{"list":"other","total":55,"rows":[{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"1910.10683","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","created":"2019-10-23","cited_by_count":14599},{"id":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"id":"1910.13461","title":"BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension","created":"2019-10-29","cited_by_count":5893},{"id":"1602.04938","title":"\"Why Should I Trust You?\": Explaining the Predictions of Any Classifier","created":"2016-02-16","cited_by_count":5070},{"id":"1910.01108","title":"DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter","created":"2019-10-02","cited_by_count":4307},{"id":"1703.01365","title":"Axiomatic Attribution for Deep Networks","created":"2017-03-04","cited_by_count":3384},{"id":"1704.05426","title":"A Broad-Coverage Challenge Corpus for Sentence Understanding through Inference","created":"2017-04-18","cited_by_count":2682},{"id":"1509.01626","title":"Character-level Convolutional Networks for Text Classification","created":"2015-09-04","cited_by_count":2330},{"id":"1508.05326","title":"A large annotated corpus for learning natural language inference","created":"2015-08-21","cited_by_count":1847},{"id":"1811.12231","title":"ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness","created":"2018-11-29","cited_by_count":1432},{"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":"2004.09456","title":"StereoSet: Measuring stereotypical bias in pretrained language models","created":"2020-04-20","cited_by_count":924},{"id":"1901.11196","title":"EDA: Easy Data Augmentation Techniques for Boosting Performance on Text Classification Tasks","created":"2019-01-31","cited_by_count":807},{"id":"1511.06709","title":"Improving Neural Machine Translation Models with Monolingual Data","created":"2015-11-20","cited_by_count":788},{"id":"2010.00133","title":"CrowS-Pairs: A Challenge Dataset for Measuring Social Biases in Masked Language Models","created":"2020-09-30","cited_by_count":710},{"id":"1804.06876","title":"Gender Bias in Coreference Resolution: Evaluation and Debiasing Methods","created":"2018-04-18","cited_by_count":659},{"id":"1807.04975","title":"Recognition in Terra Incognita","created":"2018-07-13","cited_by_count":658},{"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":"2109.02846","title":"Datasets: A Community Library for Natural Language Processing","created":"2021-09-07","cited_by_count":530},{"id":"2111.12797","title":"ReAct: Out-of-distribution Detection With Rectified Activations","created":"2021-11-24","cited_by_count":486},{"id":"1909.12434","title":"Learning the Difference that Makes a Difference with Counterfactually-Augmented Data","created":"2019-09-26","cited_by_count":439},{"id":"2101.00288","title":"Polyjuice: Generating Counterfactuals for Explaining, Evaluating, and Improving Models","created":"2021-01-01","cited_by_count":222},{"id":"1803.06535","title":"Dear Sir or Madam, May I introduce the GYAFC Dataset: Corpus, Benchmarks and Metrics for Formality Style Transfer","created":"2018-03-17","cited_by_count":211},{"id":"1906.04571","title":"Counterfactual Data Augmentation for Mitigating Gender Stereotypes in Languages with Rich Morphology","created":"2019-06-11","cited_by_count":200},{"id":"2104.08826","title":"GPT3Mix: Leveraging Large-scale Language Models for Text Augmentation","created":"2021-04-18","cited_by_count":187},{"id":"2007.08100","title":"Towards Debiasing Sentence Representations","created":"2020-07-16","cited_by_count":171},{"id":"2302.13007","title":"AugGPT: Leveraging ChatGPT for Text Data Augmentation","created":"2023-02-25","cited_by_count":130},{"id":"1812.06705","title":"Conditional BERT Contextual Augmentation","created":"2018-12-17","cited_by_count":107},{"id":"2202.05594","title":"The Shapley Value in Machine Learning","created":"2022-02-11","cited_by_count":98},{"id":"2110.07736","title":"Identifying and Mitigating Spurious Correlations for Improving Robustness in NLP Models","created":"2021-10-14","cited_by_count":76},{"id":"2106.11410","title":"A Survey of Race, Racism, and Anti-Racism in NLP","created":"2021-06-21","cited_by_count":75},{"id":"2012.10040","title":"Robustness to Spurious Correlations in Text Classification via Automatically Generated Counterfactuals","created":"2020-12-18","cited_by_count":67},{"id":"2010.02458","title":"Identifying Spurious Correlations for Robust Text Classification","created":"2020-10-06","cited_by_count":59},{"id":"2311.08648","title":"Explore Spurious Correlations at the Concept Level in Language Models for Text Classification","created":"2023-11-15","cited_by_count":48},{"id":"2009.06207","title":"Contrastive Triple Extraction with Generative Transformer","created":"2020-09-14","cited_by_count":44},{"id":"2305.14791","title":"Prompting Large Language Models for Counterfactual Generation: An Empirical Study","created":"2023-05-24","cited_by_count":37},{"id":"2310.18236","title":"How Re-sampling Helps for Long-Tail Learning?","created":"2023-10-27","cited_by_count":36},{"id":"2210.14011","title":"Are All Spurious Features in Natural Language Alike? An Analysis through a Causal Lens","created":"2022-10-25","cited_by_count":28},{"id":"2306.04597","title":"Language Models Get a Gender Makeover: Mitigating Gender Bias with Few-Shot Data Interventions","created":"2023-06-07","cited_by_count":28},{"id":"2110.03212","title":"Influence Tuning: Demoting Spurious Correlations via Instance Attribution and Instance-Driven Updates","created":"2021-10-07","cited_by_count":27},{"id":"2305.17075","title":"CREST: A Joint Framework for Rationalization and Counterfactual Text Generation","created":"2023-05-26","cited_by_count":24},{"id":"2407.03993","title":"A Survey on Natural Language Counterfactual Generation","created":"2024-07-04","cited_by_count":21},{"id":"2106.03315","title":"Semantic and Syntactic Enhanced Aspect Sentiment Triplet Extraction","created":"2021-06-07","cited_by_count":17},{"id":"2309.07822","title":"CATfOOD: Counterfactual Augmented Training for Improving Out-of-Domain Performance and Calibration","created":"2023-09-14","cited_by_count":17},{"id":"2401.06643","title":"Effects of diversity incentives on sample diversity and downstream model performance in LLM-based text augmentation","created":"2024-01-12","cited_by_count":17},{"id":"2305.13654","title":"Understanding and Mitigating Spurious Correlations in Text Classification with Neighborhood Analysis","created":"2023-05-23","cited_by_count":11},{"id":"2207.08982","title":"Selection Bias Induced Spurious Correlations in Large Language Models","created":"2022-07-18","cited_by_count":9},{"id":"2304.12425","title":"TIGTEC : Token Importance Guided TExt Counterfactuals","created":"2023-04-24","cited_by_count":8},{"id":"2406.06633","title":"PairCFR: Enhancing Model Training on Paired Counterfactually Augmented Data through Contrastive Learning","created":"2024-06-09","cited_by_count":7},{"id":"2307.07002","title":"Classical Out-of-Distribution Detection Methods Benchmark in Text Classification Tasks","created":"2023-07-13","cited_by_count":5},{"id":"2404.01921","title":"A Rationale-centric Counterfactual Data Augmentation Method for Cross-Document Event Coreference Resolution","created":"2024-04-02","cited_by_count":5},{"id":"2306.12146","title":"Which Spurious Correlations Impact Reasoning in NLI Models? A Visual Interactive Diagnosis through Data-Constrained Counterfactuals","created":"2023-06-21","cited_by_count":4}],"next_cursor":null}