{"list":"other","total":61,"rows":[{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"2402.03300","title":"DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models","created":"2024-02-05","cited_by_count":9379},{"id":"1606.06565","title":"Concrete Problems in AI Safety","created":"2016-06-21","cited_by_count":1642},{"id":"2306.16388","title":"Towards Measuring the Representation of Subjective Global Opinions in Language Models","created":"2023-06-28","cited_by_count":437},{"id":"1805.00899","title":"AI safety via debate","created":"2018-05-02","cited_by_count":400},{"id":"2402.06782","title":"Debating with More Persuasive LLMs Leads to More Truthful Answers","created":"2024-02-09","cited_by_count":266},{"id":"2307.14984","title":"S$^3$: Social-network Simulation System with Large Language Model-Empowered Agents","created":"2023-07-27","cited_by_count":233},{"id":"2312.06942","title":"AI Control: Improving Safety Despite Intentional Subversion","created":"2023-12-12","cited_by_count":229},{"id":"2308.14752","title":"AI Deception: A Survey of Examples, Risks, and Potential Solutions","created":"2023-08-28","cited_by_count":188},{"id":"2402.05070","title":"A Roadmap to Pluralistic Alignment","created":"2024-02-07","cited_by_count":184},{"id":"2305.15324","title":"Model evaluation for extreme risks","created":"2023-05-24","cited_by_count":177},{"id":"2302.00560","title":"Co-Writing with Opinionated Language Models Affects Users' Views","created":"2023-02-01","cited_by_count":148},{"id":"2403.13793","title":"Evaluating Frontier Models for Dangerous Capabilities","created":"2024-03-20","cited_by_count":128},{"id":"2306.12672","title":"From Word Models to World Models: Translating from Natural Language to the Probabilistic Language of Thought","created":"2023-06-22","cited_by_count":119},{"id":"1602.01103","title":"Winning Arguments: Interaction Dynamics and Persuasion Strategies in Good-faith Online Discussions","created":"2016-02-02","cited_by_count":110},{"id":"2403.14380","title":"On the Conversational Persuasiveness of Large Language Models: A Randomized Controlled Trial","created":"2024-03-21","cited_by_count":109},{"id":"2407.02996","title":"Are Large Language Models Consistent over Value-laden Questions?","created":"2024-07-03","cited_by_count":58},{"id":"2312.15523","title":"The Persuasive Power of Large Language Models","created":"2023-12-24","cited_by_count":47},{"id":"2303.09387","title":"Characterizing Manipulation from AI Systems","created":"2023-03-16","cited_by_count":43},{"id":"2312.01350","title":"Honesty Is the Best Policy: Defining and Mitigating AI Deception","created":"2023-12-03","cited_by_count":40},{"id":"2406.17232","title":"Beyond Demographics: Aligning Role-playing LLM-based Agents Using Human Belief Networks","created":"2024-06-25","cited_by_count":39},{"id":"1708.09085","title":"Argument Strength is in the Eye of the Beholder: Audience Effects in Persuasion","created":"2017-08-30","cited_by_count":35},{"id":"2404.15058","title":"A Mechanism-Based Approach to Mitigating Harms from Persuasive Generative AI","created":"2024-04-23","cited_by_count":34},{"id":"2411.06837","title":"Persuasion with Large Language Models: A Survey of Empirical Evidence, Study Methodologies, and Ethical Implications","created":"2024-11-11","cited_by_count":32},{"id":"1906.11301","title":"Exploring the Role of Prior Beliefs for Argument Persuasion","created":"2019-06-26","cited_by_count":31},{"id":"2406.17753","title":"Measuring and Benchmarking Large Language Models' Capabilities to Generate Persuasive Language","created":"2024-06-25","cited_by_count":31},{"id":"2503.01829","title":"Persuade Me if You Can: A Framework for Evaluating Persuasion Effectiveness and Susceptibility Among Large Language Models","created":"2025-03-03","cited_by_count":27},{"id":"2504.10430","title":"LLM Can be a Dangerous Persuader: Empirical Study of Persuasion Safety in Large Language Models","created":"2025-04-14","cited_by_count":23},{"id":"2603.16567","title":"Characterizing Delusional Spirals through Human-LLM Chat Logs","created":"2026-03-17","cited_by_count":23},{"id":"2512.08093","title":"Training LLMs for Honesty via Confessions","created":"2025-12-08","cited_by_count":22},{"id":"2404.00750","title":"Can Language Models Recognize Convincing Arguments?","created":"2024-03-31","cited_by_count":21},{"id":"2506.06299","title":"How malicious AI swarms can threaten democracy: The fusion of agentic AI and LLMs marks a new frontier in information warfare","created":"2025-05-18","cited_by_count":20},{"id":"2507.13919","title":"The Levers of Political Persuasion with Conversational AI","created":"2025-07-18","cited_by_count":20},{"id":"2510.06084","title":"Spectrum Tuning: Post-Training for Distributional Coverage and In-Context Steerability","created":"2025-10-07","cited_by_count":20},{"id":"2004.03034","title":"The Role of Pragmatic and Discourse Context in Determining Argument Impact","created":"2020-04-06","cited_by_count":18},{"id":"2502.21017","title":"PersuasiveToM: A Benchmark for Evaluating Machine Theory of Mind in Persuasive Dialogues","created":"2025-02-28","cited_by_count":17},{"id":"2505.15918","title":"Extracting Probabilistic Knowledge from Large Language Models for Bayesian Network Parameterization","created":"2025-05-21","cited_by_count":15},{"id":"2506.02873","title":"It's the Thought that Counts: Evaluating the Attempts of Frontier LLMs to Persuade on Harmful Topics","created":"2025-06-03","cited_by_count":14},{"id":"2510.04226","title":"What and Whose Knowledge? Measuring Epistemic Diversity in Large Language Models","created":"2025-10-05","cited_by_count":14},{"id":"2511.22662","title":"Difficulties with Evaluating a Deception Detector for AIs","created":"2025-11-27","cited_by_count":13},{"id":"2407.19638","title":"On the Reliability of Large Language Models for Causal Discovery","created":"2024-07-29","cited_by_count":12},{"id":"2505.22961","title":"ToMAP: Training Opponent-Aware LLM Persuaders with Theory of Mind","created":"2025-05-29","cited_by_count":12},{"id":"1907.06076","title":"Changing Views: Persuasion Modeling and Argument Extraction from Online Discussions","created":"2019-07-13","cited_by_count":11},{"id":"2506.06166","title":"The Lock-in Hypothesis: Stagnation by Algorithm","created":"2025-06-06","cited_by_count":11},{"id":"2506.06842","title":"PCoT: Persuasion-Augmented Chain of Thought for Detecting Fake News and Social Media Disinformation","created":"2025-06-07","cited_by_count":11},{"id":"2209.09578","title":"MultiMediate '22: Backchannel Detection and Agreement Estimation in Group Interactions","created":"2022-09-20","cited_by_count":10},{"id":"2507.16196","title":"Do Large Language Models Have a Planning Theory of Mind? Evidence from MindGames: a Multi-Step Persuasion Task","created":"2025-07-22","cited_by_count":9},{"id":"2311.16466","title":"The Adoption and Efficacy of Large Language Models: Evidence From Consumer Complaints in the Financial Industry","created":"2023-11-28","cited_by_count":8},{"id":"2402.07010","title":"Impact of Voice Fidelity on Decision Making: A Potential Dark Pattern?","created":"2024-02-10","cited_by_count":8},{"id":"2501.17273","title":"Tailored Truths: Optimizing LLM Persuasion with Personalization and Fabricated Statistics","created":"2025-01-28","cited_by_count":8},{"id":"2204.07741","title":"Persua: A Visual Interactive System to Enhance the Persuasiveness of Arguments in Online Discussion","created":"2022-04-16","cited_by_count":7},{"id":"2403.08890","title":"From \"um\" to \"yeah\": Producing, predicting, and regulating information flow in human conversation","created":"2024-03-13","cited_by_count":7},{"id":"2406.13905","title":"Persuasiveness of Generated Free-Text Rationales in Subjective Decisions: A Case Study on Pairwise Argument Ranking","created":"2024-06-20","cited_by_count":7},{"id":"2509.17938","title":"D-REX: A Benchmark for Detecting Deceptive Reasoning in Large Language Models","created":"2025-09-22","cited_by_count":7},{"id":"2512.01431","title":"A Meta-Analysis of the Persuasive Power of Large Language Models","created":"2025-12-01","cited_by_count":7},{"id":"2410.21141","title":"LLM-initialized Differentiable Causal Discovery","created":"2024-10-28","cited_by_count":6},{"id":"1804.00065","title":"Attentive Interaction Model: Modeling Changes in View in Argumentation","created":"2018-03-30","cited_by_count":4},{"id":"2512.06573","title":"The Effect of Belief Boxes and Open-mindedness on Persuasion","created":"2025-12-06","cited_by_count":3},{"id":"2601.10660","title":"Detecting Winning Arguments with Large Language Models and Persuasion Strategies","created":"2026-01-15","cited_by_count":3},{"id":"2006.00707","title":"Influence via Ethos: On the Persuasive Power of Reputation in Deliberation Online","created":"2020-06-01","cited_by_count":2},{"id":"2511.22109","title":"A Hybrid Theory and Data-driven Approach to Persuasion Detection with Large Language Models","created":"2025-11-27","cited_by_count":2}],"next_cursor":null}