Correcting misinformation on social media with a large language model

• URL: http://arxiv.org/abs/2403.11169v4
• Date: Tue, 3 Sep 2024 05:51:40 GMT
• Title: Correcting misinformation on social media with a large language model
• Authors: Xinyi Zhou, Ashish Sharma, Amy X. Zhang, Tim Althoff,
• Abstract summary: Real-world misinformation, often multimodal, can be misleading using diverse tactics like conflating correlation with causation. Such misinformation is severely understudied, challenging to address, and harms various social domains, particularly on social media. We propose MUSE, an LLM augmented with access to and credibility evaluation of up-to-date information.
• Score: 14.69780455372507
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Real-world misinformation, often multimodal, can be partially or fully factual but misleading using diverse tactics like conflating correlation with causation. Such misinformation is severely understudied, challenging to address, and harms various social domains, particularly on social media, where it can spread rapidly. High-quality and timely correction of misinformation that identifies and explains its (in)accuracies effectively reduces false beliefs. Despite the wide acceptance of manual correction, it is difficult to be timely and scalable. While LLMs have versatile capabilities that could accelerate misinformation correction, they struggle due to a lack of recent information, a tendency to produce false content, and limitations in addressing multimodal information. We propose MUSE, an LLM augmented with access to and credibility evaluation of up-to-date information. By retrieving evidence as refutations or supporting context, MUSE identifies and explains content (in)accuracies with references. It conducts multimodal retrieval and interprets visual content to verify and correct multimodal content. Given the absence of a comprehensive evaluation approach, we propose 13 dimensions of misinformation correction quality. Then, fact-checking experts evaluate responses to social media content that are not presupposed to be misinformation but broadly include (partially) incorrect and correct posts that may (not) be misleading. Results demonstrate MUSE's ability to write high-quality responses to potential misinformation--across modalities, tactics, domains, political leanings, and for information that has not previously been fact-checked online--within minutes of its appearance on social media. Overall, MUSE outperforms GPT-4 by 37% and even high-quality responses from laypeople by 29%. Our work provides a general methodological and evaluative framework to correct misinformation at scale.

Related papers

• MisinfoEval: Generative AI in the Era of "Alternative Facts" [50.069577397751175]
  We introduce a framework for generating and evaluating large language model (LLM) based misinformation interventions. We present (1) an experiment with a simulated social media environment to measure effectiveness of misinformation interventions, and (2) a second experiment with personalized explanations tailored to the demographics and beliefs of users. Our findings confirm that LLM-based interventions are highly effective at correcting user behavior.
  arXiv  Detail & Related papers  (2024-10-13T18:16:50Z)
• Misinformation with Legal Consequences (MisLC): A New Task Towards Harnessing Societal Harm of Misinformation [24.936670177298584]
  We take a novel angle to consolidate the definition of misinformation detection using legal issues as a measurement of societal ramifications. We introduce a new task: Misinformation with Legal Consequence (MisLC), which leverages definitions from a wide range of legal domains. We advocate a two-step dataset curation approach that utilizes crowd-sourced checkworthiness and expert evaluations of misinformation.
  arXiv  Detail & Related papers  (2024-10-04T18:00:28Z)
• Crowd Intelligence for Early Misinformation Prediction on Social Media [29.494819549803772]
  We introduce CROWDSHIELD, a crowd intelligence-based method for early misinformation prediction. We employ Q-learning to capture the two dimensions -- stances and claims. We propose MIST, a manually annotated misinformation detection Twitter corpus.
  arXiv  Detail & Related papers  (2024-08-08T13:45:23Z)
• Missci: Reconstructing Fallacies in Misrepresented Science [84.32990746227385]
  Health-related misinformation on social networks can lead to poor decision-making and real-world dangers. Missci is a novel argumentation theoretical model for fallacious reasoning. We present Missci as a dataset to test the critical reasoning abilities of large language models.
  arXiv  Detail & Related papers  (2024-06-05T12:11:10Z)
• AMMeBa: A Large-Scale Survey and Dataset of Media-Based Misinformation In-The-Wild [1.4193873432298625]
  We show the results of a two-year study using human raters to annotate online media-based misinformation. We show the rise of generative AI-based content in misinformation claims. We also show "simple" methods dominated historically, particularly context manipulations.
  arXiv  Detail & Related papers  (2024-05-19T23:05:53Z)
• The Earth is Flat? Unveiling Factual Errors in Large Language Models [89.94270049334479]
  Large Language Models (LLMs) like ChatGPT are in various applications due to their extensive knowledge from pre-training and fine-tuning. Despite this, they are prone to generating factual and commonsense errors, raising concerns in critical areas like healthcare, journalism, and education. We introduce a novel, automatic testing framework, FactChecker, aimed at uncovering factual inaccuracies in LLMs.
  arXiv  Detail & Related papers  (2024-01-01T14:02:27Z)
• Countering Misinformation via Emotional Response Generation [15.383062216223971]
  proliferation of misinformation on social media platforms (SMPs) poses a significant danger to public health, social cohesion and democracy. Previous research has shown how social correction can be an effective way to curb misinformation. We present VerMouth, the first large-scale dataset comprising roughly 12 thousand claim-response pairs.
  arXiv  Detail & Related papers  (2023-11-17T15:37:18Z)
• From Chaos to Clarity: Claim Normalization to Empower Fact-Checking [57.024192702939736]
  Claim Normalization (aka ClaimNorm) aims to decompose complex and noisy social media posts into more straightforward and understandable forms. We propose CACN, a pioneering approach that leverages chain-of-thought and claim check-worthiness estimation. Our experiments demonstrate that CACN outperforms several baselines across various evaluation measures.
  arXiv  Detail & Related papers  (2023-10-22T16:07:06Z)
• ManiTweet: A New Benchmark for Identifying Manipulation of News on Social Media [74.93847489218008]
  We present a novel task, identifying manipulation of news on social media, which aims to detect manipulation in social media posts and identify manipulated or inserted information. To study this task, we have proposed a data collection schema and curated a dataset called ManiTweet, consisting of 3.6K pairs of tweets and corresponding articles. Our analysis demonstrates that this task is highly challenging, with large language models (LLMs) yielding unsatisfactory performance.
  arXiv  Detail & Related papers  (2023-05-23T16:40:07Z)
• Adherence to Misinformation on Social Media Through Socio-Cognitive and Group-Based Processes [79.79659145328856]
  We argue that when misinformation proliferates, this happens because the social media environment enables adherence to misinformation. We make the case that polarization and misinformation adherence are closely tied.
  arXiv  Detail & Related papers  (2022-06-30T12:34:24Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.