arXiv Machine Learning
Risk-Conditioned Fine-Tuning of Large Language Models
Read the original on arXiv Machine Learning →The Flow has not summarised this story yet — read it at arXiv Machine Learning.
Related stories
arXiv Machine Learning
Jun 2
Adversarially Robust Control of Conditional Value-at-Risk via Rockafellar-Uryasev Conformal Inference
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 AI
Jul 14
Behavioural Signatures of Risk-Sensitive Decision-Making in Large Language Models
arXiv:2607. 10251v1 Announce Type: new Abstract: As large language models (LLMs) are increasingly used in decision support, it is important to understand whether their choices under uncertainty exhibit stable and interpretable behavioural regularities.
arXiv AI
Sep 25
Beyond Average Safety: Chance-Constrained LLM Fine-tuning
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 AI
Jul 3
Conformal Policy Control
arXiv:2603. 02196v3 Announce Type: replace Abstract: An agent must try new behaviors to explore and improve.
arXiv AI
4d ago
Character Training for Risk-Averse Agents
arXiv:2609.38093v1 Announce Type: new Abstract: Risk aversion in resources could prevent misaligned AI agents from causing catastrophic harm. Misaligned but risk-averse agents would tend to favor saf...
arXiv Machine Learning
Jun 15
Utility-Constrained Policy Optimization
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.