2 papers
cs.HC2025
Steerable Chatbots: Exploring Personalization Control Interfaces via LLM Activation Steering
Jessica Y. Bo, Tianyu Xu, Ishan Chatterjee +3
Personalizing LLM responses typically requires users to articulate their preferences through prompting, which can be burdensome at cold start and difficult to articulate in natural…
cs.AI2025
Reasoning-as-Logic-Units: Scaling Test-Time Reasoning in Large Language Models Through Logic Unit Alignment
Cheryl Li, Tianyuan Xu, Yiwen Guo
Chain-of-Thought (CoT) prompting has shown promise in enhancing the reasoning capabilities of large language models (LLMs) by generating natural language (NL) rationales that lead…