SOURCE-LINKED INTELLIGENCE

A Circuit for Plural Reference: How LLMs Represent and Retrieve Singular and Plural Entities

arXiv · AI, language, vision and robotics · article · Sep 3, 2026 · UTC

Coreference resolution is an important task in contextual reasoning. In this paper, we investigate the mechanism for representing and retrieving singular and plural entities for plural reference. We use a combination of mechanistic interpretability and attention pattern analysis to study the process in which LLMs predict a pronoun to refer back to previously mentioned entities. Using a range of causal intervention techniques, we find a set of attention heads that are responsible for (1) representing coreference information in the input, (2) identifying entities that form a plural reference, (3

Read original source ↗ Open in workspace

recordType

paper

region

Global