Metraipolis › archive › dc_db2037705221
Jev-DLC: Decision-Level Continual Learning from Typed Feedback — arXiv:2610.31521
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.31521
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-25T20:53:28.414Z
- SHA-256 of the archived text
ee19a3c5057d43cc1c2e3aeca64be0d4fdcfcbf680f8c19472c253bb34aec23e- Stable URL of this page
https://metraipolis.com/documento/dc_db2037705221
How to cite
Jev-DLC: Decision-Level Continual Learning from Typed Feedback — arXiv:2610.31521 — arXiv (en), https://arxiv.org/abs/2610.31521 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_db2037705221 (Metraipolis archive dc_db2037705221, sha256 ee19a3c5057d43cc1c2e3aeca64be0d4fdcfcbf680f8c19472c253bb34aec23e)
BibTeX
@misc{dcdb2037705221,
title = {Jev-DLC: Decision-Level Continual Learning from Typed Feedback — arXiv:2610.31521},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.31521},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_db2037705221; sha256 ee19a3c5057d43cc1c2e3aeca64be0d4fdcfcbf680f8c19472c253bb34aec23e},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.31521. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Individual preferences often become visible only after deployment, when a user accepts one decision or revokes it in favor of another. Jev-style typed interfaces make this feedback explicit by identifying the selected action and, under revocation, the decision it replaces. We study how these consequences persist across requests as Decision-Level Continual Learning from Typed Feedback (Jev-DLC). Jev-DLC treats each correction as both evidence about a recurring action identity and a directed relation between the preferred and rejected choices. It preserves these signals in complementary bounded channels above a frozen scorer and combines their scores to shape the next decision. The method retains no raw interaction history, adds no scorer call, and performs no runtime language-model backward pass. We also introduce TCPA-Bench, a chronological suite that credits a correction only through its effect on later decisions. On TCPA-Repeat, Jev-DLC reaches 44.83% user-macro accuracy overall, 2.43 points above Recent-4 history replay. After at least two earlier feedback events, it reaches 56.07%, a 7.54-point margin over the strongest reported comparison at this depth. These results show how explicit typed corrections can become compact causal state for continual personalization. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2610.31521 — 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 2026-10-25T20:47:56.941Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).