4 papers
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…
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…
Transformers Struggle to Learn to Search
Abulhair Saparov, Srushti Pawar, Shreyas Pimpalgaonkar +6
Search is an ability foundational in many important tasks, and recent studies have shown that large language models (LLMs) struggle to perform search robustly. It is unknown whethe…