publications
publications by categories in reversed chronological order. generated by jekyll-scholar.
2026
- COLM 2026Useless but Safe? Benchmarking Utility Recovery with User Intent Clarification in Multi-Turn ConversationsIn COLM, 2026
- ACL 2026 FindingsImperfectly Cooperative Human-AI Interactions: Comparing the Impacts of Human and AI Attributes in Simulated and User StudiesIn Findings of ACL, 2026
2025
- EMNLP 2025 FindingsLet Them Down Easy! Contextual Effects of LLM Guardrails on User Perceptions and Preferences2025
- EMNLP 2025Synthetic Socratic Debates: Examining Persona Effects on Moral Decision and Persuasion Dynamics2025
2024
- NAACL 2025Causally Modeling the Linguistic and Social Factors that Predict Email ResponseSep 2024
- EMNLP 2024 FindingsWhen "A Helpful Assistant" Is Not Really Helpful: Personas in System Prompts Do Not Improve Performances of Large Language ModelsarXiv preprint arXiv:2311.10054, Sep 2024