Yangyang Feng, Jianle Gan, Zhuoyan Feng, Chengwei Qin · 2026 · arXiv (Cornell University)
DOI: 10.48550/arxiv.2610.31521 · cited by 0 works (OpenAlex) · open-access PDF
व्यक्तिगत प्राथमिकताएं अक्सर तैनाती के बाद ही दिखाई देती हैं, जब एक उपयोगकर्ता एक निर्णय को स्वीकार करता है या इसे दूसरे के पक्ष में रद्द करता है। Jev-स्टाइल टाइपिंग इंटरफ़ेस इस प्रतिक्रिया को चयनित कार्रवाई की पहचान करके स्पष्ट बनाते हैं और, रद्द के तहत, यह निर्णय प्रतिस्थापन करता है। हम अध्ययन करते हैं कि इन परिणामों को निर्णय-स्तरीय स्कोरर के रूप में अनुरोधों के माध्यम से कैसे बनाए रखा जाता है (Jev-DLC)। Jev-DLC प्रत्येक सुधार को दोहराने वाली कार्रवाई पहचान और पसंदीदा और अस्वीकार किए गए विकल्पों के बीच निर्देशित संबंध दोनों के सबूत के रूप में व्यवहार करता है। यह इन सिग्नलों को एक फ्रीज स्कोर के ऊपर पूरक सीमाबद्ध चैनलों
Machine translation (Meta M2M100); the English original follows.
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.
Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese
Topics: Computer science, Action (physics), Margin (machine learning), Suite, Relation (database), Identity (music)
GET https://store.agentexchange.work/gw/papers/verify?title=...&year=... (0.003 USD), fetch this record as JSON with /gw/papers/paper?id=2610.31521, or list what it cites with /gw/papers/references?id=.... Pay per call in USDC (x402) or with a 19 USD card key for 1,000 calls. Catalogue · llms.txtSources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange