{"list":"other","total":84,"rows":[{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2304.03442","title":"Generative Agents: Interactive Simulacra of Human Behavior","created":"2023-04-07","cited_by_count":3568},{"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":"1607.00133","title":"Deep Learning with Differential Privacy","created":"2016-07-01","cited_by_count":2728},{"id":"2303.16634","title":"G-Eval: NLG Evaluation using GPT-4 with Better Human Alignment","created":"2023-03-29","cited_by_count":2276},{"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":"2406.01574","title":"MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark","created":"2024-06-03","cited_by_count":1848},{"id":"1806.03822","title":"Know What You Don't Know: Unanswerable Questions for SQuAD","created":"2018-06-11","cited_by_count":1554},{"id":"2310.08419","title":"Jailbreaking Black Box Large Language Models in Twenty Queries","created":"2023-10-12","cited_by_count":1420},{"id":"2310.01405","title":"Representation Engineering: A Top-Down Approach to AI Transparency","created":"2023-10-02","cited_by_count":1336},{"id":"1607.06520","title":"Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings","created":"2016-07-21","cited_by_count":1312},{"id":"2009.11462","title":"RealToxicityPrompts: Evaluating Neural Toxic Degeneration in Language Models","created":"2020-09-24","cited_by_count":1255},{"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":"2408.06292","title":"The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery","created":"2024-08-12","cited_by_count":1071},{"id":"2310.13548","title":"Towards Understanding Sycophancy in Language Models","created":"2023-10-20","cited_by_count":1040},{"id":"2202.03286","title":"Red Teaming Language Models with Language Models","created":"2022-02-07","cited_by_count":1026},{"id":"2403.08295","title":"Gemma: Open Models Based on Gemini Research and Technology","created":"2024-03-13","cited_by_count":916},{"id":"2204.07705","title":"Super-NaturalInstructions: Generalization via Declarative Instructions on 1600+ NLP Tasks","created":"2022-04-16","cited_by_count":868},{"id":"2307.04657","title":"BeaverTails: Towards Improved Safety Alignment of LLM via a Human-Preference Dataset","created":"2023-07-10","cited_by_count":860},{"id":"2212.09251","title":"Discovering Language Model Behaviors with Model-Written Evaluations","created":"2022-12-19","cited_by_count":836},{"id":"2202.07646","title":"Quantifying Memorization Across Neural Language Models","created":"2022-02-15","cited_by_count":763},{"id":"2209.07858","title":"Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons Learned","created":"2022-08-23","cited_by_count":729},{"id":"2301.10226","title":"A Watermark for Large Language Models","created":"2023-01-24","cited_by_count":725},{"id":"2107.06499","title":"Deduplicating Training Data Makes Language Models Better","created":"2021-07-14","cited_by_count":714},{"id":"2010.00133","title":"CrowS-Pairs: A Challenge Dataset for Measuring Social Biases in Masked Language Models","created":"2020-09-30","cited_by_count":710},{"id":"2104.08773","title":"Cross-Task Generalization via Natural Language Crowdsourcing Instructions","created":"2021-04-18","cited_by_count":699},{"id":"1804.06876","title":"Gender Bias in Coreference Resolution: Evaluation and Debiasing Methods","created":"2018-04-18","cited_by_count":659},{"id":"2306.11698","title":"DecodingTrust: A Comprehensive Assessment of Trustworthiness in GPT Models","created":"2023-06-20","cited_by_count":518},{"id":"2301.13848","title":"Benchmarking Large Language Models for News Summarization","created":"2023-01-31","cited_by_count":445},{"id":"2303.04048","title":"Is ChatGPT a Good NLG Evaluator? A Preliminary Study","created":"2023-03-07","cited_by_count":422},{"id":"2306.04751","title":"How Far Can Camels Go? Exploring the State of Instruction Tuning on Open Resources","created":"2023-06-07","cited_by_count":408},{"id":"1807.09937","title":"HiDDeN: Hiding Data With Deep Networks","created":"2018-07-26","cited_by_count":397},{"id":"2004.06660","title":"Weight Poisoning Attacks on Pre-trained Models","created":"2020-04-14","cited_by_count":341},{"id":"2307.15593","title":"Robust Distortion-free Watermarks for Language Models","created":"2023-07-28","cited_by_count":320},{"id":"2202.06539","title":"Deduplicating Training Data Mitigates Privacy Risks in Language Models","created":"2022-02-14","cited_by_count":314},{"id":"2303.15435","title":"The Stable Signature: Rooting Watermarks in Latent Diffusion Models","created":"2023-03-27","cited_by_count":304},{"id":"2402.07827","title":"Aya Model: An Instruction Finetuned Open-Access Multilingual Language Model","created":"2024-02-12","cited_by_count":295},{"id":"2109.13916","title":"Unsolved Problems in ML Safety","created":"2021-09-28","cited_by_count":292},{"id":"1902.09666","title":"Predicting the Type and Target of Offensive Posts in Social Media","created":"2019-02-25","cited_by_count":271},{"id":"2401.01313","title":"A Comprehensive Survey of Hallucination Mitigation Techniques in Large Language Models","created":"2024-01-02","cited_by_count":269},{"id":"2310.19852","title":"AI Alignment: A Comprehensive Survey","created":"2023-10-30","cited_by_count":263},{"id":"2209.00626","title":"The Alignment Problem from a Deep Learning Perspective","created":"2022-08-30","cited_by_count":258},{"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":"2405.20947","title":"OR-Bench: An Over-Refusal Benchmark for Large Language Models","created":"2024-05-31","cited_by_count":244},{"id":"1810.08240","title":"Time-uniform, nonparametric, nonasymptotic confidence sequences","created":"2018-10-18","cited_by_count":229},{"id":"2012.15761","title":"Learning from the Worst: Dynamically Generated Datasets to Improve Online Hate Detection","created":"2020-12-31","cited_by_count":221},{"id":"2307.03987","title":"A Stitch in Time Saves Nine: Detecting and Mitigating Hallucinations of LLMs by Validating Low-Confidence Generation","created":"2023-07-08","cited_by_count":206},{"id":"2308.14921","title":"Gender bias and stereotypes in Large Language Models","created":"2023-08-28","cited_by_count":187},{"id":"2202.11176","title":"A New Generation of Perspective API: Efficient Multilingual Character-level Transformers","created":"2022-02-22","cited_by_count":185},{"id":"2004.07213","title":"Toward Trustworthy AI Development: Mechanisms for Supporting Verifiable Claims","created":"2020-04-15","cited_by_count":165},{"id":"2210.01948","title":"Game-theoretic statistics and safe anytime-valid inference","created":"2022-10-04","cited_by_count":155},{"id":"2304.11082","title":"Fundamental Limitations of Alignment in Large Language Models","created":"2023-04-19","cited_by_count":155},{"id":"2403.13793","title":"Evaluating Frontier Models for Dangerous Capabilities","created":"2024-03-20","cited_by_count":128},{"id":"2108.01624","title":"Large-Scale Differentially Private BERT","created":"2021-08-03","cited_by_count":118},{"id":"2306.09442","title":"Explore, Establish, Exploit: Red Teaming Language Models from Scratch","created":"2023-06-15","cited_by_count":114},{"id":"2307.16513","title":"Deception Abilities Emerged in Large Language Models","created":"2023-07-31","cited_by_count":101},{"id":"2302.10870","title":"On Provable Copyright Protection for Generative Models","created":"2023-02-21","cited_by_count":98},{"id":"2307.03718","title":"Frontier AI Regulation: Managing Emerging Risks to Public Safety","created":"2023-07-06","cited_by_count":98},{"id":"2112.02701","title":"Protecting Intellectual Property of Language Generation APIs with Lexical Watermark","created":"2021-12-05","cited_by_count":84},{"id":"2203.11070","title":"From Concept Drift to Model Degradation: An Overview on Performance-Aware Drift Detectors","created":"2022-03-21","cited_by_count":83},{"id":"2305.01904","title":"Robust Multi-bit Natural Language Watermarking through Invariant Features","created":"2023-05-03","cited_by_count":82},{"id":"2209.08773","title":"CATER: Intellectual Property Protection on Text Generation APIs via Conditional Watermarks","created":"2022-09-19","cited_by_count":76},{"id":"2402.01383","title":"LLM-based NLG Evaluation: Current Status and Challenges","created":"2024-02-02","cited_by_count":73},{"id":"2004.14454","title":"SOLID: A Large-Scale Semi-Supervised Dataset for Offensive Language Identification","created":"2020-04-29","cited_by_count":53},{"id":"2102.05569","title":"There are natural scores: Full comment on Shafer, \"Testing by betting: A strategy for statistical and scientific communication\"","created":"2021-02-10","cited_by_count":53},{"id":"2402.10962","title":"Measuring and Controlling Instruction (In)Stability in Language Model Dialogs","created":"2024-02-13","cited_by_count":53},{"id":"1706.10268","title":"SafetyNets: Verifiable Execution of Deep Neural Networks on an Untrusted Cloud","created":"2017-06-30","cited_by_count":50},{"id":"1806.03281","title":"Blind Justice: Fairness with Encrypted Sensitive Attributes","created":"2018-06-08","cited_by_count":41},{"id":"1308.3946","title":"Optimal Algorithms for Testing Closeness of Discrete Distributions","created":"2013-08-19","cited_by_count":37},{"id":"2112.09162","title":"Nonparametric Two-Sample Testing by Betting","created":"2021-12-16","cited_by_count":37},{"id":"2305.00143","title":"Sequential Predictive Two-Sample and Independence Testing","created":"2023-04-29","cited_by_count":21},{"id":"2201.09186","title":"pvCNN: Privacy-Preserving and Verifiable Convolutional Neural Network Testing","created":"2022-01-23","cited_by_count":20},{"id":"2009.01534","title":"Fairness in the Eyes of the Data: Certifying Machine-Learning Models","created":"2020-09-03","cited_by_count":16},{"id":"2310.00374","title":"Coordinated pausing: An evaluation-based coordination scheme for frontier AI developers","created":"2023-09-30","cited_by_count":13},{"id":"1808.03277","title":"VerIDeep: Verifying Integrity of Deep Neural Networks through Sensitive-Sample Fingerprinting","created":"2018-08-09","cited_by_count":8},{"id":"2212.01810","title":"Constructing Highly Inductive Contexts for Dialogue Safety through Controllable Reverse Generation","created":"2022-12-04","cited_by_count":8},{"id":"2311.13154","title":"Testing Closeness of Multivariate Distributions via Ramsey Theory","created":"2023-11-22","cited_by_count":8},{"id":"2310.19384","title":"Deep anytime-valid hypothesis testing","created":"2023-10-30","cited_by_count":7},{"id":"2009.03136","title":"Black Box to White Box: Discover Model Characteristics Based on Strategic Probing","created":"2020-09-07","cited_by_count":5},{"id":"2402.15780","title":"Holding Secrets Accountable: Auditing Privacy-Preserving Machine Learning","created":"2024-02-24","cited_by_count":5},{"id":"2107.00495","title":"VeriDL: Integrity Verification of Outsourced Deep Learning Services (Extended Version)","created":"2021-07-01","cited_by_count":4},{"id":"2004.04644","title":"On the Ethics of Building AI in a Responsible Manner","created":"2020-03-30","cited_by_count":3},{"id":"2109.07461","title":"MPC-Friendly Commitments for Publicly Verifiable Covert Security","created":"2021-09-15","cited_by_count":1}],"next_cursor":null}