{"total":17,"rows":[{"id":"2601.21571","title":"Shaping capabilities with token-level data filtering","created":"2026-01-29","cited_by_count":13,"area":null},{"id":"2603.09517","title":"You Didn't Have to Say It like That: Subliminal Learning from Faithful Paraphrases","created":"2026-03-10","cited_by_count":8,"area":null},{"id":"2604.02423","title":"SWAY: A Counterfactual Computational Linguistic Approach to Measuring and Mitigating Sycophancy","created":"2026-04-02","cited_by_count":8,"area":null},{"id":"2606.11502","title":"When Role-playing, Do Models Believe What They Say?","created":"2026-06-09","cited_by_count":4,"area":null},{"id":"2607.07916","title":"Persona Cartography: Charting Language Model Personality Traits in Weight Space","created":"2026-07-08","cited_by_count":4,"area":null},{"id":"2605.13339","title":"Probing Persona-Dependent Preferences in Language Models","created":"2026-05-13","cited_by_count":3,"area":null},{"id":"2606.17657","title":"Using Cognitive Models to Improve Language Model Simulation of Human Persuasion Games","created":"2026-06-16","cited_by_count":2,"area":null},{"id":"2606.04413","title":"(Mis)generalization of Helpful-only Fine-tuning","created":"2026-06-03","cited_by_count":1,"area":null},{"id":"2609.23935","title":"Measuring the Assistant's Harmlessness Preferences on the User Turn","created":"2026-09-20","cited_by_count":1,"area":null},{"id":"2602.12763","title":"\"Not Human, Funnier\": How Machine Identity Shapes Humor Perception in Online AI Stand-up Comedy","created":"2026-02-13","cited_by_count":0,"area":null},{"id":"2605.02897","title":"Same Voice, Different Lab: On the Homogenization of Frontier LLM Personalities","created":"2026-03-20","cited_by_count":0,"area":null},{"id":"2605.07925","title":"How Value Induction Reshapes LLM Behaviour","created":"2026-05-08","cited_by_count":0,"area":null},{"id":"2608.26462","title":"Diff Mining: Logit Differences Reveal Finetuning Objectives","created":"2026-08-26","cited_by_count":0,"area":null},{"id":"2609.10883","title":"Story Imprinting: AI Assistants Absorb Traits from Human Characters They Resemble","created":"2026-09-09","cited_by_count":0,"area":null},{"id":"2609.15289","title":"Math for AI safety: an invitation for mathematicians","created":"2026-09-14","cited_by_count":0,"area":null},{"id":"2609.38093","title":"Character Training for Risk-Averse Agents","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2610.12410","title":"Predicting Alignment Generalization with Value Representations","created":"2026-10-08","cited_by_count":0,"area":null}],"next_cursor":null}