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

arXiv: https://arxiv.org/abs/2604.02866 · HTML: https://mlsanity.com/paper/2604.02866/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 22 references that are in the map.
- First posted on arXiv 3 Apr 2026.

## Builds on (most cited first, 7 of 7)

- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generation](https://mlsanity.com/paper/2305.14251/) (2023)
- [Knowledge Graphs](https://mlsanity.com/paper/2003.02320/) (2020)
- [FewRel: A Large-Scale Supervised Few-Shot Relation Classification Dataset with State-of-the-Art Evaluation](https://mlsanity.com/paper/1810.10147/) (2018)
- [Atomic Inference for NLI with Generated Facts as Atoms](https://mlsanity.com/paper/2305.13214/) (2023)
- [GLiREL -- Generalist Model for Zero-Shot Relation Extraction](https://mlsanity.com/paper/2501.03172/) (2025)
- [A Sentence Simplification System for Improving Relation Extraction](https://mlsanity.com/paper/1703.09013/) (2017)

## Built on by (most cited first, 1 of 1)

- [Can We Do Interpretable NLI with Graphs Based on Atomic Propositions?](https://mlsanity.com/paper/2609.16814/) (2026)

## Abstract (arXiv)

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.