{"list":"other","total":51,"rows":[{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"2005.11401","title":"Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks","created":"2020-05-22","cited_by_count":9297},{"id":"2306.05685","title":"Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena","created":"2023-06-09","cited_by_count":8626},{"id":"2305.18290","title":"Direct Preference Optimization: Your Language Model is Secretly a Reward Model","created":"2023-05-29","cited_by_count":8065},{"id":"2009.03300","title":"Measuring Massive Multitask Language Understanding","created":"2020-09-07","cited_by_count":7963},{"id":"2108.07258","title":"On the Opportunities and Risks of Foundation Models","created":"2021-08-16","cited_by_count":4033},{"id":"2202.05262","title":"Locating and Editing Factual Associations in GPT","created":"2022-02-10","cited_by_count":2691},{"id":"2012.07805","title":"Extracting Training Data from Large Language Models","created":"2020-12-14","cited_by_count":2189},{"id":"2310.11511","title":"Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection","created":"2023-10-17","cited_by_count":1839},{"id":"2201.08239","title":"LaMDA: Language Models for Dialog Applications","created":"2022-01-20","cited_by_count":1220},{"id":"2212.04089","title":"Editing Models with Task Arithmetic","created":"2022-12-08","cited_by_count":1120},{"id":"1802.08232","title":"The Secret Sharer: Evaluating and Testing Unintended Memorization in Neural Networks","created":"2018-02-22","cited_by_count":864},{"id":"2301.12652","title":"REPLUG: Retrieval-Augmented Black-Box Language Models","created":"2023-01-30","cited_by_count":792},{"id":"2202.07646","title":"Quantifying Memorization Across Neural Language Models","created":"2022-02-15","cited_by_count":763},{"id":"1911.04933","title":"Eternal Sunshine of the Spotless Net: Selective Forgetting in Deep Networks","created":"2019-11-12","cited_by_count":618},{"id":"1911.03030","title":"Certified Data Removal from Machine Learning Models","created":"2019-11-08","cited_by_count":535},{"id":"2401.06121","title":"TOFU: A Task of Fictitious Unlearning for LLMs","created":"2024-01-11","cited_by_count":533},{"id":"2403.03218","title":"The WMDP Benchmark: Measuring and Reducing Malicious Use With Unlearning","created":"2024-03-05","cited_by_count":509},{"id":"2404.05868","title":"Negative Preference Optimization: From Catastrophic Collapse to Effective Unlearning","created":"2024-04-08","cited_by_count":504},{"id":"2406.05946","title":"Safety Alignment Should Be Made More Than Just a Few Tokens Deep","created":"2024-06-10","cited_by_count":472},{"id":"2311.17035","title":"Scalable Extraction of Training Data from (Production) Language Models","created":"2023-11-28","cited_by_count":434},{"id":"2310.16789","title":"Detecting Pretraining Data from Large Language Models","created":"2023-10-25","cited_by_count":387},{"id":"2310.02238","title":"Who's Harry Potter? Approximate Unlearning in LLMs","created":"2023-10-03","cited_by_count":381},{"id":"1611.09830","title":"NewsQA: A Machine Comprehension Dataset","created":"2016-11-29","cited_by_count":331},{"id":"2305.14739","title":"Trusting Your Evidence: Hallucinate Less with Context-aware Decoding","created":"2023-05-24","cited_by_count":327},{"id":"2109.13398","title":"Unrolling SGD: Understanding Factors Influencing Machine Unlearning","created":"2021-09-27","cited_by_count":279},{"id":"2402.05162","title":"Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications","created":"2024-02-07","cited_by_count":231},{"id":"2310.07579","title":"In-Context Unlearning: Language Models as Few Shot Unlearners","created":"2023-10-11","cited_by_count":224},{"id":"2310.01352","title":"RA-DIT: Retrieval-Augmented Dual Instruction Tuning","created":"2023-10-02","cited_by_count":195},{"id":"2105.08209","title":"BookSum: A Collection of Datasets for Long-form Narrative Summarization","created":"2021-05-18","cited_by_count":184},{"id":"2309.17410","title":"Can Sensitive Information Be Deleted From LLMs? Objectives for Defending Against Extraction Attacks","created":"2023-09-29","cited_by_count":158},{"id":"2112.12938","title":"Counterfactual Memorization in Neural Language Models","created":"2021-12-24","cited_by_count":156},{"id":"2203.12817","title":"Continual Learning and Private Unlearning","created":"2022-03-24","cited_by_count":130},{"id":"2310.20707","title":"What's In My Big Data?","created":"2023-10-31","cited_by_count":129},{"id":"2211.12561","title":"Retrieval-Augmented Multimodal Language Modeling","created":"2022-11-22","cited_by_count":125},{"id":"2305.00118","title":"Speak, Memory: An Archaeology of Books Known to ChatGPT/GPT-4","created":"2023-04-28","cited_by_count":125},{"id":"2303.15715","title":"Foundation Models and Fair Use","created":"2023-03-28","cited_by_count":116},{"id":"2310.13771","title":"Copyright Violations and Large Language Models","created":"2023-10-20","cited_by_count":108},{"id":"2210.17546","title":"Preventing Verbatim Memorization in Language Models Gives a False Sense of Privacy","created":"2022-10-31","cited_by_count":100},{"id":"2310.20138","title":"DEPN: Detecting and Editing Privacy Neurons in Pretrained Language Models","created":"2023-10-31","cited_by_count":79},{"id":"2310.16787","title":"The Data Provenance Initiative: A Large Scale Audit of Dataset Licensing & Attribution in AI","created":"2023-10-25","cited_by_count":73},{"id":"2308.04430","title":"SILO Language Models: Isolating Legal Risk In a Nonparametric Datastore","created":"2023-08-08","cited_by_count":71},{"id":"2310.12941","title":"The Foundation Model Transparency Index","created":"2023-10-19","cited_by_count":66},{"id":"2406.10209","title":"Be like a Goldfish, Don't Memorize! Mitigating Memorization in Generative LLMs","created":"2024-06-14","cited_by_count":50},{"id":"2309.08133","title":"Talkin' 'Bout AI Generation: Copyright and the Generative-AI Supply Chain","created":"2023-09-15","cited_by_count":46},{"id":"2402.10892","title":"Proving membership in LLM pretraining data via data watermarks","created":"2024-02-16","cited_by_count":40},{"id":"2406.12975","title":"SHIELD: Evaluation and Defense Strategies for Copyright Compliance in LLM Text Generation","created":"2024-06-18","cited_by_count":34},{"id":"2303.03919","title":"Data Portraits: Recording Foundation Model Training Data","created":"2023-03-06","cited_by_count":30},{"id":"2308.12247","title":"How to Protect Copyright Data in Optimization of Large Language Models?","created":"2023-08-23","cited_by_count":26},{"id":"2406.14526","title":"Fantastic Copyrighted Beasts and How (Not) to Generate Them","created":"2024-06-20","cited_by_count":24},{"id":"2405.16567","title":"Automatic Jailbreaking of the Text-to-Image Generative AI Systems","created":"2024-05-26","cited_by_count":23}],"next_cursor":null}