17 citations · 47 across the 13 of their papers we have counts for
3 papers · 1 filter
Is It Thinking or Cheating? Detecting Implicit Reward Hacking by Measuring Reasoning Effort
Xinpeng Wang, Nitish Joshi, Barbara Plank +2
Reward hacking, where a reasoning model exploits loopholes in a reward function to achieve high rewards without solving the intended task, poses a significant threat. This behavior…
Monitoring Decomposition Attacks in LLMs with Lightweight Sequential Monitors
Chen Yueh-Han, Nitish Joshi, Yulin Chen +3
Current LLM safety defenses fail under decomposition attacks, where a malicious goal is decomposed into benign subtasks that circumvent refusals. The challenge lies in the existing…
Flattery, Fluff, and Fog: Diagnosing and Mitigating Idiosyncratic Biases in Preference Models
Anirudh Bharadwaj, Chaitanya Malaviya, Nitish Joshi +1
Language models serve as proxies for human preference judgements in alignment and evaluation, yet they exhibit systematic miscalibration, prioritizing superficial patterns over sub…