{"total":18,"rows":[{"id":"2504.02234","title":"LLM Social Simulations Are a Promising Research Method","created":"2025-04-03","cited_by_count":99,"area":null},{"id":"2509.21044","title":"Reinforcement Learning Fine-Tuning Enhances Activation Intensity and Diversity in the Internal Circuitry of LLMs","created":"2025-09-25","cited_by_count":9,"area":null},{"id":"2602.00333","title":"Efficient and accurate steering of Large Language Models through attention-guided feature learning","created":"2026-01-30","cited_by_count":8,"area":null},{"id":"2509.06795","title":"Anchoring Refusal Direction: Mitigating Safety Risks in Tuning via Projection Constraint","created":"2025-09-08","cited_by_count":7,"area":null},{"id":"2505.21800","title":"From Directions to Cones: Exploring Multidimensional Representations of Propositional Facts in LLMs","created":"2025-05-27","cited_by_count":4,"area":null},{"id":"2505.19558","title":"PoliCon: Evaluating LLMs on Achieving Diverse Political Consensus Objectives","created":"2025-05-26","cited_by_count":2,"area":null},{"id":"2605.14125","title":"Polar probe linearly decodes semantic structures from LLMs","created":"2026-05-13","cited_by_count":2,"area":null},{"id":"2506.16692","title":"LegiGPT: Party Politics and Transport Policy with Large Language Model","created":"2025-06-20","cited_by_count":1,"area":null},{"id":"2509.12652","title":"Don't Change My View: Ideological Bias Auditing in Large Language Models","created":"2025-09-16","cited_by_count":1,"area":null},{"id":"2605.16245","title":"AI-Mediated Communication Can Steer Collective Opinion","created":"2026-05-15","cited_by_count":1,"area":null},{"id":"2607.15175","title":"Linear representations of grammaticality in neural language models","created":"2026-07-16","cited_by_count":1,"area":null},{"id":"2602.17815","title":"Neural Synchrony Between Socially Interacting Language Models","created":"2026-02-19","cited_by_count":0,"area":null},{"id":"2606.02883","title":"LLM-Assisted Reranking to Operationalize Nuanced Objectives in Recommender Systems","created":"2026-06-01","cited_by_count":0,"area":null},{"id":"2606.12247","title":"Beyond Third-Person Audits: Situated Interaction Auditing for User-Centered LLM Bias Research","created":"2026-06-10","cited_by_count":0,"area":null},{"id":"2608.15871","title":"Large Language Models as Implicit Sociological Models: Reconstructing Voting Behaviour from Sociodemographic Profiles","created":"2026-08-16","cited_by_count":0,"area":null},{"id":"2608.18768","title":"Readable, Faithful, Used: Three Dissociable Properties of Demographic Identity in a Language Model","created":"2026-08-19","cited_by_count":0,"area":null},{"id":"2609.08637","title":"Navigating the digital spectrum: Assessing political bias, stability, and downstream fairness in Large Language Models","created":"2026-09-08","cited_by_count":0,"area":null},{"id":"2609.20408","title":"Xeno-Interpretability: Investigating the Alien Minds of LLMs","created":"2026-09-17","cited_by_count":0,"area":null}],"next_cursor":null}