{"list":"other","total":56,"rows":[{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"1908.10084","title":"Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks","created":"2019-08-27","cited_by_count":9170},{"id":"1705.07874","title":"A Unified Approach to Interpreting Model Predictions","created":"2017-05-22","cited_by_count":6555},{"id":"1602.04938","title":"\"Why Should I Trust You?\": Explaining the Predictions of Any Classifier","created":"2016-02-16","cited_by_count":5070},{"id":"1809.09600","title":"HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering","created":"2018-09-25","cited_by_count":3754},{"id":"2307.03172","title":"Lost in the Middle: How Language Models Use Long Contexts","created":"2023-07-06","cited_by_count":3455},{"id":"2310.06825","title":"Mistral 7B","created":"2023-10-10","cited_by_count":3164},{"id":"2307.15043","title":"Universal and Transferable Adversarial Attacks on Aligned Language Models","created":"2023-07-27","cited_by_count":3104},{"id":"1312.6034","title":"Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps","created":"2013-12-20","cited_by_count":2371},{"id":"2404.14219","title":"Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone","created":"2024-04-22","cited_by_count":1917},{"id":"2112.09332","title":"WebGPT: Browser-assisted question-answering with human feedback","created":"2021-12-17","cited_by_count":1745},{"id":"1611.09268","title":"MS MARCO: A Human Generated MAchine Reading COmprehension Dataset","created":"2016-11-28","cited_by_count":1605},{"id":"2311.05232","title":"A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions","created":"2023-11-09","cited_by_count":1601},{"id":"2302.12173","title":"Not what you've signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injection","created":"2023-02-23","cited_by_count":1443},{"id":"2305.14251","title":"FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generation","created":"2023-05-23","cited_by_count":1282},{"id":"2201.08239","title":"LaMDA: Language Models for Dialog Applications","created":"2022-01-20","cited_by_count":1220},{"id":"1706.03825","title":"SmoothGrad: removing noise by adding noise","created":"2017-06-12","cited_by_count":1109},{"id":"1902.10186","title":"Attention is not Explanation","created":"2019-02-26","cited_by_count":929},{"id":"1903.00161","title":"DROP: A Reading Comprehension Benchmark Requiring Discrete Reasoning Over Paragraphs","created":"2019-03-01","cited_by_count":903},{"id":"2211.09527","title":"Ignore Previous Prompt: Attack Techniques For Language Models","created":"2022-11-17","cited_by_count":832},{"id":"1602.06023","title":"Abstractive Text Summarization Using Sequence-to-Sequence RNNs and Beyond","created":"2016-02-19","cited_by_count":812},{"id":"2005.00928","title":"Quantifying Attention Flow in Transformers","created":"2020-05-02","cited_by_count":775},{"id":"1908.07125","title":"Universal Adversarial Triggers for Attacking and Analyzing NLP","created":"2019-08-20","cited_by_count":722},{"id":"2305.14627","title":"Enabling Large Language Models to Generate Text with Citations","created":"2023-05-24","cited_by_count":595},{"id":"2003.05002","title":"TyDi QA: A Benchmark for Information-Seeking Question Answering in Typologically Diverse Languages","created":"2020-03-10","cited_by_count":488},{"id":"1906.03731","title":"Is Attention Interpretable?","created":"2019-06-09","cited_by_count":389},{"id":"2308.03296","title":"Studying Large Language Model Generalization with Influence Functions","created":"2023-08-07","cited_by_count":326},{"id":"2304.09848","title":"Evaluating Verifiability in Generative Search Engines","created":"2023-04-19","cited_by_count":303},{"id":"1605.01713","title":"Not Just a Black Box: Learning Important Features Through Propagating Activation Differences","created":"2016-05-05","cited_by_count":297},{"id":"2203.11147","title":"Teaching language models to support answers with verified quotes","created":"2022-03-21","cited_by_count":292},{"id":"2210.08726","title":"RARR: Researching and Revising What Language Models Say, Using Language Models","created":"2022-10-17","cited_by_count":287},{"id":"2303.14186","title":"TRAK: Attributing Model Behavior at Scale","created":"2023-03-24","cited_by_count":283},{"id":"2112.12870","title":"Measuring Attribution in Natural Language Generation Models","created":"2021-12-23","cited_by_count":256},{"id":"2307.13528","title":"FacTool: Factuality Detection in Generative AI -- A Tool Augmented Framework for Multi-Task and Multi-Domain Scenarios","created":"2023-07-25","cited_by_count":251},{"id":"2011.14878","title":"Explaining by Removing: A Unified Framework for Model Explanation","created":"2020-11-21","cited_by_count":218},{"id":"1506.01066","title":"Visualizing and Understanding Neural Models in NLP","created":"2015-06-02","cited_by_count":200},{"id":"2202.00622","title":"Datamodels: Predicting Predictions from Training Data","created":"2022-02-01","cited_by_count":189},{"id":"2310.00902","title":"DataInf: Efficiently Estimating Data Influence in LoRA-tuned LLMs and Diffusion Models","created":"2023-10-02","cited_by_count":123},{"id":"2311.14648","title":"Calibrated Language Models Must Hallucinate","created":"2023-11-24","cited_by_count":115},{"id":"2212.08037","title":"Attributed Question Answering: Evaluation and Modeling for Attributed Large Language Models","created":"2022-12-15","cited_by_count":112},{"id":"2403.00745","title":"AtP*: An efficient and scalable method for localizing LLM behaviour to components","created":"2024-03-01","cited_by_count":111},{"id":"2305.11859","title":"Complex Claim Verification with Evidence Retrieved in the Wild","created":"2023-05-19","cited_by_count":110},{"id":"2401.12926","title":"DsDm: Model-Aware Dataset Selection with Datamodels","created":"2024-01-23","cited_by_count":105},{"id":"2310.01427","title":"Attention Sorting Combats Recency Bias In Long Context Language Models","created":"2023-09-28","cited_by_count":90},{"id":"2403.03792","title":"Neural Exec: Learning (and Learning from) Execution Triggers for Prompt Injection Attacks","created":"2024-03-06","cited_by_count":85},{"id":"2302.11042","title":"In-context Example Selection with Influences","created":"2023-02-21","cited_by_count":61},{"id":"2212.10378","title":"Data Curation Alone Can Stabilize In-context Learning","created":"2022-12-20","cited_by_count":59},{"id":"2305.14908","title":"PURR: Efficiently Editing Language Model Hallucinations by Denoising Language Model Corruptions","created":"2023-05-24","cited_by_count":53},{"id":"2305.15853","title":"Sequential Integrated Gradients: a simple but effective method for explaining language models","created":"2023-05-25","cited_by_count":52},{"id":"2311.09533","title":"Effective Large Language Model Adaptation for Improved Grounding and Citation Generation","created":"2023-11-16","cited_by_count":45},{"id":"2406.13663","title":"Model Internals-based Answer Attribution for Trustworthy Retrieval-Augmented Generation","created":"2024-06-19","cited_by_count":25},{"id":"2404.11534","title":"Decomposing and Editing Predictions by Modeling Model Computation","created":"2024-04-17","cited_by_count":19},{"id":"1910.13016","title":"bLIMEy: Surrogate Prediction Explanations Beyond LIME","created":"2019-10-29","cited_by_count":17},{"id":"2311.12233","title":"Unifying Corroborative and Contributive Attributions in Large Language Models","created":"2023-11-20","cited_by_count":10},{"id":"2310.01188","title":"Quantifying the Plausibility of Context Reliance in Neural Machine Translation","created":"2023-10-02","cited_by_count":7},{"id":"2403.03956","title":"Backtracing: Retrieving the Cause of the Query","created":"2024-03-06","cited_by_count":2}],"next_cursor":null}