SOURCE-LINKED INTELLIGENCE

Beyond Single-Negative Preference: Multi-Negative DPO for LLM-Centric Historical Entity Linking

arXiv · AI, language, vision and robotics · article · Sep 7, 2026 · UTC

Large language models (LLMs) have recently shown promise for historical entity linking, but preference optimization for this task is often formulated with only one negative candidate per training instance. This discards information from the remaining candidates retrieved for the same mention. We introduce 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. MDPO preserves the Bradley-Terry formulation of DPO while exploiting the complete candidate set through

Read original source ↗ Open in workspace

recordType

paper

region

Global