https://github.com/ICTMCG/LLM-for-misinformation-research
Paper list of misinformation research using (multi-modal) large language models, i.e., (M)LLMs.
https://github.com/ICTMCG/LLM-for-misinformation-research
fact-checking fact-verification fake-news-detection large-language-models misinformation paper-list rumor-detection
Last synced: 3 months ago
JSON representation
Paper list of misinformation research using (multi-modal) large language models, i.e., (M)LLMs.
- Host: GitHub
- URL: https://github.com/ICTMCG/LLM-for-misinformation-research
- Owner: ICTMCG
- License: mit
- Created: 2024-05-09T01:20:59.000Z (12 months ago)
- Default Branch: main
- Last Pushed: 2024-12-08T09:56:07.000Z (5 months ago)
- Last Synced: 2024-12-08T10:26:45.279Z (5 months ago)
- Topics: fact-checking, fact-verification, fake-news-detection, large-language-models, misinformation, paper-list, rumor-detection
- Homepage:
- Size: 229 KB
- Stars: 159
- Watchers: 7
- Forks: 7
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# LLM-for-misinformation-research
A curated paper list of misinformation research using (multi-modal) large language models, i.e., (M)LLMs.
## Methods for Detection and Verification
### As an Information/Feature Provider, Data Generator, and Analyzer
> An LLM can be seen as a (sometimes not reliable) knowledge provider, an experienced expert in specific areas, and a relatively cheap data generator (compared with collecting from the real world). For example, LLMs could be a good analyzer of social commonsense/conventions.
- **Cheap-fake Detection with LLM using Prompt Engineering**[[paper]](https://arxiv.org/abs/2306.02776)  
- **Faking Fake News for Real Fake News Detection: Propaganda-Loaded Training Data Generation**[[paper]](https://doi.org/10.18653/v1/2023.acl-long.815)  
- **Bad Actor, Good Advisor: Exploring the Role of Large Language Models in Fake News Detection**[[paper]](https://ojs.aaai.org/index.php/AAAI/article/view/30214)  
- **Analysis of Disinformation and Fake News Detection Using Fine-Tuned Large Language Model**[[paper]](https://arxiv.org/abs/2309.04704)  
- **Detecting Misinformation with LLM-Predicted Credibility Signals and Weak Supervision**[[paper]](https://arxiv.org/abs/2309.07601)  
- **FakeGPT: Fake News Generation, Explanation and Detection of Large Language Model**[[paper]](https://arxiv.org/abs/2310.05046)  
- **Fighting Fire with Fire: The Dual Role of LLMs in Crafting and Detecting Elusive Disinformation**[[paper]](https://aclanthology.org/2023.emnlp-main.883/)  
- **Language Models Hallucinate, but May Excel at Fact Verification**[[paper]](https://arxiv.org/abs/2310.14564)  
- **Clean-label Poisoning Attack against Fake News Detection Models**[[paper]](https://doi.org/10.1109/BigData59044.2023.10386777)  
- **Rumor Detection on Social Media with Crowd Intelligence and ChatGPT-Assisted Networks**[[paper]](https://doi.org/10.18653/v1/2023.emnlp-main.347)  
- **LLMs are Superior Feedback Providers: Bootstrapping Reasoning for Lie Detection with Self-Generated Feedback**[[paper]](https://tanushreebanerjee.github.io/pdfs/diplomacy_main.pdf) 
- **Can Large Language Models Detect Rumors on Social Media?**[[paper]](https://arxiv.org/abs/2402.03916)  
- **TELLER: A Trustworthy Framework for Explainable, Generalizable and Controllable Fake News Detection**[[paper]](https://arxiv.org/abs/2402.07776)  
- **DELL: Generating Reactions and Explanations for LLM-Based Misinformation Detection**[[paper]](https://arxiv.org/abs/2402.10426)  
- **Enhancing large language model capabilities for rumor detection with Knowledge-Powered Prompting**[[paper]](https://doi.org/10.1016/j.engappai.2024.108259)  
- **An Implicit Semantic Enhanced Fine-Grained Fake News Detection Method Based on Large Language Model**[[paper]](https://dx.doi.org/10.7544/issn1000-1239.202330967)  
- **RumorLLM: A Rumor Large Language Model-Based Fake-News-Detection Data-Augmentation Approach**[[paper]](https://doi.org/10.3390/app14083532)  
- **Explainable Fake News Detection With Large Language Model via Defense Among Competing Wisdom**[[paper]](https://doi.org/10.1145/3589334.3645471)  
- **Message Injection Attack on Rumor Detection under the Black-Box Evasion Setting Using Large Language Model**[[paper]](https://doi.org/10.1145/3589334.3648139)  
- **Towards Robust Evidence-Aware Fake News Detection via Improving Semantic Perception**[[paper]](https://aclanthology.org/2024.lrec-main.1443/)  
- **Let Silence Speak: Enhancing Fake News Detection with Generated Comments from Large Language Models**[[paper]](https://arxiv.org/abs/2405.16631)  
- **RAEmoLLM: Retrieval Augmented LLMs for Cross-Domain Misinformation Detection Using In-Context Learning based on Emotional Information**[[paper]](https://arxiv.org/abs/2406.11093)  
- **Adversarial Style Augmentation via Large Language Model for Robust Fake News Detection**[[paper]](https://arxiv.org/abs/2406.11260)  
- **Zero-Shot Fact Verification via Natural Logic and Large Language Models**[[paper]](https://openreview.net/attachment?id=SxGFTTQwCm&name=pdf)  
- **RAGAR, Your Falsehood Radar: RAG-Augmented Reasoning for Political Fact-Checking using Multimodal Large Language Models**[[paper]](https://openreview.net/attachment?id=TNOnM4CQsl&name=pdf)  
- **FramedTruth: A Frame-Based Model Utilising Large Language Models for Misinformation Detection**[[paper]](https://doi.org/10.1007/978-981-97-4982-9_11)  
- **Enhancing Fake News Detection through Dataset Augmentation Using Large Language Models**[[Thesis]](https://ntnuopen.ntnu.no/ntnu-xmlui/bitstream/handle/11250/3154951/no.ntnu:inspera:187264004:35303025.pdf)  
- **DAAD: Dynamic Analysis and Adaptive Discriminator for Fake News Detection** [[paper]](https://arxiv.org/abs/2408.10883)  
- **CoVLM: Leveraging Consensus from Vision-Language Models for Semi-supervised Multimodal Fake News Detection** [[paper]](https://openaccess.thecvf.com/content/ACCV2024/papers/Devank_CoVLM_Leveraging_Consensus_from_Vision-Language_Models_for_Semi-supervised_Multimodal_Fake_ACCV_2024_paper.pdf)  
### As a Tool User
> Let an LLM be an agent having access to external tools like search engines, deepfake detectors, etc.
- **Fact-Checking Complex Claims with Program-Guided Reasoning**[[paper]](https://doi.org/10.18653/v1/2023.acl-long.386)  
- **Self-Checker: Plug-and-Play Modules for Fact-Checking with Large Language Models**[[paper]](https://arxiv.org/abs/2305.14623)  
- **FacTool: Factuality Detection in Generative AI -- A Tool Augmented Framework for Multi-Task and Multi-Domain Scenarios**[[paper]](https://arxiv.org/abs/2307.13528)  
- **FactLLaMA: Optimizing Instruction-Following Language Models with External Knowledge for Automated Fact-Checking**[[paper]](https://arxiv.org/abs/2309.00240)  
- **Explainable Claim Verification via Knowledge-Grounded Reasoning with Large Language Models**[[paper]](https://aclanthology.org/2023.findings-emnlp.416)  
- **Language Models Hallucinate, but May Excel at Fact Verification**[[paper]](https://arxiv.org/abs/2310.14564)  
- **Towards LLM-based Fact Verification on News Claims with a Hierarchical Step-by-Step Prompting Method**[[paper]](https://aclanthology.org/2023.ijcnlp-main.64)  
- **Evidence-based Interpretable Open-domain Fact-checking with Large Language Models**[[paper]](https://arxiv.org/abs/2312.05834)  
- **TELLER: A Trustworthy Framework for Explainable, Generalizable and Controllable Fake News Detection**[[paper]](https://arxiv.org/abs/2402.07776)  
- **LEMMA: Towards LVLM-Enhanced Multimodal Misinformation Detection with External Knowledge Augmentation**[[paper]](https://arxiv.org/abs/2402.11943)  
- **Can Large Language Models Detect Misinformation in Scientific News Reporting?**[[paper]](https://arxiv.org/abs/2402.14268)  
- **The Perils and Promises of Fact-Checking with Large Language Models**[[paper]](https://doi.org/10.3389%2Ffrai.2024.1341697)  
- **SNIFFER: Multimodal Large Language Model for Explainable Out-of-Context Misinformation Detection**[[paper]](https://arxiv.org/abs/2403.03170)  
- **Re-Search for The Truth: Multi-round Retrieval-augmented Large Language Models are Strong Fake News Detectors**[[paper]](https://arxiv.org/abs/2403.09747)  
- **MMIDR: Teaching Large Language Model to Interpret Multimodal Misinformation via Knowledge Distillation**[[paper]](https://arxiv.org/abs/2403.14171)  
- **TrumorGPT: Query Optimization and Semantic Reasoning over Networks for Automated Fact-Checking**[[paper]](https://doi.org/10.1109/CISS59072.2024.10480162)  
- **Reinforcement Retrieval Leveraging Fine-grained Feedback for Fact Checking News Claims with Black-Box LLM**[[paper]](https://aclanthology.org/2024.lrec-main.1209)  
- **Large Language Model Agent for Fake News Detection**[[paper]](https://arxiv.org/abs/2405.01593)  
- **Argumentative Large Language Models for Explainable and Contestable Decision-Making**[[paper]](https://arxiv.org/abs/2405.02079)  
- **RAEmoLLM: Retrieval Augmented LLMs for Cross-Domain Misinformation Detection Using In-Context Learning based on Emotional Information**[[paper]](https://arxiv.org/abs/2406.11093)  
- **RAGAR, Your Falsehood Radar: RAG-Augmented Reasoning for Political Fact-Checking using Multimodal Large Language Models**[[paper]](https://openreview.net/attachment?id=TNOnM4CQsl&name=pdf)  
- **Multimodal Misinformation Detection using Large Vision-Language Models**[[paper]](https://arxiv.org/abs/2407.14321)  
- **Detect, Investigate, Judge and Determine: A Novel LLM-based Framework for Few-shot Fake News Detection** [[paper]](https://arxiv.org/abs/2407.08952)  
- **LLM-Driven External Knowledge Integration Network for Rumor Detection**[[paper]](https://doi.org/10.1007/978-981-97-5678-0_1)  
- **Evidence-backed Fact Checking using RAG and Few-Shot In-Context Learning with LLMs**[[paper]](https://arxiv.org/abs/2408.12060)  
- **Web Retrieval Agents for Evidence-Based Misinformation Detection**[[paper]](https://arxiv.org/abs/2409.00009)  
- **Real-time Fake News from Adversarial Feedback**[[paper]](https://arxiv.org/abs/2410.14651)  
- **Resolving Unseen Rumors with Retrieval-Augmented Large Language Models**[[paper]](https://doi.org/10.1007/978-981-97-9440-9_25)  
- **Do not wait: Preemptive rumor detection with cooperative LLMs and accessible social context**[[paper]](https://doi.org/10.1016/j.ipm.2024.103995)  
### As a Decision Maker/Explainer
> An LLM can directly output the final prediction and (optional) explanations.
- **A Multitask, Multilingual, Multimodal Evaluation of ChatGPT on Reasoning, Hallucination, and Interactivity**[[paper]](https://aclanthology.org/2023.ijcnlp-main.45/)  
- **Large Language Models Can Rate News Outlet Credibility**[[paper]](https://arxiv.org/abs/2304.00228)  
- **Fact-Checking Complex Claims with Program-Guided Reasoning**[[paper]](https://doi.org/10.18653/v1/2023.acl-long.386)  
- **Towards Reliable Misinformation Mitigation: Generalization, Uncertainty, and GPT-4**[[paper]](https://arxiv.org/abs/2305.14928)  
- **Self-Checker: Plug-and-Play Modules for Fact-Checking with Large Language Models**[[paper]](https://arxiv.org/abs/2305.14623)  
- **News Verifiers Showdown: A Comparative Performance Evaluation of ChatGPT 3.5, ChatGPT 4.0, Bing AI, and Bard in News Fact-Checking**[[paper]](https://arxiv.org/abs/2306.17176)  
- **Analysis of Disinformation and Fake News Detection Using Fine-Tuned Large Language Model**[[paper]](https://arxiv.org/abs/2309.04704)  
- **Explainable Claim Verification via Knowledge-Grounded Reasoning withLarge Language Models**[[paper]](https://aclanthology.org/2023.findings-emnlp.416)  
- **Language Models Hallucinate, but May Excel at Fact Verification**[[paper]](https://arxiv.org/abs/2310.14564)  
- **FakeGPT: Fake News Generation, Explanation and Detection of Large Language Model**[[paper]](https://arxiv.org/abs/2310.05046)  
- **Can Large Language Models Understand Content and Propagation for Misinformation Detection: An Empirical Study**[[paper]](https://arxiv.org/abs/2311.12699)  
- **Are Large Language Models Good Fact Checkers: A Preliminary Study**[[paper]](https://arxiv.org/abs/2311.17355)  
- **A Revisit of Fake News Dataset with Augmented Fact-checking by ChatGPT**[[paper]](https://arxiv.org/abs/2312.11870)  
- **Can Large Language Models Detect Rumors on Social Media?**[[paper]](https://arxiv.org/abs/2402.03916)  
- **DELL: Generating Reactions and Explanations for LLM-Based Misinformation Detection**[[paper]](https://arxiv.org/abs/2402.10426)  
- **Assessing the Reasoning Abilities of ChatGPT in the Context of Claim Verification**[[paper]](https://arxiv.org/abs/2402.10735)  
- **LEMMA: Towards LVLM-Enhanced Multimodal Misinformation Detection with External Knowledge Augmentation**[[paper]](https://arxiv.org/abs/2402.11943)  
- **SoMeLVLM: A Large Vision Language Model for Social Media Processing**[[paper]](https://arxiv.org/abs/2402.13022)[[project]](https://somelvlm.github.io/)  
- **Can Large Language Models Detect Misinformation in Scientific News Reporting?**[[paper]](https://arxiv.org/abs/2402.14268)  
- **The Perils and Promises of Fact-Checking with Large Language Models**[[paper]](https://doi.org/10.3389%2Ffrai.2024.1341697)  
- **Potential of Large Language Models as Tools Against Medical Disinformation**[[paper]](https://doi.org/10.1001/jamainternmed.2024.0020)  
- **FakeNewsGPT4: Advancing Multimodal Fake News Detection through Knowledge-Augmented LVLMs**[[paper]](https://arxiv.org/abs/2403.01988)  
- **SNIFFER: Multimodal Large Language Model for Explainable Out-of-Context Misinformation Detection**[[paper]](https://arxiv.org/abs/2403.03170)  
- **Multimodal Large Language Models to Support Real-World Fact-Checking**[[paper]](https://arxiv.org/abs/2403.03627)  
- **MMIDR: Teaching Large Language Model to Interpret Multimodal Misinformation via Knowledge Distillation**[[paper]](https://arxiv.org/abs/2403.14171)  
- **An Implicit Semantic Enhanced Fine-Grained Fake News Detection Method Based on Large Language Model**[[paper]](https://dx.doi.org/10.7544/issn1000-1239.202330967)  
- **Explaining Misinformation Detection Using Large Language Models**[[paper]](https://doi.org/10.3390/electronics13091673)  
- **Rumour Evaluation with Very Large Language Models**[[paper]](https://arxiv.org/abs/2404.16859)  
- **Argumentative Large Language Models for Explainable and Contestable Decision-Making**[[paper]](https://arxiv.org/abs/2405.02079)  
- **Exploring the Potential of the Large Language Models (LLMs) in Identifying Misleading News Headlines**[[paper]](https://arxiv.org/abs/2405.03153)  
- **Tell Me Why: Explainable Public Health Fact-Checking with Large Language Models**[[paper]](https://arxiv.org/abs/2405.09454)  
- **Mining the Explainability and Generalization: Fact Verification Based on Self-Instruction**[[paper]](https://arxiv.org/abs/2405.12579)  
- **Reinforcement Tuning for Detecting Stances and Debunking Rumors Jointly with Large Language Models**[[paper]](https://arxiv.org/abs/2406.02143)  
- **RAEmoLLM: Retrieval Augmented LLMs for Cross-Domain Misinformation Detection Using In-Context Learning based on Emotional Information**[[paper]](https://arxiv.org/abs/2406.11093)  
- **RAGAR, Your Falsehood Radar: RAG-Augmented Reasoning for Political Fact-Checking using Multimodal Large Language Models**[[paper]](https://openreview.net/attachment?id=TNOnM4CQsl&name=pdf)  
- **Multilingual Fact-Checking using LLM**[[paper]](https://openreview.net/attachment?id=2KtL13evFm&name=pdf)  
- **Multimodal Misinformation Detection using Large Vision-Language Models**[[paper]](https://arxiv.org/abs/2407.14321)  
- **Detect, Investigate, Judge and Determine: A Novel LLM-based Framework for Few-shot Fake News Detection** [[paper]](https://arxiv.org/abs/2407.08952)  
- **Large Visual-Language Models Are Also Good Classifiers: A Study of In-Context Multimodal Fake News Detection** [[paper]](https://arxiv.org/abs/2407.12879)  
- **Silver Lining in the Fake News Cloud: Can Large Language Models Help Detect Misinformation?**[[paper]](https://doi.org/10.1109/TAI.2024.3440248)  
- **Evidence-backed Fact Checking using RAG and Few-Shot In-Context Learning with LLMs**[[paper]](https://arxiv.org/abs/2408.12060)  
- **CoVLM: Leveraging Consensus from Vision-Language Models for Semi-supervised Multimodal Fake News Detection** [[paper]](https://openaccess.thecvf.com/content/ACCV2024/papers/Devank_CoVLM_Leveraging_Consensus_from_Vision-Language_Models_for_Semi-supervised_Multimodal_Fake_ACCV_2024_paper.pdf)  
## Claim Matching and Check-worthy Claim Detection
- **Are Large Language Models Good Fact Checkers: A Preliminary Study**[[paper]](https://arxiv.org/abs/2311.17355)  
- **Claim Check-Worthiness Detection: How Well do LLMs Grasp Annotation Guidelines?**[[paper]](https://arxiv.org/abs/2404.12174)  
- **Automated Claim Matching with Large Language Models: Empowering Fact-Checkers in the Fight Against Misinformation**[[paper]](https://doi.org/10.1145/3589335.3651910)  
- **SynDy: Synthetic Dynamic Dataset Generation Framework for Misinformation Tasks**[[paper]](https://arxiv.org/abs/2405.10700)  
## Post-hoc Explanation Generation
- **Are Large Language Models Good Fact Checkers: A Preliminary Study**[[paper]](https://arxiv.org/abs/2311.17355)  
- **JustiLM: Few-shot Justification Generation for Explainable Fact-Checking of Real-world Claims**[[paper]](https://arxiv.org/abs/2401.08026)  
- **Can LLMs Produce Faithful Explanations For Fact-checking? Towards Faithful Explainable Fact-Checking via Multi-Agent Debate**[[paper]](https://arxiv.org/abs/2402.07401)  
## Other Tasks
- **[Fake News Propagation Simulation] From Skepticism to Acceptance: Simulating the Attitude Dynamics Toward Fake News**[[paper]](https://arxiv.org/abs/2403.09498)  
- **[Misinformation Correction] Correcting Misinformation on Social Media with A Large Language Model**[[paper]](https://arxiv.org/abs/2403.11169)  
- **[Fake News Data Annoatation] Enhancing Text Classification through LLM-Driven Active Learning and Human Annotation**[[paper]](https://aclanthology.org/2024.law-1.10/)  
- **[Assisting Human Fact-Checking] On the Role of Large Language Models in Crowdsourcing Misinformation Assessment**[[paper]](https://doi.org/10.1609/icwsm.v18i1.31417)  
- **[Attacking Misinformation Detection] Fake News in Sheep's Clothing: Robust Fake News Detection Against LLM-Empowered Style Attacks**[[paper]](https://doi.org/10.1145/3637528.3671977)  
- **[Attacking Misinformation Detection] Attacking Misinformation Detection Using Adversarial Examples Generated by Language Models**[[paper]](https://arxiv.org/abs/2410.20940)  
## Tutorials & Surveys & Position Papers
- **Preventing and Detecting Misinformation Generated by Large Language Models**: A tutorial about prevention and detection techniques of LLM-generated misinformation, including an introduction of recent advances of LLM-based misinformation detection. [[Webpage]](https://sigir24-llm-misinformation.github.io/) [[Slides]](https://sigir24-llm-misinformation.github.io/slides/SIGIR%202024%20Tutorial-all-version5.pdf)  
- **Large-Language-Model-Powered Agent-Based Framework for Misinformation and Disinformation Research: Opportunities and Open Challenges**: A research framework to generate customized agent-based social networks for disinformation simulations that would enable understanding and evaluating the phenomena whilst discussing open challenges.[[paper]](https://arxiv.org/abs/2310.07545)  
- **Combating Misinformation in the Age of LLMs: Opportunities and Challenges**: A survey of the opportunities (can we utilize LLMs to combat misinformation) and challenges (how to combat LLM-generated misinformation) of combating misinformation in the age of LLMs. [[Project Webpage]](https://llm-misinformation.github.io/)[[paper]](https://arxiv.org/abs/2311.05656)  
## Resources
- [**ARG**](https://github.com/ICTMCG/ARG): A Chinese & English fake news detection dataset with adding rationales generated by GPT-3.5-Turbo.
- [**MM-Soc**](https://arxiv.org/abs/2402.14154): A benchmark for multimodal language models in social media platforms, containing a misinformation detection task.