{"list":"other","total":98,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"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":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"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":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"2107.03374","title":"Evaluating Large Language Models Trained on Code","created":"2021-07-07","cited_by_count":8320},{"id":"1705.07874","title":"A Unified Approach to Interpreting Model Predictions","created":"2017-05-22","cited_by_count":6555},{"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":"2203.11171","title":"Self-Consistency Improves Chain of Thought Reasoning in Language Models","created":"2022-03-21","cited_by_count":5708},{"id":"2205.11916","title":"Large Language Models are Zero-Shot Reasoners","created":"2022-05-24","cited_by_count":4374},{"id":"1703.01365","title":"Axiomatic Attribution for Deep Networks","created":"2017-03-04","cited_by_count":3384},{"id":"2210.11416","title":"Scaling Instruction-Finetuned Language Models","created":"2022-10-20","cited_by_count":3024},{"id":"2202.05262","title":"Locating and Editing Factual Associations in GPT","created":"2022-02-10","cited_by_count":2691},{"id":"1901.08746","title":"BioBERT: a pre-trained biomedical language representation model for biomedical text mining","created":"2019-01-25","cited_by_count":1947},{"id":"2205.10625","title":"Least-to-Most Prompting Enables Complex Reasoning in Large Language Models","created":"2022-05-21","cited_by_count":1407},{"id":"1808.08745","title":"Don't Give Me the Details, Just the Summary! Topic-Aware Convolutional Neural Networks for Extreme Summarization","created":"2018-08-27","cited_by_count":1317},{"id":"2211.00593","title":"Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small","created":"2022-11-01","cited_by_count":1165},{"id":"2301.05217","title":"Progress measures for grokking via mechanistic interpretability","created":"2023-01-12","cited_by_count":839},{"id":"1806.07421","title":"RISE: Randomized Input Sampling for Explanation of Black-box Models","created":"2018-06-19","cited_by_count":838},{"id":"1905.10650","title":"Are Sixteen Heads Really Better than One?","created":"2019-05-25","cited_by_count":816},{"id":"2304.14997","title":"Towards Automated Circuit Discovery for Mechanistic Interpretability","created":"2023-04-28","cited_by_count":724},{"id":"1909.03368","title":"Designing and Interpreting Probes with Control Tasks","created":"2019-09-08","cited_by_count":640},{"id":"2004.03685","title":"Towards Faithfully Interpretable NLP Systems: How should we define and evaluate faithfulness?","created":"2020-04-07","cited_by_count":599},{"id":"1911.03429","title":"ERASER: A Benchmark to Evaluate Rationalized NLP Models","created":"2019-11-08","cited_by_count":530},{"id":"1806.00069","title":"Explaining Explanations: An Overview of Interpretability of Machine Learning","created":"2018-05-31","cited_by_count":508},{"id":"1812.01193","title":"e-SNLI: Natural Language Inference with Natural Language Explanations","created":"2018-12-04","cited_by_count":468},{"id":"1905.06316","title":"What do you learn from context? Probing for sentence structure in contextualized word representations","created":"2019-05-15","cited_by_count":438},{"id":"2303.03846","title":"Larger language models do in-context learning differently","created":"2023-03-07","cited_by_count":394},{"id":"1906.02361","title":"Explain Yourself! Leveraging Language Models for Commonsense Reasoning","created":"2019-06-06","cited_by_count":367},{"id":"2305.07922","title":"CodeT5+: Open Code Large Language Models for Code Understanding and Generation","created":"2023-05-13","cited_by_count":333},{"id":"2309.01029","title":"Explainability for Large Language Models: A Survey","created":"2023-09-02","cited_by_count":333},{"id":"2205.05055","title":"Data Distributional Properties Drive Emergent In-Context Learning in Transformers","created":"2022-04-22","cited_by_count":309},{"id":"2201.08164","title":"From Anecdotal Evidence to Quantitative Evaluation Methods: A Systematic Review on Evaluating Explainable AI","created":"2022-01-20","cited_by_count":302},{"id":"1906.05714","title":"A Multiscale Visualization of Attention in the Transformer Model","created":"2019-06-12","cited_by_count":292},{"id":"2011.07876","title":"A Survey on the Explainability of Supervised Machine Learning","created":"2020-11-16","cited_by_count":227},{"id":"2311.10723","title":"Large Language Models in Finance: A Survey","created":"2023-09-28","cited_by_count":226},{"id":"2106.00737","title":"Implicit Representations of Meaning in Neural Language Models","created":"2021-06-01","cited_by_count":180},{"id":"1804.05392","title":"Higher-order Coreference Resolution with Coarse-to-fine Inference","created":"2018-04-15","cited_by_count":150},{"id":"2004.14546","title":"WT5?! Training Text-to-Text Models to Explain their Predictions","created":"2020-04-30","cited_by_count":148},{"id":"1908.04211","title":"On Identifiability in Transformers","created":"2019-08-12","cited_by_count":116},{"id":"2004.14786","title":"Perturbed Masking: Parameter-free Probing for Analyzing and Interpreting BERT","created":"2020-04-30","cited_by_count":109},{"id":"2203.09095","title":"Automating Code Review Activities by Large-Scale Pre-training","created":"2022-03-17","cited_by_count":98},{"id":"2307.08678","title":"Do Models Explain Themselves? Counterfactual Simulatability of Natural Language Explanations","created":"2023-07-17","cited_by_count":85},{"id":"2104.03514","title":"Low-Complexity Probing via Finding Subnetworks","created":"2021-04-08","cited_by_count":64},{"id":"1907.07237","title":"FAHT: An Adaptive Fairness-aware Decision Tree Classifier","created":"2019-07-16","cited_by_count":63},{"id":"2404.01349","title":"Fairness in Large Language Models: A Taxonomic Survey","created":"2024-03-31","cited_by_count":58},{"id":"1801.07772","title":"Evaluating Layers of Representation in Neural Machine Translation on Part-of-Speech and Semantic Tagging Tasks","created":"2018-01-23","cited_by_count":56},{"id":"2401.12874","title":"From Understanding to Utilization: A Survey on Explainability for Large Language Models","created":"2024-01-23","cited_by_count":48},{"id":"2409.00265","title":"Explainable Artificial Intelligence: A Survey of Needs, Techniques, Applications, and Future Direction","created":"2024-08-30","cited_by_count":46},{"id":"2007.00236","title":"SemEval-2020 Task 4: Commonsense Validation and Explanation","created":"2020-07-01","cited_by_count":42},{"id":"2101.09429","title":"Explainable Artificial Intelligence Approaches: A Survey","created":"2021-01-23","cited_by_count":40},{"id":"2104.05882","title":"Discourse Probing of Pretrained Language Models","created":"2021-04-13","cited_by_count":38},{"id":"2501.05435","title":"Neuro-Symbolic AI in 2024: A Systematic Review","created":"2025-01-09","cited_by_count":38},{"id":"2104.05824","title":"Evaluating Saliency Methods for Neural Language Models","created":"2021-04-12","cited_by_count":37},{"id":"2108.07403","title":"FARF: A Fair and Adaptive Random Forests Classifier","created":"2021-08-17","cited_by_count":37},{"id":"2407.21065","title":"LawLLM: Law Large Language Model for the US Legal System","created":"2024-07-27","cited_by_count":37},{"id":"2307.05052","title":"Towards Understanding In-Context Learning with Contrastive Demonstrations and Saliency Maps","created":"2023-07-11","cited_by_count":35},{"id":"1805.04787","title":"Jointly Predicting Predicates and Arguments in Neural Semantic Role Labeling","created":"2018-05-12","cited_by_count":34},{"id":"2105.00827","title":"AMMU : A Survey of Transformer-based Biomedical Pretrained Language Models","created":"2021-04-16","cited_by_count":32},{"id":"2402.06853","title":"History, Development, and Principles of Large Language Models-An Introductory Survey","created":"2024-02-10","cited_by_count":30},{"id":"2104.01477","title":"Exploring the Role of BERT Token Representations to Explain Sentence Probing Results","created":"2021-04-03","cited_by_count":29},{"id":"2105.02657","title":"Improving the Faithfulness of Attention-based Explanations with Task-specific Information for Text Classification","created":"2021-05-06","cited_by_count":29},{"id":"2402.11863","title":"How Interpretable are Reasoning Explanations from Prompting Large Language Models?","created":"2024-02-19","cited_by_count":29},{"id":"2010.07276","title":"Disentangled Dynamic Graph Deep Generation","created":"2020-10-14","cited_by_count":27},{"id":"2104.05904","title":"DirectProbe: Studying Representations without Classifiers","created":"2021-04-13","cited_by_count":25},{"id":"2306.05731","title":"Multimodal Explainable Artificial Intelligence: A Comprehensive Review of Methodological Advances and Future Research Directions","created":"2023-06-09","cited_by_count":25},{"id":"1808.08315","title":"A Deterministic Self-Organizing Map Approach and its Application on Satellite Data based Cloud Type Classification","created":"2018-08-24","cited_by_count":22},{"id":"2203.16024","title":"Longitudinal Fairness with Censorship","created":"2022-03-30","cited_by_count":22},{"id":"2101.00196","title":"On Explaining Your Explanations of BERT: An Empirical Study with Sequence Classification","created":"2021-01-01","cited_by_count":21},{"id":"2202.07170","title":"Fairness Amidst Non-IID Graph Data: A Literature Review","created":"2022-02-15","cited_by_count":20},{"id":"2302.09587","title":"On the Reliability and Explainability of Language Models for Program Generation","created":"2023-02-19","cited_by_count":17},{"id":"2312.01279","title":"TextGenSHAP: Scalable Post-hoc Explanations in Text Generation with Long Documents","created":"2023-12-03","cited_by_count":17},{"id":"2112.06204","title":"Few-Shot Out-of-Domain Transfer Learning of Natural Language Explanations in a Label-Abundant Setup","created":"2021-12-12","cited_by_count":16},{"id":"2301.12364","title":"Fair Decision-making Under Uncertainty","created":"2023-01-29","cited_by_count":15},{"id":"2407.18745","title":"FairAIED: Navigating Fairness, Bias, and Ethics in Educational AI Applications","created":"2024-07-26","cited_by_count":15},{"id":"2010.08146","title":"Online and Customizable Fairness-aware Learning","created":"2020-10-15","cited_by_count":14},{"id":"2302.08018","title":"Towards Fair Machine Learning Software: Understanding and Addressing Model Bias Through Counterfactual Thinking","created":"2023-02-16","cited_by_count":14},{"id":"2108.02924","title":"Interpretable Visual Understanding with Cognitive Attention Network","created":"2021-08-06","cited_by_count":12},{"id":"2302.08017","title":"Preventing Discriminatory Decision-making in Evolving Data Streams","created":"2023-02-16","cited_by_count":12},{"id":"2109.07043","title":"Attention Is Indeed All You Need: Semantically Attention-Guided Decoding for Data-to-Text NLG","created":"2021-09-15","cited_by_count":11},{"id":"2302.08015","title":"Individual Fairness under Uncertainty","created":"2023-02-16","cited_by_count":11},{"id":"2407.18454","title":"Fairness Definitions in Language Models Explained","created":"2024-07-26","cited_by_count":11},{"id":"2502.00837","title":"Explainability in Practice: A Survey of Explainable NLP Across Various Domains","created":"2025-02-02","cited_by_count":11},{"id":"2307.14239","title":"Revisiting the Performance-Explainability Trade-Off in Explainable Artificial Intelligence (XAI)","created":"2023-07-26","cited_by_count":10},{"id":"2504.02963","title":"Digital Forensics in the Age of Large Language Models","created":"2025-04-03","cited_by_count":10},{"id":"2104.02205","title":"Attention Head Masking for Inference Time Content Selection in Abstractive Summarization","created":"2021-04-06","cited_by_count":9},{"id":"2009.06891","title":"Global-aware Beam Search for Neural Abstractive Summarization","created":"2020-09-15","cited_by_count":8},{"id":"2201.11650","title":"Incremental Mining of Frequent Serial Episodes Considering Multiple Occurrences","created":"2022-01-27","cited_by_count":7},{"id":"2506.23411","title":"Datasets for Fairness in Language Models: An In-Depth Survey","created":"2025-06-29","cited_by_count":7},{"id":"2406.02625","title":"Progressive Inference: Explaining Decoder-Only Sequence Classification Models Using Intermediate Predictions","created":"2024-06-03","cited_by_count":6},{"id":"2108.13140","title":"DuTrust: A Sentiment Analysis Dataset for Trustworthiness Evaluation","created":"2021-08-30","cited_by_count":5},{"id":"2407.11773","title":"Educational Personalized Learning Path Planning with Large Language Models","created":"2024-07-16","cited_by_count":5},{"id":"2008.08769","title":"Lite Training Strategies for Portuguese-English and English-Portuguese Translation","created":"2020-08-20","cited_by_count":4},{"id":"2207.13948","title":"An Interpretability Evaluation Benchmark for Pre-trained Language Models","created":"2022-07-28","cited_by_count":4},{"id":"2509.00641","title":"AMCR: A Framework for Assessing and Mitigating Copyright Risks in Generative Models","created":"2025-08-31","cited_by_count":3}],"next_cursor":null}