{"total":73,"rows":[{"id":"2305.16367","title":"Role-Play with Large Language Models","created":"2023-05-25","cited_by_count":294,"area":null},{"id":"2307.14324","title":"Evaluating the Moral Beliefs Encoded in LLMs","created":"2023-07-26","cited_by_count":215,"area":null},{"id":"2307.04738","title":"RoCo: Dialectic Multi-Robot Collaboration with Large Language Models","created":"2023-07-10","cited_by_count":172,"area":null},{"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,"area":null},{"id":"2406.02630","title":"AI Agents Under Threat: A Survey of Key Security Challenges and Future Pathways","created":"2024-06-04","cited_by_count":127,"area":null},{"id":"2309.17234","title":"Cooperation, Competition, and Maliciousness: LLM-Stakeholders Interactive Negotiation","created":"2023-09-29","cited_by_count":96,"area":null},{"id":"2304.00612","title":"Eight Things to Know about Large Language Models","created":"2023-04-02","cited_by_count":73,"area":null},{"id":"2212.06801","title":"A fine-grained comparison of pragmatic language understanding in humans and language models","created":"2022-12-13","cited_by_count":70,"area":null},{"id":"2407.02996","title":"Are Large Language Models Consistent over Value-laden Questions?","created":"2024-07-03","cited_by_count":58,"area":null},{"id":"2308.13198","title":"Journey to the Center of the Knowledge Neurons: Discoveries of Language-Independent Knowledge Neurons and Degenerate Knowledge Neurons","created":"2023-08-25","cited_by_count":56,"area":null},{"id":"2307.07870","title":"Large Language Models as Superpositions of Cultural Perspectives","created":"2023-07-15","cited_by_count":49,"area":null},{"id":"2401.04536","title":"Evaluating Language Model Agency through Negotiations","created":"2024-01-09","cited_by_count":48,"area":null},{"id":"2310.18168","title":"Personas as a Way to Model Truthfulness in Language Models","created":"2023-10-27","cited_by_count":47,"area":null},{"id":"2502.02528","title":"Why human-AI relationships need socioaffective alignment","created":"2025-02-04","cited_by_count":47,"area":null},{"id":"2310.18362","title":"SoK: Memorization in General-Purpose Large Language Models","created":"2023-10-24","cited_by_count":37,"area":null},{"id":"2401.11839","title":"AI for social science and social science of AI: A Survey","created":"2024-01-22","cited_by_count":29,"area":null},{"id":"2310.11409","title":"LLMs as Hackers: Autonomous Linux Privilege Escalation Attacks","created":"2023-10-17","cited_by_count":27,"area":null},{"id":"2409.14457","title":"Large Model Based Agents: State-of-the-Art, Cooperation Paradigms, Security and Privacy, and Future Trends","created":"2024-09-22","cited_by_count":26,"area":null},{"id":"2306.09610","title":"CHORUS: Foundation Models for Unified Data Discovery and Exploration","created":"2023-06-16","cited_by_count":24,"area":null},{"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,"area":null},{"id":"2401.03910","title":"A Philosophical Introduction to Language Models -- Part I: Continuity With Classic Debates","created":"2024-01-08","cited_by_count":23,"area":null},{"id":"2311.08576","title":"Towards Evaluating AI Systems for Moral Status Using Self-Reports","created":"2023-11-14","cited_by_count":22,"area":null},{"id":"2302.01339","title":"Creating a Large Language Model of a Philosopher","created":"2023-02-02","cited_by_count":21,"area":null},{"id":"2308.00189","title":"Generative Models as a Complex Systems Science: How can we make sense of large language model behavior?","created":"2023-07-31","cited_by_count":19,"area":null},{"id":"2402.00854","title":"SymbolicAI: A framework for logic-based approaches combining generative models and solvers","created":"2024-02-01","cited_by_count":16,"area":null},{"id":"2402.12422","title":"Simulacra as Conscious Exotica","created":"2024-02-19","cited_by_count":16,"area":null},{"id":"2311.00687","title":"Improving Interpersonal Communication by Simulating Audiences with Language Models","created":"2023-11-01","cited_by_count":14,"area":null},{"id":"2212.10029","title":"Do language models have coherent mental models of everyday things?","created":"2022-12-20","cited_by_count":13,"area":null},{"id":"2506.10341","title":"Formalizing Learning from Language Feedback with Provable Guarantees","created":"2025-06-12","cited_by_count":13,"area":null},{"id":"2303.13360","title":"Towards the Scalable Evaluation of Cooperativeness in Language Models","created":"2023-03-16","cited_by_count":12,"area":null},{"id":"2304.07007","title":"Dialogue Games for Benchmarking Language Understanding: Motivation, Taxonomy, Strategy","created":"2023-04-14","cited_by_count":12,"area":null},{"id":"2305.02469","title":"The System Model and the User Model: Exploring AI Dashboard Design","created":"2023-05-04","cited_by_count":12,"area":null},{"id":"2308.03854","title":"Revisiting Prompt Engineering via Declarative Crowdsourcing","created":"2023-08-07","cited_by_count":12,"area":null},{"id":"2406.03707","title":"What Should Embeddings Embed? Autoregressive Models Represent Latent Generating Distributions","created":"2024-06-06","cited_by_count":10,"area":null},{"id":"2504.00285","title":"When Do Large Language Models Exhibit Unsolicited Deception?","created":"2025-03-31","cited_by_count":10,"area":null},{"id":"2306.05240","title":"Dealing with Semantic Underspecification in Multimodal NLP","created":"2023-06-08","cited_by_count":9,"area":null},{"id":"2411.02989","title":"Growing a Tail: Increasing Output Diversity in Large Language Models","created":"2024-11-05","cited_by_count":9,"area":null},{"id":"2601.04436","title":"Learning to Simulate Human Dialogue","created":"2026-01-07","cited_by_count":9,"area":null},{"id":"2410.01985","title":"Lost-in-Distance: Impact of Contextual Proximity on LLM Performance in Graph Tasks","created":"2024-10-02","cited_by_count":8,"area":null},{"id":"2312.14226","title":"Deep de Finetti: Recovering Topic Distributions from Large Language Models","created":"2023-12-21","cited_by_count":7,"area":null},{"id":"2407.10735","title":"Transforming Agency. On the mode of existence of Large Language Models","created":"2024-07-15","cited_by_count":7,"area":null},{"id":"2510.25744","title":"Completion $\\neq$ Collaboration: Scaling Collaborative Effort with Agents","created":"2025-10-29","cited_by_count":6,"area":null},{"id":"2505.13157","title":"Role-Playing Evaluation for Large Language Models","created":"2025-05-19","cited_by_count":5,"area":null},{"id":"2303.04229","title":"Understanding Natural Language Understanding Systems. A Critical Analysis","created":"2023-03-01","cited_by_count":4,"area":null},{"id":"2405.06478","title":"Attention is all they need: Cognitive science and the (techno)political economy of attention in humans and machines","created":"2024-05-10","cited_by_count":4,"area":null},{"id":"2412.06412","title":"StarWhisper Telescope: An AI framework for automating end-to-end astronomical observations","created":"2024-12-09","cited_by_count":4,"area":null},{"id":"2505.10309","title":"A large-scale evaluation of commonsense knowledge in humans and large language models","created":"2025-05-15","cited_by_count":4,"area":null},{"id":"2506.04650","title":"Neural Network Reprogrammability: A Unified Theme on Model Reprogramming, Prompt Tuning, and Prompt Instruction","created":"2025-06-05","cited_by_count":4,"area":null},{"id":"2312.03853","title":"Dr. Jekyll and Mr. Hyde: Two Faces of LLMs","created":"2023-12-06","cited_by_count":3,"area":null},{"id":"2602.02467","title":"Indications of Belief-Guided Agency and Meta-Cognitive Monitoring in Large Language Models","created":"2026-02-02","cited_by_count":3,"area":null},{"id":"2605.13339","title":"Probing Persona-Dependent Preferences in Language Models","created":"2026-05-13","cited_by_count":3,"area":null},{"id":"2305.02632","title":"A framework for the emergence and analysis of language in social learning agents","created":"2023-05-04","cited_by_count":2,"area":null},{"id":"2306.12609","title":"Towards Regulatable AI Systems: Technical Gaps and Policy Opportunities","created":"2023-06-22","cited_by_count":2,"area":null},{"id":"2311.02294","title":"LLMs grasp morality in concept","created":"2023-11-04","cited_by_count":2,"area":null},{"id":"2501.10476","title":"Revisiting Rogers' Paradox in the Context of Human-AI Interaction","created":"2025-01-16","cited_by_count":2,"area":null},{"id":"2507.00163","title":"Prompting as Scientific Inquiry","created":"2025-06-30","cited_by_count":2,"area":null},{"id":"2603.29846","title":"SNEAK: Evaluating Strategic Communication and Information Leakage in Large Language Models","created":"2026-03-31","cited_by_count":2,"area":null},{"id":"2607.03598","title":"They Infer What You Meant: Models Represent Communicative Intent More Reliably Than They Act On It","created":"2026-07-03","cited_by_count":2,"area":null},{"id":"2402.11821","title":"Microstructures and Accuracy of Graph Recall by Large Language Models","created":"2024-02-19","cited_by_count":1,"area":null},{"id":"2407.13765","title":"Latent Causal Probing: A Formal Perspective on Probing with Causal Models of Data","created":"2024-07-18","cited_by_count":1,"area":null},{"id":"2410.16392","title":"Scaffolded Language Models with Language Supervision for Mixed-Autonomy: A Survey","created":"2024-10-21","cited_by_count":1,"area":null},{"id":"2506.01095","title":"Modular Speaker Architecture: A Framework for Sustaining Responsibility and Contextual Integrity in Multi-Agent AI Communication","created":"2025-06-01","cited_by_count":1,"area":null},{"id":"2506.13403","title":"Deflating Deflationism: A Critical Perspective on Debunking Arguments Against LLM Mentality","created":"2025-06-16","cited_by_count":1,"area":null},{"id":"2606.09475","title":"Emergent alignment and the projectability of ethical personas","created":"2026-06-08","cited_by_count":1,"area":null},{"id":"2402.16482","title":"On Languaging a Simulation Engine","created":"2024-02-26","cited_by_count":0,"area":null},{"id":"2411.01807","title":"Can Language Models Enable In-Context Database?","created":"2024-11-04","cited_by_count":0,"area":null},{"id":"2507.01061","title":"Epitome: Pioneering an Experimental Platform for AI-Social Science Integration","created":"2025-06-30","cited_by_count":0,"area":null},{"id":"2606.00545","title":"The Assistant as a Privileged Persona: A canonical reference in cross-persona self-recognition","created":"2026-05-30","cited_by_count":0,"area":null},{"id":"2606.23668","title":"On the Limits of Prompt-Conditioned Language Models as General-Purpose Learners","created":"2026-06-22","cited_by_count":0,"area":null},{"id":"2608.28560","title":"A Formal Limitation on Learning Human Language From Textual Corpora","created":"2026-08-28","cited_by_count":0,"area":null},{"id":"2609.22607","title":"Pretrained Persona Mixture Models and Tandem Models for Human Simulation","created":"2026-09-18","cited_by_count":0,"area":null},{"id":"2609.39341","title":"Understanding as No-Arbitrage: Bounded Dutch Books as a Definition and Training Objective for Language Models","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2609.39807","title":"Stress-Testing LLM Lie Detectors: Role-Play Failures and Spurious Correlations","created":"2026-09-30","cited_by_count":0,"area":null}],"next_cursor":null}