{"list":"other","total":54,"rows":[{"id":"2306.05685","title":"Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena","created":"2023-06-09","cited_by_count":8626},{"id":"1506.02142","title":"Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning","created":"2015-06-06","cited_by_count":4448},{"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":"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":"1902.10811","title":"Do ImageNet Classifiers Generalize to ImageNet?","created":"2019-02-13","cited_by_count":1515},{"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":"2310.08419","title":"Jailbreaking Black Box Large Language Models in Twenty Queries","created":"2023-10-12","cited_by_count":1420},{"id":"2009.11462","title":"RealToxicityPrompts: Evaluating Neural Toxic Degeneration in Language Models","created":"2020-09-24","cited_by_count":1255},{"id":"2307.03109","title":"A Survey on Evaluation of Large Language Models","created":"2023-07-06","cited_by_count":1242},{"id":"2202.07646","title":"Quantifying Memorization Across Neural Language Models","created":"2022-02-15","cited_by_count":763},{"id":"2307.15217","title":"Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback","created":"2023-07-27","cited_by_count":759},{"id":"2306.11698","title":"DecodingTrust: A Comprehensive Assessment of Trustworthiness in GPT Models","created":"2023-06-20","cited_by_count":518},{"id":"2403.03218","title":"The WMDP Benchmark: Measuring and Reducing Malicious Use With Unlearning","created":"2024-03-05","cited_by_count":509},{"id":"2011.03395","title":"Underspecification Presents Challenges for Credibility in Modern Machine Learning","created":"2020-11-06","cited_by_count":496},{"id":"2104.14337","title":"Dynabench: Rethinking Benchmarking in NLP","created":"2021-04-07","cited_by_count":459},{"id":"2402.16822","title":"Rainbow Teaming: Open-Ended Generation of Diverse Adversarial Prompts","created":"2024-02-26","cited_by_count":205},{"id":"2402.07841","title":"Do Membership Inference Attacks Work on Large Language Models?","created":"2024-02-12","cited_by_count":195},{"id":"2310.07298","title":"Beyond Memorization: Violating Privacy Via Inference with Large Language Models","created":"2023-10-11","cited_by_count":175},{"id":"1909.03004","title":"Show Your Work: Improved Reporting of Experimental Results","created":"2019-09-06","cited_by_count":169},{"id":"2403.06634","title":"Stealing Part of a Production Language Model","created":"2024-03-11","cited_by_count":159},{"id":"2310.11986","title":"Sociotechnical Safety Evaluation of Generative AI Systems","created":"2023-10-18","cited_by_count":157},{"id":"2408.15221","title":"LLM Defenses Are Not Robust to Multi-Turn Human Jailbreaks Yet","created":"2024-08-27","cited_by_count":151},{"id":"2311.18760","title":"TaskBench: Benchmarking Large Language Models for Task Automation","created":"2023-11-30","cited_by_count":144},{"id":"2209.07572","title":"Power to the People? Opportunities and Challenges for Participatory AI","created":"2022-09-15","cited_by_count":138},{"id":"2210.05791","title":"Sociotechnical Harms of Algorithmic Systems: Scoping a Taxonomy for Harm Reduction","created":"2022-10-11","cited_by_count":138},{"id":"2006.03463","title":"Sponge Examples: Energy-Latency Attacks on Neural Networks","created":"2020-06-05","cited_by_count":111},{"id":"2007.02423","title":"Participation is not a Design Fix for Machine Learning","created":"2020-07-05","cited_by_count":111},{"id":"2312.16337","title":"Task Contamination: Language Models May Not Be Few-Shot Anymore","created":"2023-12-26","cited_by_count":99},{"id":"2503.04761","title":"Which Economic Tasks are Performed with AI? Evidence from Millions of Claude Conversations","created":"2025-02-11","cited_by_count":96},{"id":"2206.09511","title":"The Fallacy of AI Functionality","created":"2022-06-20","cited_by_count":88},{"id":"2204.09308","title":"A Deeper Look into Aleatoric and Epistemic Uncertainty Disentanglement","created":"2022-04-20","cited_by_count":87},{"id":"1901.09749","title":"Fairwashing: the risk of rationalization","created":"2019-01-28","cited_by_count":81},{"id":"2308.01222","title":"Calibration in Deep Learning: A Survey of the State-of-the-Art","created":"2023-08-02","cited_by_count":75},{"id":"2310.00741","title":"FELM: Benchmarking Factuality Evaluation of Large Language Models","created":"2023-10-01","cited_by_count":66},{"id":"2207.07048","title":"Leakage and the Reproducibility Crisis in ML-based Science","created":"2022-07-14","cited_by_count":65},{"id":"2109.06598","title":"Just What do You Think You're Doing, Dave?' A Checklist for Responsible Data Use in NLP","created":"2021-09-14","cited_by_count":47},{"id":"2310.13595","title":"The History and Risks of Reinforcement Learning and Human Feedback","created":"2023-10-20","cited_by_count":42},{"id":"2002.08512","title":"The Problem with Metrics is a Fundamental Problem for AI","created":"2020-02-20","cited_by_count":37},{"id":"2209.15259","title":"On the Impossible Safety of Large AI Models","created":"2022-09-30","cited_by_count":28},{"id":"2106.11022","title":"Hard Choices in Artificial Intelligence","created":"2021-06-10","cited_by_count":26},{"id":"2011.13416","title":"Overcoming Failures of Imagination in AI Infused System Development and Deployment","created":"2020-11-26","cited_by_count":22},{"id":"2401.10899","title":"Concrete Problems in AI Safety, Revisited","created":"2023-12-18","cited_by_count":22},{"id":"2205.08363","title":"REAL ML: Recognizing, Exploring, and Articulating Limitations of Machine Learning Research","created":"2022-05-05","cited_by_count":20},{"id":"2407.01294","title":"A Collaborative, Human-Centred Taxonomy of AI, Algorithmic, and Automation Harms","created":"2024-07-01","cited_by_count":19},{"id":"2403.13213","title":"From Representational Harms to Quality-of-Service Harms: A Case Study on Llama 2 Safety Safeguards","created":"2024-03-20","cited_by_count":17},{"id":"2406.00020","title":"Harmful Speech Detection by Language Models Exhibits Gender-Queer Dialect Bias","created":"2024-05-23","cited_by_count":16},{"id":"2412.01934","title":"A Shared Standard for Valid Measurement of Generative AI Systems' Capabilities, Risks, and Impacts","created":"2024-12-02","cited_by_count":13},{"id":"2502.05324","title":"Atlas of AI Risks: Enhancing Public Understanding of AI Risks","created":"2025-02-07","cited_by_count":7},{"id":"2505.00174","title":"Real-World Gaps in AI Governance Research","created":"2025-04-30","cited_by_count":5},{"id":"2504.03359","title":"A metrological framework for uncertainty evaluation in machine learning classification models","created":"2025-04-04","cited_by_count":4},{"id":"2404.11224","title":"Analytical results for uncertainty propagation through trained machine learning regression models","created":"2024-04-17","cited_by_count":3},{"id":"2406.10430","title":"Challenging the Machine: Contestability in Government AI Systems","created":"2024-06-14","cited_by_count":3}],"next_cursor":null}