activity
20242026
collaborators

5 papers

cs.AI2026

Proxy Reward Internalization and Mechanistic Exploitation: A Learned Precursor to Reward Hacking and Its Generalization

Mohammad Beigi, Ming Jin, Lifu Huang

Reward hacking is usually studied after it becomes visible, once a model earns high proxy reward while failing the intended task. We instead study what proxy RL teaches before that…

cs.AI2026

Adversarial Reward Auditing for Active Detection and Mitigation of Reward Hacking

Mohammad Beigi, Ming Jin, Junshan Zhang +2

Reinforcement Learning from Human Feedback (RLHF) remains vulnerable to reward hacking, where models exploit spurious correlations in learned reward models to achieve high scores w…

cs.AI2025

Sycophancy Mitigation Through Reinforcement Learning with Uncertainty-Aware Adaptive Reasoning Trajectories

Mohammad Beigi, Ying Shen, Parshin Shojaee +5

Despite the remarkable capabilities of large language models, current training paradigms inadvertently foster \textit{sycophancy}, i.e., the tendency of a model to agree with or re…

cs.AI2024

Rethinking the Uncertainty: A Critical Review and Analysis in the Era of Large Language Models

Mohammad Beigi, Sijia Wang, Ying Shen +9

In recent years, Large Language Models (LLMs) have become fundamental to a broad spectrum of artificial intelligence applications. As the use of LLMs expands, precisely estimating…

cs.CL2024

Can We Trust the Performance Evaluation of Uncertainty Estimation Methods in Text Summarization?

Jianfeng He, Runing Yang, Linlin Yu +5

Text summarization, a key natural language generation (NLG) task, is vital in various domains. However, the high cost of inaccurate summaries in risk-critical applications, particu…