LLM-based Atomic Propositions help weak extractors: Evaluation of a Propositioner for triplet extraction

• URL: http://arxiv.org/abs/2604.02866v1
• Date: Fri, 03 Apr 2026 08:31:22 GMT
• Title: LLM-based Atomic Propositions help weak extractors: Evaluation of a Propositioner for triplet extraction
• Abstract summary: We introduce MPropositionneur-V2, a small multilingual model covering six European languages.<n> Experiments on SMiLER, FewRel, DocRED and CaRB show that atomic propositions benefit weaker extractors.<n>For stronger LLMs, a fallback combination strategy recovers entity recall losses while preserving the gains in relation extraction.
• Score: 6.356031718676497
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Knowledge Graph construction from natural language requires extracting structured triplets from complex, information-dense sentences. In this paper, we investigate if the decomposition of text into atomic propositions (minimal, semantically autonomous units of information) can improve the triplet extraction. We introduce MPropositionneur-V2, a small multilingual model covering six European languages trained by knowledge distillation from Qwen3-32B into a Qwen3-0.6B architecture, and we evaluate its integration into two extraction paradigms: entity-centric (GLiREL) and generative (Qwen3). Experiments on SMiLER, FewRel, DocRED and CaRB show that atomic propositions benefit weaker extractors (GLiREL, CoreNLP, 0.6B models), improving relation recall and, in the multilingual setting, overall accuracy. For stronger LLMs, a fallback combination strategy recovers entity recall losses while preserving the gains in relation extraction. These results show that atomic propositions are an interpretable intermediate data structure that complements extractors without replacing them.

Related papers

• Knowledge Restoration-driven Prompt Optimization: Unlocking LLM Potential for Open-Domain Relational Triplet Extraction [4.01163688152329]
  Open mining of triplets is the foundation for structured knowledge without predefined schemas.<n>Existing methods exhibit vulnerability in ambiguity making often erroneous extraction patterns permanent.<n>We propose a Knowledge Reconstruction-driven Prompt Optimization (KRPO) framework to assist Large Language Models (LLMs) in continuously improving their extraction capabilities.
  arXiv  Detail & Related papers  (2026-01-21T14:42:13Z)
• Extractive Fact Decomposition for Interpretable Natural Language Inference in one Forward Pass [4.990228412613982]
  JEDI is an encoder-only architecture that jointly performs atomic fact decomposition and interpretable inference.<n>To facilitate training, we produce a large corpus of synthetic rationales covering multiple NLI benchmarks.<n>Our findings show that interpretability and robust generalization in NLI can be realized using encoder-only architectures and synthetic rationales.
  arXiv  Detail & Related papers  (2025-09-23T11:30:42Z)
• AtomR: Atomic Operator-Empowered Large Language Models for Heterogeneous Knowledge Reasoning [49.24235059299745]
  We introduce AtomR, a framework for large language models to conduct accurate heterogeneous knowledge reasoning at the atomic level.<n>AtomR decomposes a complex question into a reasoning tree where each leaf node corresponds to an atomic knowledge operator.<n>In the reasoning execution stage, AtomR executes each atomic knowledge operator, which flexibly selects, retrieves, and operates atomic level knowledge from heterogeneous sources.
  arXiv  Detail & Related papers  (2024-11-25T15:35:51Z)
• Improving Recall of Large Language Models: A Model Collaboration Approach for Relational Triple Extraction [44.716502690026026]
  Relation triple extraction, which outputs a set of triples from long sentences, plays a vital role in knowledge acquisition. Large language models can accurately extract triples from simple sentences through few-shot learning or fine-tuning when given appropriate instructions. In this paper, we design an evaluation-filtering framework that integrates large language models with small models for relational triple extraction tasks.
  arXiv  Detail & Related papers  (2024-04-15T09:03:05Z)
• TriSum: Learning Summarization Ability from Large Language Models with Structured Rationale [66.01943465390548]
  We introduce TriSum, a framework for distilling large language models' text summarization abilities into a compact, local model. Our method enhances local model performance on various benchmarks. It also improves interpretability by providing insights into the summarization rationale.
  arXiv  Detail & Related papers  (2024-03-15T14:36:38Z)
• Enriching Relation Extraction with OpenIE [70.52564277675056]
  Relation extraction (RE) is a sub-discipline of information extraction (IE) In this work, we explore how recent approaches for open information extraction (OpenIE) may help to improve the task of RE. Our experiments over two annotated corpora, KnowledgeNet and FewRel, demonstrate the improved accuracy of our enriched models.
  arXiv  Detail & Related papers  (2022-12-19T11:26:23Z)
• Modeling Multi-Granularity Hierarchical Features for Relation Extraction [26.852869800344813]
  We propose a novel method to extract multi-granularity features based solely on the original input sentences. We show that effective structured features can be attained even without external knowledge.
  arXiv  Detail & Related papers  (2022-04-09T09:44:05Z)
• RelationPrompt: Leveraging Prompts to Generate Synthetic Data for Zero-Shot Relation Triplet Extraction [65.4337085607711]
  We introduce the task setting of Zero-Shot Relation Triplet Extraction (ZeroRTE) Given an input sentence, each extracted triplet consists of the head entity, relation label, and tail entity where the relation label is not seen at the training stage. We propose to synthesize relation examples by prompting language models to generate structured texts.
  arXiv  Detail & Related papers  (2022-03-17T05:55:14Z)
• Integrating diverse extraction pathways using iterative predictions for Multilingual Open Information Extraction [11.344977846840747]
  We propose a neural multilingual OpenIE system that iteratively extracts triples by conditioning extractions on different elements of the triple. MiLIE outperforms SOTA systems on multiple languages ranging from Chinese to Galician thanks to it's ability of combining multiple extraction pathways.
  arXiv  Detail & Related papers  (2021-10-15T15:19:11Z)
• Contrastive Triple Extraction with Generative Transformer [72.21467482853232]
  We introduce a novel model, contrastive triple extraction with a generative transformer. Specifically, we introduce a single shared transformer module for encoder-decoder-based generation. To generate faithful results, we propose a novel triplet contrastive training object.
  arXiv  Detail & Related papers  (2020-09-14T05:29:24Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.