# Relation as a Prior: A Novel Paradigm for LLM-based Document-level Relation Extraction

arXiv: https://arxiv.org/abs/2511.08143 · HTML: https://mlsanity.com/paper/2511.08143/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 27 of its 31 references that are in the map.
- First posted on arXiv 11 Nov 2025.

## Builds on (most cited first, 27 of 27)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Qwen Technical Report](https://mlsanity.com/paper/2309.16609/) (2023)
- [LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Models](https://mlsanity.com/paper/2403.13372/) (2024)
- [DocRED: A Large-Scale Document-Level Relation Extraction Dataset](https://mlsanity.com/paper/1906.06127/) (2019)
- [Document-Level Relation Extraction with Adaptive Thresholding and Localized Context Pooling](https://mlsanity.com/paper/2010.11304/) (2020)
- [Large Language Models Meet NLP: A Survey](https://mlsanity.com/paper/2405.12819/) (2024)
- [Revisiting Relation Extraction in the era of Large Language Models](https://mlsanity.com/paper/2305.05003/) (2023)
- [Cross-Sentence N-ary Relation Extraction with Graph LSTMs](https://mlsanity.com/paper/1708.03743/) (2017)
- [Double Graph Based Reasoning for Document-level Relation Extraction](https://mlsanity.com/paper/2009.13752/) (2020)
- [GPT-RE: In-context Learning for Relation Extraction using Large Language Models](https://mlsanity.com/paper/2305.02105/) (2023)
- [Revisiting DocRED -- Addressing the False Negative Problem in Relation Extraction](https://mlsanity.com/paper/2205.12696/) (2022)
- [Improved Neural Relation Detection for Knowledge Base Question Answering](https://mlsanity.com/paper/1704.06194/) (2017)
- [DREEAM: Guiding Attention with Evidence for Improving Document-Level Relation Extraction](https://mlsanity.com/paper/2302.08675/) (2023)
- [Eider: Empowering Document-level Relation Extraction with Efficient Evidence Extraction and Inference-stage Fusion](https://mlsanity.com/paper/2106.08657/) (2021)
- [Chain of Thought with Explicit Evidence Reasoning for Few-shot Relation Extraction](https://mlsanity.com/paper/2311.05922/) (2023)
- [Document-Level Relation Extraction with Sentences Importance Estimation and Focusing](https://mlsanity.com/paper/2204.12679/) (2022)
- [AutoRE: Document-Level Relation Extraction with Large Language Models](https://mlsanity.com/paper/2403.14888/) (2024)
- [Consistency Guided Knowledge Retrieval and Denoising in LLMs for Zero-shot Document-level Relation Triplet Extraction](https://mlsanity.com/paper/2401.13598/) (2024)
- [Document-level Causal Relation Extraction with Knowledge-guided Binary Question Answering](https://mlsanity.com/paper/2410.04752/) (2024)
- [Document-level Relation Extraction with Cross-sentence Reasoning Graph](https://mlsanity.com/paper/2303.03912/) (2023)
- [Semi-automatic Data Enhancement for Document-Level Relation Extraction with Distant Supervision from Large Language Models](https://mlsanity.com/paper/2311.07314/) (2023)
- [Discovering Hypernymy in Text-Rich Heterogeneous Information Network by Exploiting Context Granularity](https://mlsanity.com/paper/1909.01584/) (2019)
- [LLM with Relation Classifier for Document-Level Relation Extraction](https://mlsanity.com/paper/2408.13889/) (2024)
- [Graphical Reasoning: LLM-based Semi-Open Relation Extraction](https://mlsanity.com/paper/2405.00216/) (2024)
- [Extracting and Following Paths for Robust Relational Reasoning with Large Language Models](https://mlsanity.com/paper/2412.17963/) (2024)

## Abstract (arXiv)

Large Language Models (LLMs) have demonstrated their remarkable capabilities in document understanding. However, recent research reveals that LLMs still exhibit performance gaps in Document-level Relation Extraction (DocRE) as requiring fine-grained comprehension. The commonly adopted "extract entities then predict relations" paradigm in LLM-based methods leads to these gaps due to two main reasons: (1) Numerous unrelated entity pairs introduce noise and interfere with the relation prediction for truly related entity pairs. (2) Although LLMs have identified semantic associations between entities, relation labels beyond the predefined set are still treated as prediction errors. To address these challenges, we propose a novel Relation as a Prior (RelPrior) paradigm for LLM-based DocRE. For challenge (1), RelPrior utilizes binary relation as a prior to extract and determine whether two entities are correlated, thereby filtering out irrelevant entity pairs and reducing prediction noise. For challenge (2), RelPrior utilizes predefined relation as a prior to match entities for triples extraction instead of directly predicting relation. Thus, it avoids misjudgment caused by strict predefined relation labeling. Extensive experiments on two benchmarks demonstrate that RelPrior achieves state-of-the-art performance, surpassing existing LLM-based methods.