@inproceedings{pommeret-etal-2026-llm,
title = "{LLM}-based Atomic Propositions Help Weak Extractors: Evaluation of a Propositioner for Triplet Extraction",
author = "Pommeret, Luc and
Gerald, Thomas and
Servan, Christophe and
Ghannay, Sahar and
Paroubek, Patrick and
Rosset, Sophie",
editor = "S{\'e}rasset, Gilles and
Gkirtzou, Katerina and
Cochez, Michael and
Kalo, Jan-Christoph",
booktitle = "Proceedings of the Knowledge Graphs and Large Language Models Workshop ({KG}-{LLM}) @ {LREC}26",
month = may,
year = "2026",
address = "Palma, Mallorca (Spain)",
publisher = "ELRA Language Resources Association (ELRA)",
url = "https://aclanthology.org/2026.kallm-1.14/",
doi = "10.63317/3kna3utavhgb",
pages = "134--143",
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 \textit{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."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="pommeret-etal-2026-llm">
<titleInfo>
<title>LLM-based Atomic Propositions Help Weak Extractors: Evaluation of a Propositioner for Triplet Extraction</title>
</titleInfo>
<name type="personal">
<namePart type="given">Luc</namePart>
<namePart type="family">Pommeret</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thomas</namePart>
<namePart type="family">Gerald</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christophe</namePart>
<namePart type="family">Servan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sahar</namePart>
<namePart type="family">Ghannay</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Patrick</namePart>
<namePart type="family">Paroubek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sophie</namePart>
<namePart type="family">Rosset</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Knowledge Graphs and Large Language Models Workshop (KG-LLM) @ LREC26</title>
</titleInfo>
<name type="personal">
<namePart type="given">Gilles</namePart>
<namePart type="family">Sérasset</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Katerina</namePart>
<namePart type="family">Gkirtzou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michael</namePart>
<namePart type="family">Cochez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan-Christoph</namePart>
<namePart type="family">Kalo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Palma, Mallorca (Spain)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<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.</abstract>
<identifier type="citekey">pommeret-etal-2026-llm</identifier>
<identifier type="doi">10.63317/3kna3utavhgb</identifier>
<location>
<url>https://aclanthology.org/2026.kallm-1.14/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>134</start>
<end>143</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T LLM-based Atomic Propositions Help Weak Extractors: Evaluation of a Propositioner for Triplet Extraction
%A Pommeret, Luc
%A Gerald, Thomas
%A Servan, Christophe
%A Ghannay, Sahar
%A Paroubek, Patrick
%A Rosset, Sophie
%Y Sérasset, Gilles
%Y Gkirtzou, Katerina
%Y Cochez, Michael
%Y Kalo, Jan-Christoph
%S Proceedings of the Knowledge Graphs and Large Language Models Workshop (KG-LLM) @ LREC26
%D 2026
%8 May
%I ELRA Language Resources Association (ELRA)
%C Palma, Mallorca (Spain)
%F pommeret-etal-2026-llm
%X 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.
%R 10.63317/3kna3utavhgb
%U https://aclanthology.org/2026.kallm-1.14/
%U https://doi.org/10.63317/3kna3utavhgb
%P 134-143
Markdown (Informal)
[LLM-based Atomic Propositions Help Weak Extractors: Evaluation of a Propositioner for Triplet Extraction](https://aclanthology.org/2026.kallm-1.14/) (Pommeret et al., KaLLM 2026)
ACL