@inproceedings{gubelmann-etal-2023-truth,
title = "When Truth Matters - Addressing Pragmatic Categories in Natural Language Inference ({NLI}) by Large Language Models ({LLM}s)",
author = "Gubelmann, Reto and
Kalouli, Aikaterini-lida and
Niklaus, Christina and
Handschuh, Siegfried",
editor = "Palmer, Alexis and
Camacho-collados, Jose",
booktitle = "Proceedings of the 12th Joint Conference on Lexical and Computational Semantics (*SEM 2023)",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.starsem-1.4",
doi = "10.18653/v1/2023.starsem-1.4",
pages = "24--39",
abstract = "In this paper, we focus on the ability of large language models (LLMs) to accommodate different pragmatic sentence types, such as questions, commands, as well as sentence fragments for natural language inference (NLI). On the commonly used notion of logical inference, nothing can be inferred from a question, an order, or an incomprehensible sentence fragment. We find MNLI, arguably the most important NLI dataset, and hence models fine-tuned on this dataset, insensitive to this fact. Using a symbolic semantic parser, we develop and make publicly available, fine-tuning datasets designed specifically to address this issue, with promising results. We also make a first exploration of ChatGPT{'}s concept of entailment.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="gubelmann-etal-2023-truth">
<titleInfo>
<title>When Truth Matters - Addressing Pragmatic Categories in Natural Language Inference (NLI) by Large Language Models (LLMs)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Reto</namePart>
<namePart type="family">Gubelmann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aikaterini-lida</namePart>
<namePart type="family">Kalouli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christina</namePart>
<namePart type="family">Niklaus</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Siegfried</namePart>
<namePart type="family">Handschuh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 12th Joint Conference on Lexical and Computational Semantics (*SEM 2023)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Alexis</namePart>
<namePart type="family">Palmer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jose</namePart>
<namePart type="family">Camacho-collados</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Toronto, Canada</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In this paper, we focus on the ability of large language models (LLMs) to accommodate different pragmatic sentence types, such as questions, commands, as well as sentence fragments for natural language inference (NLI). On the commonly used notion of logical inference, nothing can be inferred from a question, an order, or an incomprehensible sentence fragment. We find MNLI, arguably the most important NLI dataset, and hence models fine-tuned on this dataset, insensitive to this fact. Using a symbolic semantic parser, we develop and make publicly available, fine-tuning datasets designed specifically to address this issue, with promising results. We also make a first exploration of ChatGPT’s concept of entailment.</abstract>
<identifier type="citekey">gubelmann-etal-2023-truth</identifier>
<identifier type="doi">10.18653/v1/2023.starsem-1.4</identifier>
<location>
<url>https://aclanthology.org/2023.starsem-1.4</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>24</start>
<end>39</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T When Truth Matters - Addressing Pragmatic Categories in Natural Language Inference (NLI) by Large Language Models (LLMs)
%A Gubelmann, Reto
%A Kalouli, Aikaterini-lida
%A Niklaus, Christina
%A Handschuh, Siegfried
%Y Palmer, Alexis
%Y Camacho-collados, Jose
%S Proceedings of the 12th Joint Conference on Lexical and Computational Semantics (*SEM 2023)
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F gubelmann-etal-2023-truth
%X In this paper, we focus on the ability of large language models (LLMs) to accommodate different pragmatic sentence types, such as questions, commands, as well as sentence fragments for natural language inference (NLI). On the commonly used notion of logical inference, nothing can be inferred from a question, an order, or an incomprehensible sentence fragment. We find MNLI, arguably the most important NLI dataset, and hence models fine-tuned on this dataset, insensitive to this fact. Using a symbolic semantic parser, we develop and make publicly available, fine-tuning datasets designed specifically to address this issue, with promising results. We also make a first exploration of ChatGPT’s concept of entailment.
%R 10.18653/v1/2023.starsem-1.4
%U https://aclanthology.org/2023.starsem-1.4
%U https://doi.org/10.18653/v1/2023.starsem-1.4
%P 24-39
Markdown (Informal)
[When Truth Matters - Addressing Pragmatic Categories in Natural Language Inference (NLI) by Large Language Models (LLMs)](https://aclanthology.org/2023.starsem-1.4) (Gubelmann et al., *SEM 2023)
ACL