Cognitive Mirroring for DocRE: A Self-Supervised Iterative Reflection Framework with Triplet-Centric Explicit and Implicit Feedback

Large language models (LLMs) have advanced document-level relation extraction (DocRE), but DocRE is more complex than sentencelevel relation extraction (SentRE), facing challenges like diverse relation types, coreference resolution and long-distance dependencies.Traditional pipeline methods, which detect relations before generating triplets, often propagate errors and harm performance.Meanwhile, fine-tuning methods require extensive human-annotated data, and in-context learning (ICL) underperforms compared to supervised approaches.We propose an iterative reflection framework for DocRE, inspired by human nonlinear reading cognition.The framework leverages explicit and implicit relations between triplets to provide feedback for LLMs refinement.Explicit feedback uses logical rulesbased reasoning, while implicit feedback reconstructs triplets into documents for comparison.This dual-process iteration mimics human semantic cognition, enabling dynamic optimization through self-generated supervision.For the first time, this achieves zero-shot performance comparable to fully supervised models.Experiments show our method surpasses existing LLM-based approaches and matches state-ofthe-art BERT-based methods 1 .