{"list":"other","total":52,"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":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"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":"2307.15043","title":"Universal and Transferable Adversarial Attacks on Aligned Language Models","created":"2023-07-27","cited_by_count":3104},{"id":"1802.03426","title":"UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction","created":"2018-02-09","cited_by_count":2898},{"id":"2101.00027","title":"The Pile: An 800GB Dataset of Diverse Text for Language Modeling","created":"2020-12-31","cited_by_count":2411},{"id":"1807.03888","title":"A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attacks","created":"2018-07-10","cited_by_count":1485},{"id":"2201.08239","title":"LaMDA: Language Models for Dialog Applications","created":"2022-01-20","cited_by_count":1220},{"id":"2312.06674","title":"Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations","created":"2023-12-07","cited_by_count":1207},{"id":"2310.03693","title":"Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!","created":"2023-10-05","cited_by_count":1154},{"id":"2301.11305","title":"DetectGPT: Zero-Shot Machine-Generated Text Detection using Probability Curvature","created":"2023-01-26","cited_by_count":726},{"id":"2301.10226","title":"A Watermark for Large Language Models","created":"2023-01-24","cited_by_count":725},{"id":"2308.06463","title":"GPT-4 Is Too Smart To Be Safe: Stealthy Chat with LLMs via Cipher","created":"2023-08-12","cited_by_count":423},{"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":"2308.03296","title":"Studying Large Language Model Generalization with Influence Functions","created":"2023-08-07","cited_by_count":326},{"id":"2310.10683","title":"Large Language Model Unlearning","created":"2023-10-14","cited_by_count":302},{"id":"2310.07579","title":"In-Context Unlearning: Language Models as Few Shot Unlearners","created":"2023-10-11","cited_by_count":224},{"id":"2310.20150","title":"Unlearn What You Want to Forget: Efficient Unlearning for LLMs","created":"2023-10-31","cited_by_count":215},{"id":"2407.00079","title":"Mooncake: A KVCache-centric Disaggregated Architecture for LLM Serving","created":"2024-06-24","cited_by_count":196},{"id":"2305.15060","title":"Who Wrote this Code? Watermarking for Code Generation","created":"2023-05-24","cited_by_count":141},{"id":"2206.07550","title":"Evaluating and Inducing Personality in Pre-trained Language Models","created":"2022-05-20","cited_by_count":123},{"id":"2306.02272","title":"OWQ: Outlier-Aware Weight Quantization for Efficient Fine-Tuning and Inference of Large Language Models","created":"2023-06-04","cited_by_count":114},{"id":"2306.09442","title":"Explore, Establish, Exploit: Red Teaming Language Models from Scratch","created":"2023-06-15","cited_by_count":114},{"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":"2104.08027","title":"Fast, Effective, and Self-Supervised: Transforming Masked Language Models into Universal Lexical and Sentence Encoders","created":"2021-04-16","cited_by_count":88},{"id":"2310.12362","title":"REMARK-LLM: A Robust and Efficient Watermarking Framework for Generative Large Language Models","created":"2023-10-18","cited_by_count":78},{"id":"2402.09910","title":"DE-COP: Detecting Copyrighted Content in Language Models Training Data","created":"2024-02-15","cited_by_count":74},{"id":"2309.10818","title":"SlimPajama-DC: Understanding Data Combinations for LLM Training","created":"2023-09-19","cited_by_count":72},{"id":"2308.04430","title":"SILO Language Models: Isolating Legal Risk In a Nonparametric Datastore","created":"2023-08-08","cited_by_count":71},{"id":"2311.03731","title":"A Survey of Large Language Models Attribution","created":"2023-11-07","cited_by_count":71},{"id":"2406.16201","title":"Blind Baselines Beat Membership Inference Attacks for Foundation Models","created":"2024-06-23","cited_by_count":69},{"id":"2405.19327","title":"MAP-Neo: Highly Capable and Transparent Bilingual Large Language Model Series","created":"2024-05-29","cited_by_count":67},{"id":"2402.08416","title":"Pandora: Jailbreak GPTs by Retrieval Augmented Generation Poisoning","created":"2024-02-13","cited_by_count":64},{"id":"2407.15847","title":"LLMmap: Fingerprinting For Large Language Models","created":"2024-07-22","cited_by_count":58},{"id":"2404.16369","title":"Don't Say No: Jailbreaking LLM by Suppressing Refusal","created":"2024-04-25","cited_by_count":56},{"id":"2406.18664","title":"Evaluating Copyright Takedown Methods for Language Models","created":"2024-06-26","cited_by_count":43},{"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":"2308.08090","title":"Separate the Wheat from the Chaff: Model Deficiency Unlearning via Parameter-Efficient Module Operation","created":"2023-08-16","cited_by_count":33},{"id":"2310.20307","title":"Causal Interpretation of Self-Attention in Pre-Trained Transformers","created":"2023-10-31","cited_by_count":30},{"id":"2305.14822","title":"Can Copyright be Reduced to Privacy?","created":"2023-05-24","cited_by_count":24},{"id":"2309.10544","title":"Model Leeching: An Extraction Attack Targeting LLMs","created":"2023-09-19","cited_by_count":22},{"id":"2404.13964","title":"An Economic Solution to Copyright Challenges of Generative AI","created":"2024-04-22","cited_by_count":18},{"id":"2407.17417","title":"Can Watermarking Large Language Models Prevent Copyrighted Text Generation and Hide Training Data?","created":"2024-07-24","cited_by_count":18},{"id":"2206.01230","title":"Formalizing Human Ingenuity: A Quantitative Framework for Copyright Law's Substantial Similarity","created":"2022-06-02","cited_by_count":15},{"id":"2309.09401","title":"ChatGPT Hallucinates when Attributing Answers","created":"2023-09-17","cited_by_count":14},{"id":"2210.11034","title":"Enhancing Out-of-Distribution Detection in Natural Language Understanding via Implicit Layer Ensemble","created":"2022-10-20","cited_by_count":9},{"id":"2309.16082","title":"Forgetting Private Textual Sequences in Language Models via Leave-One-Out Ensemble","created":"2023-09-28","cited_by_count":6},{"id":"2111.02188","title":"BERT-DRE: BERT with Deep Recursive Encoder for Natural Language Sentence Matching","created":"2021-11-03","cited_by_count":3}],"next_cursor":null}