Enhanced Reasoning for Biomedical Document-Level Relation Extraction via a Novel Cascade Language Model Framework

ACL ARR 2026 January Submission1780 Authors

Keywords: document-level relation extraction, language model

Abstract: Biomedical document-level relation extraction poses significant challenges beyond sentence-level tasks, as it necessitates the integration of evidence from entire documents and the ability for coherent cross-sentence reasoning. While pretrained language models (PLMs) demonstrate efficiency in handling local contexts, they often struggle with global dependency modeling. Conversely, large language models (LLMs) exhibit strong reasoning capabilities but tend to generate hallucinations in knowledge-intensive biomedical domains. This paper introduces CoRE, a novel cascade framework that leverages the complementary strengths of PLMs and LLMs through a detect-then-rethink paradigm. The PLM serves as an efficient detector for high-confidence relations, while challenging cases are forwarded to an LLM enhanced with semantic retrieval and iterative reasoning mechanisms. Experimental results on BioRED and CDR datasets show that CoRE achieves substantial improvements over state-of-the-art baselines, validating the effectiveness of the proposed cascade paradigm for complex biomedical relation extraction.

Paper Type: Long

Research Area: Clinical and Biomedical Applications

Research Area Keywords: Information Extraction, Language Modeling, NLP Applications

Languages Studied: English

Submission Number: 1780