Jev-DLC: Decision-Level Continual Learning from Typed Feedback
[Sztuczna inteligencja] Autorzy: Yangyang Feng, Jianle Gan, Zhuoyan Feng i 1 więcej
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 i…
- Kategoria arxiv
- cs.AI
- Kategoria
- Sztuczna inteligencja