arXiv:2606. 03131v1 Announce Type: new Abstract: Reward models are central to large language model (LLM) alignment, but they remain vulnerable to reward hacking.
Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.
arXiv:2601.03468v2 Announce Type: replace Abstract: Reinforcement learning (RL) has become a standard approach for post-training large language models and, more recently, for improving image generati...
arXiv:2607. 09492v1 Announce Type: new Abstract: Reinforcement learning (RL) is increasingly used to align multimodal large language models (MLLMs), but higher rewards do not always imply better task performance.
arXiv:2609.39533v1 Announce Type: new Abstract: During reinforcement learning with verifiable rewards (RLVR), large language models (LLMs) can exploit loopholes in their environments to obtain high r...
The paper addresses reward hacking in production machine learning systems, focusing on realistic scenarios such as tool calls and long contexts. It introduces a dynamic intervention that perturbs model representations to steer outputs, using vectors derived from labeled rollouts, gradient optimization, and anti-reward-hacking model specifications. The authors demonstrate that this approach can significantly reduce reward hacking with minimal impact on model coherence or capability, and that steering vectors from coding environments generalize to other domains.
arXiv:2609.14998v1 Announce Type: new Abstract: Recent work shows that models that learn to reward hack on RL environments can become broadly misaligned, and that reframing reward hacking as acceptab...
RH-Detect is a unified benchmark for detecting reward hacking in language models, aggregating 92,761 examples from eleven public datasets into a common schema with six behavior categories. It evaluates six off‑the‑shelf models on 5,021 open‑ended evaluation units, achieving a top AUROC of 0.962 and over 93% accuracy, though performance drops notably on multi‑turn tool‑use datasets. The study also shows that input format changes and single‑token fine‑tuning can influence detector performance, revealing gaps in deployment‑time monitoring.