@inproceedings{petcu-etal-2025-comprehensive,
title = "A Comprehensive Taxonomy of Negation for {NLP} and Neural Retrievers",
author = "Petcu, Roxana and
Bhargav, Samarth and
de Rijke, Maarten and
Kanoulas, Evangelos",
editor = "Christodoulopoulos, Christos and
Chakraborty, Tanmoy and
Rose, Carolyn and
Peng, Violet",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2025",
month = nov,
year = "2025",
address = "Suzhou, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.findings-emnlp.839/",
doi = "10.18653/v1/2025.findings-emnlp.839",
pages = "15511--15533",
ISBN = "979-8-89176-335-7",
abstract = "Understanding and solving complex reasoning tasks is vital for addressing the information needs of a user. Although dense neural models learn contextualised embeddings, they underperform on queries containing negation. To understand this phenomenon, we study negation in traditional neural information retrieval and LLM-based models. We (1) introduce a taxonomy of negation that derives from philosophical, linguistic, and logical definitions; (2) generate two benchmark datasets that can be used to evaluate the performance of neural information retrieval models and to fine-tune models for a more robust performance on negation; and (3) propose a logic-based classification mechanism that can be used to analyze the performance of retrieval models on existing datasets. Our taxonomy produces a balanced data distribution over negation types, providing a better training setup that leads to faster convergence on the NevIR dataset. Moreover, we propose a classification schema that reveals the coverage of negation types in existing datasets, offering insights into the factors that might affect the generalization of fine-tuned models on negation. Our code is publicly available on GitHub, and the datasets are available on HuggingFace."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="petcu-etal-2025-comprehensive">
<titleInfo>
<title>A Comprehensive Taxonomy of Negation for NLP and Neural Retrievers</title>
</titleInfo>
<name type="personal">
<namePart type="given">Roxana</namePart>
<namePart type="family">Petcu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Samarth</namePart>
<namePart type="family">Bhargav</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maarten</namePart>
<namePart type="family">de Rijke</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Evangelos</namePart>
<namePart type="family">Kanoulas</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2025</title>
</titleInfo>
<name type="personal">
<namePart type="given">Christos</namePart>
<namePart type="family">Christodoulopoulos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tanmoy</namePart>
<namePart type="family">Chakraborty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Carolyn</namePart>
<namePart type="family">Rose</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Violet</namePart>
<namePart type="family">Peng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Suzhou, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-335-7</identifier>
</relatedItem>
<abstract>Understanding and solving complex reasoning tasks is vital for addressing the information needs of a user. Although dense neural models learn contextualised embeddings, they underperform on queries containing negation. To understand this phenomenon, we study negation in traditional neural information retrieval and LLM-based models. We (1) introduce a taxonomy of negation that derives from philosophical, linguistic, and logical definitions; (2) generate two benchmark datasets that can be used to evaluate the performance of neural information retrieval models and to fine-tune models for a more robust performance on negation; and (3) propose a logic-based classification mechanism that can be used to analyze the performance of retrieval models on existing datasets. Our taxonomy produces a balanced data distribution over negation types, providing a better training setup that leads to faster convergence on the NevIR dataset. Moreover, we propose a classification schema that reveals the coverage of negation types in existing datasets, offering insights into the factors that might affect the generalization of fine-tuned models on negation. Our code is publicly available on GitHub, and the datasets are available on HuggingFace.</abstract>
<identifier type="citekey">petcu-etal-2025-comprehensive</identifier>
<identifier type="doi">10.18653/v1/2025.findings-emnlp.839</identifier>
<location>
<url>https://aclanthology.org/2025.findings-emnlp.839/</url>
</location>
<part>
<date>2025-11</date>
<extent unit="page">
<start>15511</start>
<end>15533</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Comprehensive Taxonomy of Negation for NLP and Neural Retrievers
%A Petcu, Roxana
%A Bhargav, Samarth
%A de Rijke, Maarten
%A Kanoulas, Evangelos
%Y Christodoulopoulos, Christos
%Y Chakraborty, Tanmoy
%Y Rose, Carolyn
%Y Peng, Violet
%S Findings of the Association for Computational Linguistics: EMNLP 2025
%D 2025
%8 November
%I Association for Computational Linguistics
%C Suzhou, China
%@ 979-8-89176-335-7
%F petcu-etal-2025-comprehensive
%X Understanding and solving complex reasoning tasks is vital for addressing the information needs of a user. Although dense neural models learn contextualised embeddings, they underperform on queries containing negation. To understand this phenomenon, we study negation in traditional neural information retrieval and LLM-based models. We (1) introduce a taxonomy of negation that derives from philosophical, linguistic, and logical definitions; (2) generate two benchmark datasets that can be used to evaluate the performance of neural information retrieval models and to fine-tune models for a more robust performance on negation; and (3) propose a logic-based classification mechanism that can be used to analyze the performance of retrieval models on existing datasets. Our taxonomy produces a balanced data distribution over negation types, providing a better training setup that leads to faster convergence on the NevIR dataset. Moreover, we propose a classification schema that reveals the coverage of negation types in existing datasets, offering insights into the factors that might affect the generalization of fine-tuned models on negation. Our code is publicly available on GitHub, and the datasets are available on HuggingFace.
%R 10.18653/v1/2025.findings-emnlp.839
%U https://aclanthology.org/2025.findings-emnlp.839/
%U https://doi.org/10.18653/v1/2025.findings-emnlp.839
%P 15511-15533
Markdown (Informal)
[A Comprehensive Taxonomy of Negation for NLP and Neural Retrievers](https://aclanthology.org/2025.findings-emnlp.839/) (Petcu et al., Findings 2025)
ACL