{"list":"other","total":60,"rows":[{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"2305.18290","title":"Direct Preference Optimization: Your Language Model is Secretly a Reward Model","created":"2023-05-29","cited_by_count":8065},{"id":"1706.03741","title":"Deep reinforcement learning from human preferences","created":"2017-06-12","cited_by_count":3912},{"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":"2307.15043","title":"Universal and Transferable Adversarial Attacks on Aligned Language Models","created":"2023-07-27","cited_by_count":3104},{"id":"1909.08593","title":"Fine-Tuning Language Models from Human Preferences","created":"2019-09-18","cited_by_count":2150},{"id":"2307.02483","title":"Jailbroken: How Does LLM Safety Training Fail?","created":"2023-07-05","cited_by_count":1651},{"id":"1606.06565","title":"Concrete Problems in AI Safety","created":"2016-06-21","cited_by_count":1642},{"id":"2310.08419","title":"Jailbreaking Black Box Large Language Models in Twenty Queries","created":"2023-10-12","cited_by_count":1420},{"id":"1803.09010","title":"Datasheets for Datasets","created":"2018-03-23","cited_by_count":1386},{"id":"1810.03993","title":"Model Cards for Model Reporting","created":"2018-10-05","cited_by_count":1080},{"id":"2112.00861","title":"A General Language Assistant as a Laboratory for Alignment","created":"2021-12-01","cited_by_count":1055},{"id":"2011.03395","title":"Underspecification Presents Challenges for Credibility in Modern Machine Learning","created":"2020-11-06","cited_by_count":496},{"id":"2001.09768","title":"Artificial Intelligence, Values and Alignment","created":"2020-01-13","cited_by_count":448},{"id":"1811.07871","title":"Scalable agent alignment via reward modeling: a research direction","created":"2018-11-19","cited_by_count":447},{"id":"2206.06520","title":"Memory-Based Model Editing at Scale","created":"2022-06-13","cited_by_count":447},{"id":"2012.00955","title":"How Can We Know When Language Models Know? On the Calibration of Language Models for Question Answering","created":"2020-12-02","cited_by_count":445},{"id":"2306.16388","title":"Towards Measuring the Representation of Subjective Global Opinions in Language Models","created":"2023-06-28","cited_by_count":437},{"id":"2308.05374","title":"Trustworthy LLMs: a Survey and Guideline for Evaluating Large Language Models' Alignment","created":"2023-08-10","cited_by_count":401},{"id":"1805.00899","title":"AI safety via debate","created":"2018-05-02","cited_by_count":400},{"id":"2412.14093","title":"Alignment faking in large language models","created":"2024-12-18","cited_by_count":360},{"id":"2305.03047","title":"Principle-Driven Self-Alignment of Language Models from Scratch with Minimal Human Supervision","created":"2023-05-04","cited_by_count":318},{"id":"1711.02827","title":"Inverse Reward Design","created":"2017-11-08","cited_by_count":249},{"id":"2309.15025","title":"Large Language Model Alignment: A Survey","created":"2023-09-26","cited_by_count":243},{"id":"2203.10020","title":"Challenges and Strategies in Cross-Cultural NLP","created":"2022-03-18","cited_by_count":218},{"id":"2209.13085","title":"Defining and Characterizing Reward Hacking","created":"2022-09-27","cited_by_count":203},{"id":"2109.13238","title":"Visually Grounded Reasoning across Languages and Cultures","created":"2021-09-28","cited_by_count":189},{"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":"2010.07487","title":"Formalizing Trust in Artificial Intelligence: Prerequisites, Causes and Goals of Human Trust in AI","created":"2020-10-15","cited_by_count":167},{"id":"2011.07586","title":"Uncertainty as a Form of Transparency: Measuring, Communicating, and Using Uncertainty","created":"2020-11-15","cited_by_count":129},{"id":"2310.03708","title":"Beyond One-Preference-Fits-All Alignment: Multi-Objective Direct Preference Optimization","created":"2023-10-05","cited_by_count":124},{"id":"2412.05563","title":"A Survey on Uncertainty Quantification of Large Language Models: Taxonomy, Open Research Challenges, and Future Directions","created":"2024-12-07","cited_by_count":121},{"id":"2406.02543","title":"To Believe or Not to Believe Your LLM","created":"2024-06-04","cited_by_count":120},{"id":"1912.01683","title":"Optimal Policies Tend to Seek Power","created":"2019-12-03","cited_by_count":119},{"id":"2404.16244","title":"The Ethics of Advanced AI Assistants","created":"2024-04-24","cited_by_count":107},{"id":"2407.10920","title":"Benchmarking Vision Language Models for Cultural Understanding","created":"2024-07-15","cited_by_count":101},{"id":"2204.03021","title":"The Moral Integrity Corpus: A Benchmark for Ethical Dialogue Systems","created":"2022-04-06","cited_by_count":93},{"id":"2310.10076","title":"Verbosity Bias in Preference Labeling by Large Language Models","created":"2023-10-16","cited_by_count":91},{"id":"2102.03896","title":"Consequences of Misaligned AI","created":"2021-02-07","cited_by_count":80},{"id":"2406.18682","title":"The Multilingual Alignment Prism: Aligning Global and Local Preferences to Reduce Harm","created":"2024-06-26","cited_by_count":70},{"id":"2310.07251","title":"Ethical Reasoning over Moral Alignment: A Case and Framework for In-Context Ethical Policies in LLMs","created":"2023-10-11","cited_by_count":64},{"id":"2310.11523","title":"Group Preference Optimization: Few-Shot Alignment of Large Language Models","created":"2023-10-17","cited_by_count":63},{"id":"1804.04268","title":"Incomplete Contracting and AI Alignment","created":"2018-04-12","cited_by_count":62},{"id":"1906.00250","title":"Metric Learning for Individual Fairness","created":"2019-06-01","cited_by_count":52},{"id":"2411.02306","title":"On Targeted Manipulation and Deception when Optimizing LLMs for User Feedback","created":"2024-11-04","cited_by_count":47},{"id":"1902.09725","title":"Conservative Agency via Attainable Utility Preservation","created":"2019-02-26","cited_by_count":35},{"id":"2404.06664","title":"CulturalTeaming: AI-Assisted Interactive Red-Teaming for Challenging LLMs' (Lack of) Multicultural Knowledge","created":"2024-04-10","cited_by_count":28},{"id":"2309.13356","title":"Probing the Moral Development of Large Language Models through Defining Issues Test","created":"2023-09-23","cited_by_count":25},{"id":"2406.19354","title":"Fundamental Problems With Model Editing: How Should Rational Belief Revision Work in LLMs?","created":"2024-06-27","cited_by_count":24},{"id":"2305.17319","title":"Moral Machine or Tyranny of the Majority?","created":"2023-05-27","cited_by_count":22},{"id":"2407.02551","title":"Breach By A Thousand Leaks: Unsafe Information Leakage in `Safe' AI Responses","created":"2024-07-02","cited_by_count":18},{"id":"2311.13628","title":"Prompt Risk Control: A Rigorous Framework for Responsible Deployment of Large Language Models","created":"2023-11-22","cited_by_count":17},{"id":"2208.06931","title":"A Theory for Knowledge Transfer in Continual Learning","created":"2022-08-14","cited_by_count":16},{"id":"1811.01267","title":"Legible Normativity for AI Alignment: The Value of Silly Rules","created":"2018-11-03","cited_by_count":15},{"id":"2402.11178","title":"RENOVI: A Benchmark Towards Remediating Norm Violations in Socio-Cultural Conversations","created":"2024-02-17","cited_by_count":14},{"id":"2406.15599","title":"Pareto-Optimal Learning from Preferences with Hidden Context","created":"2024-06-21","cited_by_count":8},{"id":"2405.17700","title":"Learning Social Welfare Functions","created":"2024-05-27","cited_by_count":7},{"id":"2001.09318","title":"Silly rules improve the capacity of agents to learn stable enforcement and compliance behaviors","created":"2020-01-25","cited_by_count":3}],"next_cursor":null}