A framework distills noisy user logs into rules and preference pairs, clusters them by query and feedback, then fine-tunes either an expert adapter or a critic adapter to improve future responses.
Title resolution pending
2 Pith papers cite this work, alongside 1 external citations. Polarity classification is still indexing.
2
Pith papers citing it
1
external citations · OpenAlex
years
2026 2representative citing papers
A multi-agent multimodal system with fact-grounded adjudication and a dynamic two-tier preference graph cuts false positives in content filtering by 74.3% and nearly doubles F1-score versus text-only baselines while supporting user-driven Delta adjustments.
citing papers explorer
-
Improve Large Language Model Systems with User Logs
A framework distills noisy user logs into rules and preference pairs, clusters them by query and feedback, then fine-tunes either an expert adapter or a critic adapter to improve future responses.
-
Transparent and Controllable Recommendation Filtering via Multimodal Multi-Agent Collaboration
A multi-agent multimodal system with fact-grounded adjudication and a dynamic two-tier preference graph cuts false positives in content filtering by 74.3% and nearly doubles F1-score versus text-only baselines while supporting user-driven Delta adjustments.