activity
20232026
most citedArtificial Intelligence in Spectroscopy: Advancing Chemistry from Prediction to Generation and Beyond

7 citations · 12 across the 18 of their papers we have counts for

collaborators
Showing cs.CLShow all

11 papers · 1 filter

cs.CL2026

Learning from Synthetic Data without Model Collapse in Iterative Instruction Tuning

Xiaonan Luo, Yue Huang, Kehan Guo +4

Model collapse is a central challenge in learning from synthetic data: as later-generation large language models (LLMs) are trained on an increasing proportion of model-generated d…

cs.CL2026

NARRA-Gym for Evaluating Interactive Narrative Agents

Yue Huang, Yuchen Ma, Jiayi Ye +14

Interactive narrative tasks require LLMs to sustain a coherent, evolving story while adapting to a user over multiple turns. However, suitable benchmarks for this setting are limit…

cs.CL2026

PolicyLLM: Towards Excellent Comprehension of Public Policy for Large Language Models

Han Bao, Penghao Zhang, Yue Huang +9

Large Language Models (LLMs) are increasingly integrated into real-world decision-making, including in the domain of public policy. Yet, their ability to comprehend and reason abou…

cs.CL2026

Reliable Control-Point Selection for Steering Reasoning in Large Language Models

Haomin Zhuang, Hojun Yoo, Xiaonan Luo +2

Steering vectors offer a training-free mechanism for controlling reasoning behaviors in large language models, but constructing effective vectors requires identifying genuine behav…

cs.CL2026

Dual Optimal: Make Your LLM Peer-like with Dignity

Xiangqi Wang, Yue Huang, Haomin Zhuang +2

Current aligned language models exhibit a dual failure mode we term the Evasive Servant: they sycophantically validate flawed user beliefs while deflecting responsibility with boil…

cs.CL2026

ProbeLLM: Automating Principled Diagnosis of LLM Failures

Yue Huang, Zhengzhe Jiang, Yuchen Ma +8

Understanding how and why large language models (LLMs) fail is becoming a central challenge as models rapidly evolve and static evaluations fall behind. While automated probing has…