Tracing Relational Knowledge Recall in Large Language Models

ArXi:2604.19934v1 Announce Type: new We study how large language models recall relational knowledge during text generation, with a focus on identifying latent representations suitable for relation classification via linear probes. Prior work shows how attention heads and MLPs interact to resolve subject, predicate, and object, but it remains unclear which representations faithful linear relation classification and why some relation types are easier to capture linearly than others.