arXiv:2603. 10938v2 Announce Type: replace-cross Abstract: Safe Reinforcement Learning from Human Feedback (RLHF) typically enforces safety through expected cost constraints, but the expectation captures only a single statistic of the cost distribution and fails to account for distributional uncertainty, particularly under heavy tails or rare catastrophic events.
arXiv:2607. 22929v1 Announce Type: new Abstract: A short fine-tuning run can undo the safety guards of an open-weight model---retraining a refusal-trained assistant to aid weapons development or produce hate speech.
arXiv:2607. 13175v1 Announce Type: cross Abstract: Safe reinforcement learning typically enforces safety by bounding expected cumulative costs, a criterion that often fails to detect rare but catastrophic tail events.
The paper introduces new evaluation metrics for safe reinforcement learning that go beyond average safety guarantees by examining how often and how severely safety bounds are violated, consistency across tasks and bounds, and the relationship between training-time and final policy behavior. It also proposes a safety tier system for categorizing algorithms and presents empirical safety evaluations on multiple navigation tasks. The authors recommend reporting aggregate metrics, distributional data, and task‑specific results together, and provide an open‑source suite, SafeRLEval, to facilitate reliable safety assessment.
arXiv:2609.38938v1 Announce Type: new Abstract: Reinforcement learning with human feedback (RLHF) learns from human comparisons, which can be corrupted or deliberately manipulated. This paper studies...
arXiv:2605. 00155v3 Announce Type: replace Abstract: Reinforcement learning from human feedback (RLHF) is a central post-training tool for aligning large language models, but its training reward is only a learned proxy for true human utility.
arXiv:2604. 26360v2 Announce Type: replace-cross Abstract: Reinforcement learning from human feedback (RLHF) systems face a compounding alignment challenge: not only are learned reward models uncertain about unseen state-action pairs, but the human preference annotations they are trained on are themselves inconsistent, context-dependent, and noisy.
arXiv:2606. 14029v1 Announce Type: new Abstract: Constrained MDPs (CMDPs) are a widely adopted framework for incorporating safety into RL agents; however, the framework does not support risk-sensitive constraints.
arXiv:2405.14749v3 Announce Type: replace-cross Abstract: Risk-sensitive reinforcement learning (RL) is crucial for maintaining reliable performance in high-stakes applications. While traditional RL...
The paper introduces a new approach to learning chance-constrained Markov decision processes (CCMDPs) using a Bellman distributional certificate. It provides both model-based and model-free algorithms with theoretical guarantees, including matching upper and lower bounds for tabular discounted CCMDPs with bounded successor support. Numerical experiments on synthetic CCMDPs and an IEEE 14-bus energy storage benchmark demonstrate the safety and effectiveness of the proposed methods.
The paper introduces a chance-constrained approach to fine‑tune large language models (LLMs) that limits the proportion of safety examples whose performance degrades beyond a set threshold relative to a reference model. By replacing the discontinuous violation indicator with a differentiable majorization, the authors derive a tractable, conservative constraint and a closed‑form, constraint‑aware gradient update that focuses on examples near or above the degradation threshold. Experiments on harmful fine‑tuning across three tasks and models show that this tail‑aware method consistently outperforms existing safety‑preserving baselines, suggesting that safety preservation should be treated as a reliability‑constrained optimization problem rather than average‑risk regularization.
arXiv:2606. 00320v1 Announce Type: new Abstract: We present an online, distribution-free framework for controlling the Conditional Value-at-Risk (CVaR), extending conformal tail risk control to non-stationary and adversarial environments.
arXiv:2607. 15457v1 Announce Type: new Abstract: We study robust peak-cost constrained reinforcement learning (RP-CRL), where the objective is to maximize expected reward while controlling the maximum cost encountered along a trajectory.