Metraipolis › archive › dc_ac889ac1194e

Risk-Conditioned Fine-Tuning of Large Language Models — arXiv:2609.08064

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.08064
License (as archived)
CC0-1.0
Archived
2026-10-16T13:58:05.574Z
SHA-256 of the archived text
2ca1197726a808b797c15a3419825186f9535a746332ef362dac7720e7aa1480
Stable URL of this page
https://metraipolis.com/documento/dc_ac889ac1194e

How to cite

Risk-Conditioned Fine-Tuning of Large Language Models — arXiv:2609.08064 — arXiv (en), https://arxiv.org/abs/2609.08064 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ac889ac1194e (Metraipolis archive dc_ac889ac1194e, sha256 2ca1197726a808b797c15a3419825186f9535a746332ef362dac7720e7aa1480)
BibTeX
@misc{dcac889ac1194e,
  title = {Risk-Conditioned Fine-Tuning of Large Language Models — arXiv:2609.08064},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.08064},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ac889ac1194e; sha256 2ca1197726a808b797c15a3419825186f9535a746332ef362dac7720e7aa1480},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.08064. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Large Language Models (LLMs) are increasingly deployed in settings where rare but severe harmful generations can have significant consequences. Existing Risk-Averse RLHF addresses this issue by optimizing Conditional Value-at-Risk (CVaR), but it trains policies for fixed risk levels and therefore cannot adjust the desired degree of risk aversion at inference time. In this paper, we propose risk-conditioned RLHF, a framework that trains a single policy that provides a continuous risk-control interface, enabling users to select different degrees of risk aversion without retraining or deploying multiple risk-specific models. Experiments across multiple benchmarks demonstrate that a single risk-conditioned policy can adapt to different risk levels at inference time, enabling more flexible and risk-aware LLM deployment.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-09 in cs.LG).
Categorie arXiv: Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2609.08064 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-16T13:39:43.015Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-09?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).