{"list":"other","total":84,"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":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"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":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"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":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"2107.03374","title":"Evaluating Large Language Models Trained on Code","created":"2021-07-07","cited_by_count":8320},{"id":"2009.03300","title":"Measuring Massive Multitask Language Understanding","created":"2020-09-07","cited_by_count":7963},{"id":"1705.07874","title":"A Unified Approach to Interpreting Model Predictions","created":"2017-05-22","cited_by_count":6555},{"id":"2204.02311","title":"PaLM: Scaling Language Modeling with Pathways","created":"2022-04-05","cited_by_count":5326},{"id":"2410.21276","title":"GPT-4o System Card","created":"2024-10-25","cited_by_count":4588},{"id":"1910.01108","title":"DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter","created":"2019-10-02","cited_by_count":4307},{"id":"2108.07258","title":"On the Opportunities and Risks of Foundation Models","created":"2021-08-16","cited_by_count":4033},{"id":"1911.02116","title":"Unsupervised Cross-lingual Representation Learning at Scale","created":"2019-11-05","cited_by_count":3935},{"id":"2204.05862","title":"Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback","created":"2022-04-12","cited_by_count":3720},{"id":"2403.05530","title":"Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context","created":"2024-03-08","cited_by_count":3224},{"id":"2101.03961","title":"Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity","created":"2021-01-11","cited_by_count":3073},{"id":"2312.10997","title":"Retrieval-Augmented Generation for Large Language Models: A Survey","created":"2023-12-18","cited_by_count":2212},{"id":"2308.12950","title":"Code Llama: Open Foundation Models for Code","created":"2023-08-24","cited_by_count":2139},{"id":"2202.03629","title":"Survey of Hallucination in Natural Language Generation","created":"2022-02-08","cited_by_count":2075},{"id":"2211.05100","title":"BLOOM: A 176B-Parameter Open-Access Multilingual Language Model","created":"2022-11-09","cited_by_count":1984},{"id":"2401.04088","title":"Mixtral of Experts","created":"2024-01-08","cited_by_count":1823},{"id":"2006.16668","title":"GShard: Scaling Giant Models with Conditional Computation and Automatic Sharding","created":"2020-06-30","cited_by_count":1631},{"id":"1702.08608","title":"Towards A Rigorous Science of Interpretable Machine Learning","created":"2017-02-28","cited_by_count":1416},{"id":"2409.12186","title":"Qwen2.5-Coder Technical Report","created":"2024-09-18","cited_by_count":1203},{"id":"2306.14824","title":"Kosmos-2: Grounding Multimodal Large Language Models to the World","created":"2023-06-26","cited_by_count":1089},{"id":"2103.10360","title":"GLM: General Language Model Pretraining with Autoregressive Blank Infilling","created":"2021-03-18","cited_by_count":1031},{"id":"1802.01933","title":"A Survey Of Methods For Explaining Black Box Models","created":"2018-02-06","cited_by_count":973},{"id":"2403.08295","title":"Gemma: Open Models Based on Gemini Research and Technology","created":"2024-03-13","cited_by_count":916},{"id":"2309.03409","title":"Large Language Models as Optimizers","created":"2023-09-07","cited_by_count":864},{"id":"2301.05217","title":"Progress measures for grokking via mechanistic interpretability","created":"2023-01-12","cited_by_count":839},{"id":"2211.09085","title":"Galactica: A Large Language Model for Science","created":"2022-11-16","cited_by_count":744},{"id":"2204.06745","title":"GPT-NeoX-20B: An Open-Source Autoregressive Language Model","created":"2022-04-14","cited_by_count":713},{"id":"2401.02954","title":"DeepSeek LLM: Scaling Open-Source Language Models with Longtermism","created":"2024-01-05","cited_by_count":642},{"id":"1701.07875","title":"Wasserstein GAN","created":"2017-01-26","cited_by_count":639},{"id":"2401.02385","title":"TinyLlama: An Open-Source Small Language Model","created":"2024-01-04","cited_by_count":618},{"id":"1704.03296","title":"Interpretable Explanations of Black Boxes by Meaningful Perturbation","created":"2017-04-11","cited_by_count":612},{"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":"2309.05463","title":"Textbooks Are All You Need II: phi-1.5 technical report","created":"2023-09-11","cited_by_count":565},{"id":"2311.16867","title":"The Falcon Series of Open Language Models","created":"2023-11-28","cited_by_count":535},{"id":"2105.13626","title":"ByT5: Towards a token-free future with pre-trained byte-to-byte models","created":"2021-05-28","cited_by_count":509},{"id":"2402.19173","title":"StarCoder 2 and The Stack v2: The Next Generation","created":"2024-02-29","cited_by_count":502},{"id":"2010.16061","title":"Evaluation: from precision, recall and F-measure to ROC, informedness, markedness and correlation","created":"2020-10-11","cited_by_count":425},{"id":"2309.01029","title":"Explainability for Large Language Models: A Survey","created":"2023-09-02","cited_by_count":333},{"id":"2212.10071","title":"Large Language Models Are Reasoning Teachers","created":"2022-12-20","cited_by_count":329},{"id":"1812.08951","title":"Analysis Methods in Neural Language Processing: A Survey","created":"2018-12-21","cited_by_count":277},{"id":"2309.11235","title":"OpenChat: Advancing Open-source Language Models with Mixed-Quality Data","created":"2023-09-20","cited_by_count":252},{"id":"2303.10420","title":"A Comprehensive Capability Analysis of GPT-3 and GPT-3.5 Series Models","created":"2023-03-18","cited_by_count":246},{"id":"1808.00033","title":"Techniques for Interpretable Machine Learning","created":"2018-07-31","cited_by_count":238},{"id":"1310.4375","title":"Fast Computation of Wasserstein Barycenters","created":"2013-10-16","cited_by_count":216},{"id":"2001.06216","title":"GraphLIME: Local Interpretable Model Explanations for Graph Neural Networks","created":"2020-01-17","cited_by_count":209},{"id":"1708.08296","title":"Explainable Artificial Intelligence: Understanding, Visualizing and Interpreting Deep Learning Models","created":"2017-08-28","cited_by_count":206},{"id":"2108.04840","title":"Post-hoc Interpretability for Neural NLP: A Survey","created":"2021-08-10","cited_by_count":156},{"id":"2209.11326","title":"Towards Faithful Model Explanation in NLP: A Survey","created":"2022-09-22","cited_by_count":130},{"id":"2402.18060","title":"Benchmarking Large Language Models on Answering and Explaining Challenging Medical Questions","created":"2024-02-28","cited_by_count":109},{"id":"2402.04614","title":"Faithfulness vs. Plausibility: On the (Un)Reliability of Explanations from Large Language Models","created":"2024-02-07","cited_by_count":105},{"id":"2302.11520","title":"Guiding Large Language Models via Directional Stimulus Prompting","created":"2023-02-22","cited_by_count":95},{"id":"2404.01869","title":"Beyond Accuracy: Evaluating the Reasoning Behavior of Large Language Models -- A Survey","created":"2024-04-02","cited_by_count":83},{"id":"2106.16138","title":"XLM-E: Cross-lingual Language Model Pre-training via ELECTRA","created":"2021-06-30","cited_by_count":72},{"id":"2106.07875","title":"S-LIME: Stabilized-LIME for Model Explanation","created":"2021-06-15","cited_by_count":52},{"id":"2012.03058","title":"BayLIME: Bayesian Local Interpretable Model-Agnostic Explanations","created":"2020-12-05","cited_by_count":51},{"id":"2312.15407","title":"A Comprehensive Analysis of the Effectiveness of Large Language Models as Automatic Dialogue Evaluators","created":"2023-12-24","cited_by_count":45},{"id":"1909.02437","title":"ALIME: Autoencoder Based Approach for Local Interpretability","created":"2019-09-04","cited_by_count":41},{"id":"2502.06855","title":"Self-Supervised Prompt Optimization","created":"2025-02-07","cited_by_count":37},{"id":"2006.05714","title":"OptiLIME: Optimized LIME Explanations for Diagnostic Computer Algorithms","created":"2020-06-10","cited_by_count":30},{"id":"2109.08438","title":"TS-MULE: Local Interpretable Model-Agnostic Explanations for Time Series Forecast Models","created":"2021-09-17","cited_by_count":28},{"id":"2502.05489","title":"Mechanistic Interpretability of Emotion Inference in Large Language Models","created":"2025-02-08","cited_by_count":27},{"id":"2502.15871","title":"A Comprehensive Survey on the Trustworthiness of Large Language Models in Healthcare","created":"2025-02-21","cited_by_count":27},{"id":"2412.16100","title":"Logical Consistency of Large Language Models in Fact-checking","created":"2024-12-20","cited_by_count":15},{"id":"2502.12131","title":"Transformer Dynamics: A neuroscientific approach to interpretability of large language models","created":"2025-02-17","cited_by_count":11},{"id":"2202.08063","title":"Information Extraction in Low-Resource Scenarios: Survey and Perspective","created":"2022-02-16","cited_by_count":10},{"id":"2311.07286","title":"Explaining black boxes with a SMILE: Statistical Model-agnostic Interpretability with Local Explanations","created":"2023-11-13","cited_by_count":8},{"id":"2503.24365","title":"Which LIME should I trust? Concepts, Challenges, and Solutions","created":"2025-03-31","cited_by_count":8},{"id":"2403.07706","title":"Fast and Simple Explainability for Point Cloud Networks","created":"2024-03-12","cited_by_count":6},{"id":"2406.16203","title":"LLMs' Classification Performance is Overclaimed","created":"2024-06-23","cited_by_count":6},{"id":"2505.07610","title":"Concept-Level Explainability for Auditing & Steering LLM Responses","created":"2025-05-12","cited_by_count":6},{"id":"2410.15374","title":"Explainability of Point Cloud Neural Networks Using SMILE: Statistical Model-Agnostic Interpretability with Local Explanations","created":"2024-10-20","cited_by_count":4},{"id":"2403.17742","title":"Using Stratified Sampling to Improve LIME Image Explanations","created":"2024-03-26","cited_by_count":3},{"id":"2412.16277","title":"Mapping the Mind of an Instruction-based Image Editing using SMILE","created":"2024-12-20","cited_by_count":3},{"id":"2505.03368","title":"Geospatial Mechanistic Interpretability of Large Language Models","created":"2025-05-06","cited_by_count":2},{"id":"2505.12509","title":"Revitalizing Black-Box Interpretability: Actionable Interpretability for LLMs via Proxy Models","created":"2025-05-18","cited_by_count":2}],"next_cursor":null}