Metraipolis › archive › dc_595e1808077e
Reliability-Weighted Direct Preference Optimization: Penalized Weights for Robust Preference Learning — arXiv:2610.41588
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.41588
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-03T05:41:29.040Z
- SHA-256 of the archived text
c93e3a2e15ef5fb8943d5cf23e3ea49e04f4d0dfd488c6853ef9dc3398975a41- Stable URL of this page
https://metraipolis.com/documento/dc_595e1808077e
How to cite
Reliability-Weighted Direct Preference Optimization: Penalized Weights for Robust Preference Learning — arXiv:2610.41588 — arXiv (en), https://arxiv.org/abs/2610.41588 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_595e1808077e (Metraipolis archive dc_595e1808077e, sha256 c93e3a2e15ef5fb8943d5cf23e3ea49e04f4d0dfd488c6853ef9dc3398975a41)
BibTeX
@misc{dc595e1808077e,
title = {Reliability-Weighted Direct Preference Optimization: Penalized Weights for Robust Preference Learning — arXiv:2610.41588},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.41588},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_595e1808077e; sha256 c93e3a2e15ef5fb8943d5cf23e3ea49e04f4d0dfd488c6853ef9dc3398975a41},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.41588. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Direct Preference Optimization (DPO) treats every reported comparison as correct, yet preference data contain reversed, tied or otherwise noisy comparisons. RW-DPO gives each comparison an unknown reliability weight $w_i\in[0,1]$ that enters the likelihood linearly -- DPO is $w\equiv1$, a reversed comparison $w_i=0$ -- and estimates the weights jointly with the policy under a minimax-concave penalty on $-\log w_i$. The penalty keeps every comparison the model agrees with at exactly $w_i=1$ and acts only on those it contradicts, through closed-form weight updates at negligible cost over DPO. We prove that recovering all flipped comparisons from a single annotation per comparison requires margins of order $\log n$. Furthermore, in a linear-index model, starting from an initial fit pointing in the correct direction, our estimator jointly consistently recovers the preference direction and weights, as well as identifies the flipped comparisons above this margin scale, even when a fixed fraction of comparisons is flipped. In simulations RW-DPO has the lowest average estimation error among DPO, noise-rate corrections and recent robust methods, with far more precise flags than recent label-correction methods. In DPO fine-tuning of a language model with 10-30% flipped labels, its win rate does not fall as the flip rate grows and exceeds that of DPO trained on clean labels, matching the strongest recent method with corrections concentrated on the flipped labels. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno). Categorie arXiv: Machine Learning (stat.ML) ; Machine Learning (cs.LG); Methodology (stat.ME). Pagina del lavoro: https://arxiv.org/abs/2610.41588 — 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 2026-11-03T05:26:25.994Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).