@inproceedings{lucas-etal-2023-fighting,
title = "Fighting Fire with Fire: The Dual Role of {LLM}s in Crafting and Detecting Elusive Disinformation",
author = "Lucas, Jason and
Uchendu, Adaku and
Yamashita, Michiharu and
Lee, Jooyoung and
Rohatgi, Shaurya and
Lee, Dongwon",
editor = "Bouamor, Houda and
Pino, Juan and
Bali, Kalika",
booktitle = "Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing",
month = dec,
year = "2023",
address = "Singapore",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.emnlp-main.883",
doi = "10.18653/v1/2023.emnlp-main.883",
pages = "14279--14305",
abstract = "Recent ubiquity and disruptive impacts of large language models (LLMs) have raised concerns about their potential to be misused (*.i.e, generating large-scale harmful and misleading content*). To combat this emerging risk of LLMs, we propose a novel {``}***Fighting Fire with Fire***{''} (F3) strategy that harnesses modern LLMs{'} generative and emergent reasoning capabilities to counter human-written and LLM-generated disinformation. First, we leverage GPT-3.5-turbo to synthesize authentic and deceptive LLM-generated content through paraphrase-based and perturbation-based prefix-style prompts, respectively. Second, we apply zero-shot in-context semantic reasoning techniques with cloze-style prompts to discern genuine from deceptive posts and news articles. In our extensive experiments, we observe GPT-3.5-turbo{'}s zero-shot superiority for both in-distribution and out-of-distribution datasets, where GPT-3.5-turbo consistently achieved accuracy at 68-72{\%}, unlike the decline observed in previous customized and fine-tuned disinformation detectors. Our codebase and dataset are available at https://github.com/mickeymst/F3.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lucas-etal-2023-fighting">
<titleInfo>
<title>Fighting Fire with Fire: The Dual Role of LLMs in Crafting and Detecting Elusive Disinformation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jason</namePart>
<namePart type="family">Lucas</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Adaku</namePart>
<namePart type="family">Uchendu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michiharu</namePart>
<namePart type="family">Yamashita</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jooyoung</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shaurya</namePart>
<namePart type="family">Rohatgi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dongwon</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Houda</namePart>
<namePart type="family">Bouamor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Juan</namePart>
<namePart type="family">Pino</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kalika</namePart>
<namePart type="family">Bali</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Singapore</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Recent ubiquity and disruptive impacts of large language models (LLMs) have raised concerns about their potential to be misused (*.i.e, generating large-scale harmful and misleading content*). To combat this emerging risk of LLMs, we propose a novel “***Fighting Fire with Fire***” (F3) strategy that harnesses modern LLMs’ generative and emergent reasoning capabilities to counter human-written and LLM-generated disinformation. First, we leverage GPT-3.5-turbo to synthesize authentic and deceptive LLM-generated content through paraphrase-based and perturbation-based prefix-style prompts, respectively. Second, we apply zero-shot in-context semantic reasoning techniques with cloze-style prompts to discern genuine from deceptive posts and news articles. In our extensive experiments, we observe GPT-3.5-turbo’s zero-shot superiority for both in-distribution and out-of-distribution datasets, where GPT-3.5-turbo consistently achieved accuracy at 68-72%, unlike the decline observed in previous customized and fine-tuned disinformation detectors. Our codebase and dataset are available at https://github.com/mickeymst/F3.</abstract>
<identifier type="citekey">lucas-etal-2023-fighting</identifier>
<identifier type="doi">10.18653/v1/2023.emnlp-main.883</identifier>
<location>
<url>https://aclanthology.org/2023.emnlp-main.883</url>
</location>
<part>
<date>2023-12</date>
<extent unit="page">
<start>14279</start>
<end>14305</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Fighting Fire with Fire: The Dual Role of LLMs in Crafting and Detecting Elusive Disinformation
%A Lucas, Jason
%A Uchendu, Adaku
%A Yamashita, Michiharu
%A Lee, Jooyoung
%A Rohatgi, Shaurya
%A Lee, Dongwon
%Y Bouamor, Houda
%Y Pino, Juan
%Y Bali, Kalika
%S Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing
%D 2023
%8 December
%I Association for Computational Linguistics
%C Singapore
%F lucas-etal-2023-fighting
%X Recent ubiquity and disruptive impacts of large language models (LLMs) have raised concerns about their potential to be misused (*.i.e, generating large-scale harmful and misleading content*). To combat this emerging risk of LLMs, we propose a novel “***Fighting Fire with Fire***” (F3) strategy that harnesses modern LLMs’ generative and emergent reasoning capabilities to counter human-written and LLM-generated disinformation. First, we leverage GPT-3.5-turbo to synthesize authentic and deceptive LLM-generated content through paraphrase-based and perturbation-based prefix-style prompts, respectively. Second, we apply zero-shot in-context semantic reasoning techniques with cloze-style prompts to discern genuine from deceptive posts and news articles. In our extensive experiments, we observe GPT-3.5-turbo’s zero-shot superiority for both in-distribution and out-of-distribution datasets, where GPT-3.5-turbo consistently achieved accuracy at 68-72%, unlike the decline observed in previous customized and fine-tuned disinformation detectors. Our codebase and dataset are available at https://github.com/mickeymst/F3.
%R 10.18653/v1/2023.emnlp-main.883
%U https://aclanthology.org/2023.emnlp-main.883
%U https://doi.org/10.18653/v1/2023.emnlp-main.883
%P 14279-14305
Markdown (Informal)
[Fighting Fire with Fire: The Dual Role of LLMs in Crafting and Detecting Elusive Disinformation](https://aclanthology.org/2023.emnlp-main.883) (Lucas et al., EMNLP 2023)
ACL