When Harry Meets Superman: The Role of The Interlocutor in Persona-Based Dialogue GenerationAnnual Meeting of the Association for Computational Linguistics (ACL), 2025 |
Position is Power: System Prompts as a Mechanism of Bias in Large Language Models (LLMs)Conference on Fairness, Accountability and Transparency (FAccT), 2025 |
Beyond Prompt Engineering: Robust Behavior Control in LLMs via Steering Target AtomsAnnual Meeting of the Association for Computational Linguistics (ACL), 2025 |
Exploiting Fine-Grained Skip Behaviors for Micro-Video RecommendationAAAI Conference on Artificial Intelligence (AAAI), 2025 |
An Auditing Test To Detect Behavioral Shift in Language ModelsInternational Conference on Learning Representations (ICLR), 2024 |