{"list":"other","total":52,"rows":[{"id":"2505.09388","title":"Qwen3 Technical Report","created":"2025-05-14","cited_by_count":8820},{"id":"2304.03442","title":"Generative Agents: Interactive Simulacra of Human Behavior","created":"2023-04-07","cited_by_count":3568},{"id":"2308.08155","title":"AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation","created":"2023-08-16","cited_by_count":1988},{"id":"2308.00352","title":"MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework","created":"2023-08-01","cited_by_count":1808},{"id":"2309.08600","title":"Sparse Autoencoders Find Highly Interpretable Features in Language Models","created":"2023-09-15","cited_by_count":1420},{"id":"2303.17760","title":"CAMEL: Communicative Agents for \"Mind\" Exploration of Large Language Model Society","created":"2023-03-31","cited_by_count":1395},{"id":"2310.01405","title":"Representation Engineering: A Top-Down Approach to AI Transparency","created":"2023-10-02","cited_by_count":1336},{"id":"2306.03341","title":"Inference-Time Intervention: Eliciting Truthful Answers from a Language Model","created":"2023-06-06","cited_by_count":1302},{"id":"2312.06681","title":"Steering Llama 2 via Contrastive Activation Addition","created":"2023-12-09","cited_by_count":1085},{"id":"2406.11717","title":"Refusal in Language Models Is Mediated by a Single Direction","created":"2024-06-17","cited_by_count":1032},{"id":"2209.10652","title":"Toy Models of Superposition","created":"2022-09-21","cited_by_count":971},{"id":"2308.10248","title":"Steering Language Models With Activation Engineering","created":"2023-08-20","cited_by_count":922},{"id":"2307.07924","title":"ChatDev: Communicative Agents for Software Development","created":"2023-07-16","cited_by_count":919},{"id":"2102.12452","title":"Probing Classifiers: Promises, Shortcomings, and Advances","created":"2021-02-24","cited_by_count":876},{"id":"2303.17548","title":"Whose Opinions Do Language Models Reflect?","created":"2023-03-30","cited_by_count":773},{"id":"2209.06899","title":"Out of One, Many: Using Language Models to Simulate Human Samples","created":"2022-09-14","cited_by_count":752},{"id":"2311.03658","title":"The Linear Representation Hypothesis and the Geometry of Large Language Models","created":"2023-11-07","cited_by_count":716},{"id":"2406.04093","title":"Scaling and evaluating sparse autoencoders","created":"2024-06-06","cited_by_count":553},{"id":"2403.19647","title":"Sparse Feature Circuits: Discovering and Editing Interpretable Causal Graphs in Language Models","created":"2024-03-28","cited_by_count":435},{"id":"2507.21509","title":"Persona Vectors: Monitoring and Controlling Character Traits in Language Models","created":"2025-07-29","cited_by_count":345},{"id":"2310.10158","title":"Character-LLM: A Trainable Agent for Role-Playing","created":"2023-10-16","cited_by_count":339},{"id":"2308.07702","title":"Better Zero-Shot Reasoning with Role-Play Prompting","created":"2023-08-15","cited_by_count":223},{"id":"2405.14860","title":"Not All Language Model Features Are One-Dimensionally Linear","created":"2024-05-23","cited_by_count":212},{"id":"2406.01171","title":"Two Tales of Persona in LLMs: A Survey of Role-Playing and Personalization","created":"2024-06-03","cited_by_count":208},{"id":"2305.18189","title":"Marked Personas: Using Natural Language Prompts to Measure Stereotypes in Language Models","created":"2023-05-29","cited_by_count":207},{"id":"2311.04892","title":"Bias Runs Deep: Implicit Reasoning Biases in Persona-Assigned LLMs","created":"2023-11-08","cited_by_count":199},{"id":"2310.17976","title":"InCharacter: Evaluating Personality Fidelity in Role-Playing Agents through Psychological Interviews","created":"2023-10-27","cited_by_count":179},{"id":"2310.00746","title":"RoleLLM: Benchmarking, Eliciting, and Enhancing Role-Playing Abilities of Large Language Models","created":"2023-10-01","cited_by_count":175},{"id":"2406.01506","title":"The Geometry of Categorical and Hierarchical Concepts in Large Language Models","created":"2024-06-03","cited_by_count":159},{"id":"2305.14930","title":"In-Context Impersonation Reveals Large Language Models' Strengths and Biases","created":"2023-05-24","cited_by_count":155},{"id":"2310.10436","title":"EconAgent: Large Language Model-Empowered Agents for Simulating Macroeconomic Activities","created":"2023-10-16","cited_by_count":154},{"id":"2401.01275","title":"CharacterEval: A Chinese Benchmark for Role-Playing Conversational Agent Evaluation","created":"2024-01-02","cited_by_count":143},{"id":"2601.10387","title":"The Assistant Axis: Situating and Stabilizing the Default Persona of Language Models","created":"2026-01-15","cited_by_count":90},{"id":"2412.03563","title":"From Individual to Society: A Survey on Social Simulation Driven by Large Language Model-based Agents","created":"2024-12-04","cited_by_count":82},{"id":"2312.15997","title":"Aligning Large Language Models with Human Preferences through Representation Engineering","created":"2023-12-26","cited_by_count":71},{"id":"2312.03813","title":"Improving Activation Steering in Language Models with Mean-Centring","created":"2023-12-06","cited_by_count":68},{"id":"2310.05984","title":"Simulating Social Media Using Large Language Models to Evaluate Alternative News Feed Algorithms","created":"2023-10-05","cited_by_count":65},{"id":"2406.17055","title":"Large Language Models Assume People are More Rational than We Really are","created":"2024-06-24","cited_by_count":54},{"id":"2311.04978","title":"On the steerability of large language models toward data-driven personas","created":"2023-11-08","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":"2307.04986","title":"Epidemic Modeling with Generative Agents","created":"2023-07-11","cited_by_count":49},{"id":"2407.11484","title":"The Oscars of AI Theater: A Survey on Role-Playing with Language Models","created":"2024-07-16","cited_by_count":48},{"id":"2310.18168","title":"Personas as a Way to Model Truthfulness in Language Models","created":"2023-10-27","cited_by_count":47},{"id":"2501.08579","title":"LLM-based Human Simulations Have Not Yet Been Reliable","created":"2025-01-15","cited_by_count":30},{"id":"2405.06058","title":"Large Language Models Show Human-like Social Desirability Biases in Survey Responses","created":"2024-05-09","cited_by_count":28},{"id":"2502.17601","title":"Representation Engineering for Large-Language Models: Survey and Research Challenges","created":"2025-02-24","cited_by_count":21},{"id":"2602.15669","title":"PERSONA: Dynamic and Compositional Inference-Time Personality Control via Activation Vector Algebra","created":"2026-02-17","cited_by_count":12},{"id":"2604.17031","title":"Where is the Mind? Persona Vectors and LLM Individuation","created":"2026-04-18","cited_by_count":10},{"id":"2409.13733","title":"RNR: Teaching Large Language Models to Follow Roles and Rules","created":"2024-09-10","cited_by_count":6},{"id":"2604.11048","title":"A Systematic Analysis of the Impact of Persona Steering on LLM Capabilities","created":"2026-04-13","cited_by_count":5},{"id":"2604.07886","title":"Linear Representations of Hierarchical Concepts in Language Models","created":"2026-04-09","cited_by_count":4},{"id":"2507.06427","title":"Exploring Task Performance with Interpretable Models via Sparse Auto-Encoders","created":"2025-07-08","cited_by_count":1}],"next_cursor":null}