{"list":"other","total":136,"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":"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":"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":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"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":"2109.01652","title":"Finetuned Language Models Are Zero-Shot Learners","created":"2021-09-03","cited_by_count":3780},{"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":"2310.06825","title":"Mistral 7B","created":"2023-10-10","cited_by_count":3164},{"id":"2212.08073","title":"Constitutional AI: Harmlessness from AI Feedback","created":"2022-12-15","cited_by_count":3050},{"id":"2109.07958","title":"TruthfulQA: Measuring How Models Mimic Human Falsehoods","created":"2021-09-08","cited_by_count":2975},{"id":"1705.03551","title":"TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension","created":"2017-05-09","cited_by_count":2955},{"id":"1904.09751","title":"The Curious Case of Neural Text Degeneration","created":"2019-04-22","cited_by_count":2916},{"id":"2202.05262","title":"Locating and Editing Factual Associations in GPT","created":"2022-02-10","cited_by_count":2691},{"id":"2303.12712","title":"Sparks of Artificial General Intelligence: Early experiments with GPT-4","created":"2023-03-22","cited_by_count":2592},{"id":"2101.00027","title":"The Pile: An 800GB Dataset of Diverse Text for Language Modeling","created":"2020-12-31","cited_by_count":2411},{"id":"1610.05820","title":"Membership Inference Attacks against Machine Learning Models","created":"2016-10-18","cited_by_count":2281},{"id":"2012.07805","title":"Extracting Training Data from Large Language Models","created":"2020-12-14","cited_by_count":2189},{"id":"2202.03629","title":"Survey of Hallucination in Natural Language Generation","created":"2022-02-08","cited_by_count":2075},{"id":"2206.04615","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","created":"2022-06-09","cited_by_count":1998},{"id":"2211.05100","title":"BLOOM: A 176B-Parameter Open-Access Multilingual Language Model","created":"2022-11-09","cited_by_count":1984},{"id":"1909.01066","title":"Language Models as Knowledge Bases?","created":"2019-09-03","cited_by_count":1936},{"id":"1907.02893","title":"Invariant Risk Minimization","created":"2019-07-05","cited_by_count":1854},{"id":"2304.01373","title":"Pythia: A Suite for Analyzing Large Language Models Across Training and Scaling","created":"2023-04-03","cited_by_count":1786},{"id":"2112.09332","title":"WebGPT: Browser-assisted question-answering with human feedback","created":"2021-12-17","cited_by_count":1745},{"id":"1703.04730","title":"Understanding Black-box Predictions via Influence Functions","created":"2017-03-14","cited_by_count":1741},{"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":"2212.04089","title":"Editing Models with Task Arithmetic","created":"2022-12-08","cited_by_count":1120},{"id":"2301.08243","title":"Self-Supervised Learning from Images with a Joint-Embedding Predictive Architecture","created":"2023-01-19","cited_by_count":1039},{"id":"2210.07229","title":"Mass-Editing Memory in a Transformer","created":"2022-10-13","cited_by_count":1001},{"id":"1911.12543","title":"How Can We Know What Language Models Know?","created":"2019-11-28","cited_by_count":959},{"id":"1802.08232","title":"The Secret Sharer: Evaluating and Testing Unintended Memorization in Neural Networks","created":"2018-02-22","cited_by_count":864},{"id":"2301.05217","title":"Progress measures for grokking via mechanistic interpretability","created":"2023-01-12","cited_by_count":839},{"id":"1911.00172","title":"Generalization through Memorization: Nearest Neighbor Language Models","created":"2019-11-01","cited_by_count":800},{"id":"2301.12652","title":"REPLUG: Retrieval-Augmented Black-Box Language Models","created":"2023-01-30","cited_by_count":792},{"id":"2301.13688","title":"The Flan Collection: Designing Data and Methods for Effective Instruction Tuning","created":"2023-01-31","cited_by_count":739},{"id":"2107.06499","title":"Deduplicating Training Data Makes Language Models Better","created":"2021-07-14","cited_by_count":714},{"id":"2302.00083","title":"In-Context Retrieval-Augmented Language Models","created":"2023-01-31","cited_by_count":702},{"id":"2306.08302","title":"Unifying Large Language Models and Knowledge Graphs: A Roadmap","created":"2023-06-14","cited_by_count":668},{"id":"2212.10403","title":"Towards Reasoning in Large Language Models: A Survey","created":"2022-12-20","cited_by_count":596},{"id":"1805.04049","title":"Exploiting Unintended Feature Leakage in Collaborative Learning","created":"2018-05-10","cited_by_count":520},{"id":"2306.11698","title":"DecodingTrust: A Comprehensive Assessment of Trustworthiness in GPT Models","created":"2023-06-20","cited_by_count":518},{"id":"2308.08998","title":"Reinforced Self-Training (ReST) for Language Modeling","created":"2023-08-17","cited_by_count":500},{"id":"2204.05999","title":"InCoder: A Generative Model for Code Infilling and Synthesis","created":"2022-04-12","cited_by_count":498},{"id":"2008.03703","title":"What Neural Networks Memorize and Why: Discovering the Long Tail via Influence Estimation","created":"2020-08-09","cited_by_count":497},{"id":"2104.08758","title":"Documenting Large Webtext Corpora: A Case Study on the Colossal Clean Crawled Corpus","created":"2021-04-18","cited_by_count":492},{"id":"1906.05271","title":"Does Learning Require Memorization? A Short Tale about a Long Tail","created":"2019-06-12","cited_by_count":460},{"id":"2211.15533","title":"The Stack: 3 TB of permissively licensed source code","created":"2022-11-20","cited_by_count":359},{"id":"1904.01557","title":"Analysing Mathematical Reasoning Abilities of Neural Models","created":"2019-04-02","cited_by_count":335},{"id":"2304.05197","title":"Multi-step Jailbreaking Privacy Attacks on ChatGPT","created":"2023-04-11","cited_by_count":333},{"id":"2202.06539","title":"Deduplicating Training Data Mitigates Privacy Risks in Language Models","created":"2022-02-14","cited_by_count":314},{"id":"2302.10149","title":"Poisoning Web-Scale Training Datasets is Practical","created":"2023-02-20","cited_by_count":290},{"id":"2302.00539","title":"Analyzing Leakage of Personally Identifiable Information in Language Models","created":"2023-02-01","cited_by_count":285},{"id":"2303.14186","title":"TRAK: Attributing Model Behavior at Scale","created":"2023-03-24","cited_by_count":283},{"id":"1301.2300","title":"Direct and Indirect Effects","created":"2013-01-10","cited_by_count":280},{"id":"2305.18462","title":"Membership Inference Attacks against Language Models via Neighbourhood Comparison","created":"2023-05-29","cited_by_count":258},{"id":"2112.12870","title":"Measuring Attribution in Natural Language Generation Models","created":"2021-12-23","cited_by_count":256},{"id":"2111.09679","title":"Enhanced Membership Inference Attacks against Machine Learning Models","created":"2021-11-18","cited_by_count":248},{"id":"2302.08582","title":"Pretraining Language Models with Human Preferences","created":"2023-02-16","cited_by_count":247},{"id":"2306.09479","title":"Inverse Scaling: When Bigger Isn't Better","created":"2023-06-15","cited_by_count":207},{"id":"2206.04624","title":"Factuality Enhanced Language Models for Open-Ended Text Generation","created":"2022-06-09","cited_by_count":202},{"id":"2202.05520","title":"What Does it Mean for a Language Model to Preserve Privacy?","created":"2022-02-11","cited_by_count":195},{"id":"2106.10328","title":"Process for Adapting Language Models to Society (PALMS) with Values-Targeted Datasets","created":"2021-06-18","cited_by_count":181},{"id":"2309.13638","title":"Embers of Autoregression: Understanding Large Language Models Through the Problem They are Trained to Solve","created":"2023-09-24","cited_by_count":178},{"id":"2310.07298","title":"Beyond Memorization: Violating Privacy Via Inference with Large Language Models","created":"2023-10-11","cited_by_count":175},{"id":"2011.00416","title":"Deep Learning for Text Style Transfer: A Survey","created":"2020-11-01","cited_by_count":162},{"id":"2104.06683","title":"The Curious Case of Hallucinations in Neural Machine Translation","created":"2021-04-14","cited_by_count":161},{"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":"2204.06031","title":"A Review on Language Models as Knowledge Bases","created":"2022-04-12","cited_by_count":157},{"id":"2304.11082","title":"Fundamental Limitations of Alignment in Large Language Models","created":"2023-04-19","cited_by_count":155},{"id":"2303.03915","title":"The BigScience ROOTS Corpus: A 1.6TB Composite Multilingual Dataset","created":"2023-03-07","cited_by_count":148},{"id":"2302.08500","title":"Auditing large language models: a three-layered approach","created":"2023-02-16","cited_by_count":137},{"id":"2212.01681","title":"Language Models as Agent Models","created":"2022-12-03","cited_by_count":132},{"id":"1306.4447","title":"Hacking Smart Machines with Smarter Ones: How to Extract Meaningful Data from Machine Learning Classifiers","created":"2013-06-19","cited_by_count":130},{"id":"2307.01881","title":"ProPILE: Probing Privacy Leakage in Large Language Models","created":"2023-07-04","cited_by_count":129},{"id":"2005.03642","title":"On Exposure Bias, Hallucination and Domain Shift in Neural Machine Translation","created":"2020-05-07","cited_by_count":127},{"id":"2305.00118","title":"Speak, Memory: An Archaeology of Books Known to ChatGPT/GPT-4","created":"2023-04-28","cited_by_count":125},{"id":"1906.01081","title":"Handling Divergent Reference Texts when Evaluating Table-to-Text Generation","created":"2019-06-03","cited_by_count":119},{"id":"2207.00099","title":"Measuring Forgetting of Memorized Training Examples","created":"2022-06-30","cited_by_count":118},{"id":"2104.10706","title":"Dataset Inference: Ownership Resolution in Machine Learning","created":"2021-04-21","cited_by_count":116},{"id":"2303.15715","title":"Foundation Models and Fair Use","created":"2023-03-28","cited_by_count":116},{"id":"2005.10881","title":"Revisiting Membership Inference Under Realistic Assumptions","created":"2020-05-21","cited_by_count":112},{"id":"2109.03910","title":"A Recipe For Arbitrary Text Style Transfer with Large Language Models","created":"2021-09-08","cited_by_count":107},{"id":"2104.08455","title":"Neural Path Hunter: Reducing Hallucination in Dialogue Systems via Path Grounding","created":"2021-04-17","cited_by_count":106},{"id":"2305.06535","title":"KGA: A General Machine Unlearning Framework Based on Knowledge Gap Alignment","created":"2023-05-11","cited_by_count":99},{"id":"2302.10870","title":"On Provable Copyright Protection for Generative Models","created":"2023-02-21","cited_by_count":98},{"id":"1911.03681","title":"E-BERT: Efficient-Yet-Effective Entity Embeddings for BERT","created":"2019-11-09","cited_by_count":96},{"id":"2104.07762","title":"Does BERT Pretrained on Clinical Notes Reveal Sensitive Data?","created":"2021-04-15","cited_by_count":93},{"id":"2303.04245","title":"How Do Transformers Learn Topic Structure: Towards a Mechanistic Understanding","created":"2023-03-07","cited_by_count":86},{"id":"2308.12833","title":"Use of LLMs for Illicit Purposes: Threats, Prevention Measures, and Vulnerabilities","created":"2023-08-24","cited_by_count":82},{"id":"2105.02732","title":"What's in the Box? A Preliminary Analysis of Undesirable Content in the Common Crawl Corpus","created":"2021-05-06","cited_by_count":80},{"id":"2203.07618","title":"Do Language Models Plagiarize?","created":"2022-03-15","cited_by_count":73},{"id":"2102.11845","title":"Learning with User-Level Privacy","created":"2021-02-23","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":"2307.09542","title":"Can Neural Network Memorization Be Localized?","created":"2023-07-18","cited_by_count":69},{"id":"2108.12944","title":"Selective Differential Privacy for Language Modeling","created":"2021-08-30","cited_by_count":62},{"id":"2302.05206","title":"The Wisdom of Hindsight Makes Language Models Better Instruction Followers","created":"2023-02-10","cited_by_count":62}],"next_cursor":"100"}