@inproceedings{adewumi-etal-2025-limitations,
title = "On the Limitations of Large Language Models ({LLM}s): False Attribution",
author = "Adewumi, Tosin and
Habib, Nudrat and
Alkhaled, Lama and
Barney, Elisa",
editor = "Angelova, Galia and
Kunilovskaya, Maria and
Escribe, Marie and
Mitkov, Ruslan",
booktitle = "Proceedings of the 15th International Conference on Recent Advances in Natural Language Processing - Natural Language Processing in the Generative AI Era",
month = sep,
year = "2025",
address = "Varna, Bulgaria",
publisher = "INCOMA Ltd., Shoumen, Bulgaria",
url = "https://aclanthology.org/2025.ranlp-1.2/",
pages = "11--21",
abstract = "In this work, we introduce a new hallucination metric - SHI and provide insight into one important limitation of the parametric knowledge of large language models LLMs, i.e. false attribution. The task of automatic author attribution for relatively small chunks of text is an important NLP task but can be challenging. We empirically evaluate the power of 3 open SotA LLMs in zero-shot setting (Gemma-7B, Mixtral 8x7B, and LLaMA-2-13B). We acquired the top 10 most popular books of a month, according to Project Gutenberg, divided each one into equal chunks of 400 words, and prompted each LLM to predict the author. We then randomly sampled 162 chunks per book for human evaluation, based on the error margin of 7{\%} and a confidence level of 95{\%}. The average results show that Mixtral 8x7B has the highest prediction accuracy, the lowest SHI, and a Pearson{'}s correlation r of 0.724, 0.263, and -0.9996, respectively, followed by LLaMA-2-13B and Gemma-7B. However, Mixtral 8x7B suffers from high hallucinations for 3 books, rising as high as a SHI of 0.87 (in the range 0-1, where 1 is the worst). The strong negative correlation of accuracy and SHI, given by r, demonstrates the fidelity of the new hallucination metric, which may generalize to other tasks. We also show that prediction accuracies correlate positively with the frequencies of Wikipedia instances of the book titles instead of the downloads and we perform error analyses of predictions. We publicly release the annotated chunks of data and our codes to aid the reproducibility and evaluation of other models."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="adewumi-etal-2025-limitations">
<titleInfo>
<title>On the Limitations of Large Language Models (LLMs): False Attribution</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tosin</namePart>
<namePart type="family">Adewumi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nudrat</namePart>
<namePart type="family">Habib</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lama</namePart>
<namePart type="family">Alkhaled</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Elisa</namePart>
<namePart type="family">Barney</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-09</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 15th International Conference on Recent Advances in Natural Language Processing - Natural Language Processing in the Generative AI Era</title>
</titleInfo>
<name type="personal">
<namePart type="given">Galia</namePart>
<namePart type="family">Angelova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="family">Kunilovskaya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marie</namePart>
<namePart type="family">Escribe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruslan</namePart>
<namePart type="family">Mitkov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>INCOMA Ltd., Shoumen, Bulgaria</publisher>
<place>
<placeTerm type="text">Varna, Bulgaria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In this work, we introduce a new hallucination metric - SHI and provide insight into one important limitation of the parametric knowledge of large language models LLMs, i.e. false attribution. The task of automatic author attribution for relatively small chunks of text is an important NLP task but can be challenging. We empirically evaluate the power of 3 open SotA LLMs in zero-shot setting (Gemma-7B, Mixtral 8x7B, and LLaMA-2-13B). We acquired the top 10 most popular books of a month, according to Project Gutenberg, divided each one into equal chunks of 400 words, and prompted each LLM to predict the author. We then randomly sampled 162 chunks per book for human evaluation, based on the error margin of 7% and a confidence level of 95%. The average results show that Mixtral 8x7B has the highest prediction accuracy, the lowest SHI, and a Pearson’s correlation r of 0.724, 0.263, and -0.9996, respectively, followed by LLaMA-2-13B and Gemma-7B. However, Mixtral 8x7B suffers from high hallucinations for 3 books, rising as high as a SHI of 0.87 (in the range 0-1, where 1 is the worst). The strong negative correlation of accuracy and SHI, given by r, demonstrates the fidelity of the new hallucination metric, which may generalize to other tasks. We also show that prediction accuracies correlate positively with the frequencies of Wikipedia instances of the book titles instead of the downloads and we perform error analyses of predictions. We publicly release the annotated chunks of data and our codes to aid the reproducibility and evaluation of other models.</abstract>
<identifier type="citekey">adewumi-etal-2025-limitations</identifier>
<location>
<url>https://aclanthology.org/2025.ranlp-1.2/</url>
</location>
<part>
<date>2025-09</date>
<extent unit="page">
<start>11</start>
<end>21</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T On the Limitations of Large Language Models (LLMs): False Attribution
%A Adewumi, Tosin
%A Habib, Nudrat
%A Alkhaled, Lama
%A Barney, Elisa
%Y Angelova, Galia
%Y Kunilovskaya, Maria
%Y Escribe, Marie
%Y Mitkov, Ruslan
%S Proceedings of the 15th International Conference on Recent Advances in Natural Language Processing - Natural Language Processing in the Generative AI Era
%D 2025
%8 September
%I INCOMA Ltd., Shoumen, Bulgaria
%C Varna, Bulgaria
%F adewumi-etal-2025-limitations
%X In this work, we introduce a new hallucination metric - SHI and provide insight into one important limitation of the parametric knowledge of large language models LLMs, i.e. false attribution. The task of automatic author attribution for relatively small chunks of text is an important NLP task but can be challenging. We empirically evaluate the power of 3 open SotA LLMs in zero-shot setting (Gemma-7B, Mixtral 8x7B, and LLaMA-2-13B). We acquired the top 10 most popular books of a month, according to Project Gutenberg, divided each one into equal chunks of 400 words, and prompted each LLM to predict the author. We then randomly sampled 162 chunks per book for human evaluation, based on the error margin of 7% and a confidence level of 95%. The average results show that Mixtral 8x7B has the highest prediction accuracy, the lowest SHI, and a Pearson’s correlation r of 0.724, 0.263, and -0.9996, respectively, followed by LLaMA-2-13B and Gemma-7B. However, Mixtral 8x7B suffers from high hallucinations for 3 books, rising as high as a SHI of 0.87 (in the range 0-1, where 1 is the worst). The strong negative correlation of accuracy and SHI, given by r, demonstrates the fidelity of the new hallucination metric, which may generalize to other tasks. We also show that prediction accuracies correlate positively with the frequencies of Wikipedia instances of the book titles instead of the downloads and we perform error analyses of predictions. We publicly release the annotated chunks of data and our codes to aid the reproducibility and evaluation of other models.
%U https://aclanthology.org/2025.ranlp-1.2/
%P 11-21
Markdown (Informal)
[On the Limitations of Large Language Models (LLMs): False Attribution](https://aclanthology.org/2025.ranlp-1.2/) (Adewumi et al., RANLP 2025)
ACL
- Tosin Adewumi, Nudrat Habib, Lama Alkhaled, and Elisa Barney. 2025. On the Limitations of Large Language Models (LLMs): False Attribution. In Proceedings of the 15th International Conference on Recent Advances in Natural Language Processing - Natural Language Processing in the Generative AI Era, pages 11–21, Varna, Bulgaria. INCOMA Ltd., Shoumen, Bulgaria.