MoCo supplies a unified library of 26 collaboration strategies and benchmarks demonstrating average outperformance over single models in 61 percent of (model, data) pairs.
Align- ing large language models with implicit preferences from user-generated content.arXiv preprint arXiv:2506.04463
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CL 2years
2026 2representative citing papers
Preference-Paired Fine-Tuning (PFT) lets LLMs handle conflicting and dynamic individual preferences better than single-preference methods, reaching 96.6% accuracy on the new VCD dataset and 44.76% gains in user alignment with limited history.
citing papers explorer
-
Meet Dynamic Individual Preferences: Resolving Conflicting Human Value with Paired Fine-Tuning
Preference-Paired Fine-Tuning (PFT) lets LLMs handle conflicting and dynamic individual preferences better than single-preference methods, reaching 96.6% accuracy on the new VCD dataset and 44.76% gains in user alignment with limited history.