SOURCE-LINKED INTELLIGENCE

Event Interaction in Low-Rank Bottlenecks for Temporal Relation Extraction

arXiv · AI, language, vision and robotics · article · Sep 6, 2026 · UTC

Temporal relation extraction determines whether an event occurs before, after, or simultaneously with another event, and therefore relies on accurately modeling how the two events interact. Mainstream systems achieve this by concatenating event spans or using shallow fusion, which works well when all model parameters are trainable. However, in parameter-efficient fine-tuning, low-rank bottlenecks restrict information flow and prevent these interaction signals from passing through, leading to clear performance drops. To address this limitation, we propose a theoretically grounded architecture,

Read original source ↗ Open in workspace

recordType

paper

region

Global