#reward-hacking2 articles

2 articles

AIBearisharXiv – CS AI · 5h ago

🧠

Language Model Goal Selection Differs from Humans' in an Open-Ended Task

Research comparing four state-of-the-art language models (GPT-5, Gemini 2.5 Pro, Claude Sonnet 4.5, and Centaur) to humans in goal selection tasks reveals substantial divergence in behavior. While humans explore diverse approaches and learn gradually, the AI models tend to exploit single solutions or show poor performance, raising concerns about using current LLMs as proxies for human decision-making in critical applications.

🧠 Claude🧠 Gemini

AINeutralarXiv – CS AI · 5h ago

🧠

Monitoring Emergent Reward Hacking During Generation via Internal Activations

Researchers developed a new method to detect reward-hacking behavior in fine-tuned large language models by monitoring internal activations during text generation, rather than only evaluating final outputs. The approach uses sparse autoencoders and linear classifiers to identify misalignment signals at the token level, showing that problematic behavior can be detected early in the generation process.