"2005.12116","title":"NILE : Natural Language Inference with Faithful Natural Language Explanations","created":"2020-05-25","cited_by_count":96},{"id":"2104.08646","title":"Competency Problems: On Finding and Removing Artifacts in Language Data","created":"2021-04-17","cited_by_count":91},{"id":"1911.02969","title":"BERTs of a feather do not generalize together: Large variability in generalization across models with similar test set performance","created":"2019-11-07","cited_by_count":89},{"id":"2004.11999","title":"Syntactic Data Augmentation Increases Robustness to Inference Heuristics","created":"2020-04-24","cited_by_count":86},{"id":"2005.00315","title":"Mind the Trade-off: Debiasing NLU Models without Degrading the In-distribution Performance","created":"2020-05-01","cited_by_count":85},{"id":"2012.01300","title":"Learning from others' mistakes: Avoiding dataset biases without modeling them","created":"2020-12-02","cited_by_count":83},{"id":"2103.06922","title":"Towards Interpreting and Mitigating Shortcut Learning Behavior of NLU Models","created":"2021-03-11","cited_by_count":78},{"id":"2501.10970","title":"The Alternative Annotator Test for LLM-as-a-Judge: How to Statistically Justify Replacing Human Annotators with LLMs","created":"2025-01-19","cited_by_count":74},{"id":"2004.09034","title":"Learning What Makes a Difference from Counterfactual Examples and Gradient Supervision","created":"2020-04-20","cited_by_count":66},{"id":"2104.07163","title":"Annealing Knowledge Distillation","created":"2021-04-14","cited_by_count":61},{"id":"2106.05469","title":"Variational Information Bottleneck for Effective Low-Resource Fine-Tuning","created":"2021-06-10","cited_by_count":51},{"id":"1907.04380","title":"Don't Take the Premise for Granted: Mitigating Artifacts in Natural Language Inference","created":"2019-07-09","cited_by_count":49},{"id":"1808.08609","title":"Adversarially Regularising Neural NLI Models to Integrate Logical Background Knowledge","created":"2018-08-26","cited_by_count":46},{"id":"2011.03856","title":"Learning to Model and Ignore Dataset Bias with Mixed Capacity Ensembles","created":"2020-11-07","cited_by_count":43},{"id":"2408.05534","title":"Can LLMs Replace Manual Annotation of Software Engineering Artifacts?","created":"2024-08-10","cited_by_count":42},{"id":"1911.00225","title":"When Choosing Plausible Alternatives, Clever Hans can be Clever","created":"2019-11-01","cited_by_count":40},{"id":"2502.01968","title":"Token Cleaning: Fine-Grained Data Selection for LLM Supervised Fine-Tuning","created":"2025-02-04","cited_by_count":39},{"id":"1907.04389","title":"On Adversarial Removal of Hypothesis-only Bias in Natural Language Inference","created":"2019-07-09","cited_by_count":29},{"id":"2105.05912","title":"MATE-KD: Masked Adversarial TExt, a Companion to Knowledge Distillation","created":"2021-05-12","cited_by_count":27},{"id":"2305.04990","title":"Explanation-based Finetuning Makes Models More Robust to Spurious Cues","created":"2023-05-08","cited_by_count":25},{"id":"2012.09157","title":"LIREx: Augmenting Language Inference with Relevant Explanation","created":"2020-12-16","cited_by_count":24},{"id":"2109.02071","title":"End-to-End Self-Debiasing Framework for Robust NLU Training","created":"2021-09-05","cited_by_count":24},{"id":"2311.07811","title":"In-context Learning Generalizes, But Not Always Robustly: The Case of Syntax","created":"2023-11-13","cited_by_count":22},{"id":"2503.11441","title":"D3: Diversity, Difficulty, and Dependability-Aware Data Selection for Sample-Efficient LLM Instruction Tuning","created":"2025-03-14","cited_by_count":21},{"id":"2505.12212","title":"Data Whisperer: Efficient Data Selection for Task-Specific LLM Fine-Tuning via Few-Shot In-Context Learning","created":"2025-05-18","cited_by_count":20},{"id":"2205.11432","title":"Logical Reasoning with Span-Level Predictions for Interpretable and Robust NLI Models","created":"2022-05-23","cited_by_count":18},{"id":"2305.13214","title":"Atomic Inference for NLI with Generated Facts as Atoms","created":"2023-05-22","cited_by_count":18},{"id":"2010.03777","title":"An Empirical Study on Model-agnostic Debiasing Strategies for Robust Natural Language Inference","created":"2020-10-08","cited_by_count":16},{"id":"2105.12628","title":"Predict then Interpolate: A Simple Algorithm to Learn Stable Classifiers","created":"2021-05-26","cited_by_count":16},{"id":"2111.04104","title":"Uncertainty Calibration for Ensemble-Based Debiasing Methods","created":"2021-11-07","cited_by_count":16},{"id":"2204.13749","title":"Learning to Split for Automatic Bias Detection","created":"2022-04-28","cited_by_count":16},{"id":"2305.17804","title":"Targeted Data Generation: Finding and Fixing Model Weaknesses","created":"2023-05-28","cited_by_count":15},{"id":"2402.12368","title":"A synthetic data approach for domain generalization of NLI models","created":"2024-02-19","cited_by_count":15},{"id":"2205.12593","title":"Less Learn Shortcut: Analyzing and Mitigating Learning of Spurious Feature-Label Correlation","created":"2022-05-25","cited_by_count":13},{"id":"2305.15017","title":"Calc-X and Calcformers: Empowering Arithmetical Chain-of-Thought through Interaction with Symbolic Systems","created":"2023-05-24","cited_by_count":13},{"id":"2311.09825","title":"Human Still Wins over LLM: An Empirical Study of Active Learning on Domain-Specific Annotation Tasks","created":"2023-11-16","cited_by_count":13},{"id":"2212.00921","title":"AGRO: Adversarial Discovery of Error-prone groups for Robust Optimization","created":"2022-12-02","cited_by_count":10},{"id":"2305.17627","title":"Robust Natural Language Understanding with Residual Attention Debiasing","created":"2023-05-28","cited_by_count":10},{"id":"2210.13575","title":"Does Self-Rationalization Improve Robustness to Spurious Correlations?","created":"2022-10-24","cited_by_count":9},{"id":"2501.07719","title":"Entailed Between the Lines: Incorporating Implication into NLI","created":"2025-01-13","cited_by_count":9},{"id":"2201.06777","title":"COPA-SSE: Semi-structured Explanations for Commonsense Reasoning","created":"2022-01-18","cited_by_count":8},{"id":"2410.14745","title":"Semi-supervised Fine-tuning for Large Language Models","created":"2024-10-17","cited_by_count":8},{"id":"2305.13067","title":"Distilling Robustness into Natural Language Inference Models with Domain-Targeted Augmentation","created":"2023-05-22","cited_by_count":7},{"id":"2403.00462","title":"LUCID: LLM-Generated Utterances for Complex and Interesting Dialogues","created":"2024-03-01","cited_by_count":7},{"id":"2412.09263","title":"First Train to Generate, then Generate to Train: UnitedSynT5 for Few-Shot NLI","created":"2024-12-12","cited_by_count":7},{"id":"2204.07674","title":"CILDA: Contrastive Data Augmentation using Intermediate Layer Knowledge Distillation","created":"2022-04-15","cited_by_count":4},{"id":"2306.01907","title":"A Simple yet Effective Self-Debiasing Framework for Transformer Models","created":"2023-06-02","cited_by_count":4},{"id":"2410.03429","title":"How Hard is this Test Set? NLI Characterization by Exploiting Training Dynamics","created":"2024-10-04","cited_by_count":4},{"id":"2504.14810","title":"DONOD: Efficient and Generalizable Instruction Fine-Tuning for LLMs via Model-Intrinsic Dataset Pruning","created":"2025-04-21","cited_by_count":4},{"id":"2404.13390","title":"Explanation based Bias Decoupling Regularization for Natural Language Inference","created":"2024-04-20","cited_by_count":3},{"id":"2311.00292","title":"IBADR: an Iterative Bias-Aware Dataset Refinement Framework for Debiasing NLU models","created":"2023-11-01","cited_by_count":2},{"id":"2409.07423","title":"Enhancing adversarial robustness in Natural Language Inference using explanations","created":"2024-09-11","cited_by_count":2},{"id":"2502.09567","title":"MorphNLI: A Stepwise Approach to Natural Language Inference Using Text Morphing","created":"2025-02-13","cited_by_count":2},{"id":"2410.10865","title":"Generating Synthetic Datasets for Few-shot Prompt Tuning","created":"2024-10-08","cited_by_count":1}],"next_cursor":null}