6 papers · 1 filter
Thinking Hard, Not Smart: Reasoning Models Fail to Ration Test-Time Compute Across Questions
Chenrui Fan, Yize Cheng, Ming Li +3
Reasoning language models increasingly use test-time compute to improve performance, but existing evaluations typically study this compute one question at a time. Yet when multiple…
When is Your LLM Steerable?
Chenrui Fan, Yize Cheng, Ming Li +2
Activation steering offers a lightweight approach to control language models' behavior at inference time, but whether it succeeds or fails heavily depends on the prompt, concept, m…
Schoenfeld's Anatomy of Mathematical Reasoning by Language Models
Ming Li, Chenrui Fan, Yize Cheng +2
Large language models increasingly expose reasoning traces, yet their underlying cognitive structure and steps remain difficult to identify and analyze beyond surface-level statist…
Your LLM Agents are Temporally Blind: The Misalignment Between Tool Use Decisions and Human Time Perception
Yize Cheng, Arshia Soltani Moakhar, Chenrui Fan +5
Large language model (LLM) agents are increasingly used to interact with and execute tasks in dynamic environments. However, a critical yet overlooked limitation of these agents is…
Adversarial Paraphrasing: A Universal Attack for Humanizing AI-Generated Text
Yize Cheng, Vinu Sankar Sadasivan, Mehrdad Saberi +2
The increasing capabilities of Large Language Models (LLMs) have raised concerns about their misuse in AI-generated plagiarism and social engineering. While various AI-generated te…
DyePack: Provably Flagging Test Set Contamination in LLMs Using Backdoors
Yize Cheng, Wenxiao Wang, Mazda Moayeri +1
Open benchmarks are essential for evaluating and advancing large language models, offering reproducibility and transparency. However, their accessibility makes them likely targets…