Beyond Single-Negative Preference: Multi-Negative DPO for LLM-Centric Historical Entity Linking
Multi-negative direct preference optimisation (MDPO), a reference-based pairwise objective that compares the correct entity with all valid rejected candidates associated with each mention, demonstrates that incorporating all within-instance negative candidates is a simple and effective improvement for LLM-based histori...
Tien N. Nguyen, Emanuela Boros, Ahmed Hamdi et al.
· 0 citations