activity
20242026
collaborators

7 papers

cs.CR2026

Single Canonical Prompts Underestimate LLM Safety's Surface-Form Sensitivity

Yongxi Zhou, Junwei Yao, Yuanzhe Liu +4

A benchmark score is a measurement instrument, yet most benchmarks read each item at a single canonical surface form. We ask whether that reading is faithful: when an item's intent…

cs.LG2026

Accuracy, Stability, and Repeated-Run Reliability of Large Language Models on Deterministic Programming Tasks

Yongxi Zhou, Lai Yun Choi, Jiaxi Wen +1

Run-level pass rate overstates retry-free coverage by up to 17.8 percentage points -- and the gap is largest precisely for mid-performing systems. We investigate this accuracy--sta…

cs.CL2026

Unsupervised Elicitation of Language Models

Jiaxin Wen, Zachary Ankner, Arushi Somani +10

To steer pretrained language models for downstream tasks, today's post-training paradigm relies on humans to specify desired behaviors. However, for models with superhuman capabili…

cs.LG2025

Efficient Hyperparameter Tuning via Trajectory Invariance Principle

Bingrui Li, Jiaxin Wen, Zhanpeng Zhou +2

As hyperparameter tuning becomes increasingly costly at scale, efficient tuning methods are essential. Yet principles for guiding hyperparameter tuning remain limited. In this work…

cs.CR2025

Measuring Harmfulness of Computer-Using Agents

Aaron Xuxiang Tian, Ruofan Zhang, Janet Tang +3

Computer-using agents (CUAs), which can autonomously control computers to perform multi-step actions, might pose significant safety risks if misused. However, existing benchmarks m…

cs.AI2025

Predicting Empirical AI Research Outcomes with Language Models

Jiaxin Wen, Chenglei Si, Yueh-han Chen +2

Many promising-looking ideas in AI research fail to deliver, but their validation takes substantial human labor and compute. Predicting an idea's chance of success is thus crucial…