mlsanityData to 7 Oct 2026

Generative Debunking of Climate Misinformation

arXiv 2407.05599 ↗First posted 8 Jul 2024cs.CL cs.CYcited by 1

Not on the map. Why?

Abstract (arXiv)

Misinformation about climate change causes numerous negative impacts, necessitating corrective responses. Psychological research has offered various strategies for reducing the influence of climate misinformation, such as the fact-myth-fallacy-fact-structure. However, practically implementing corrective interventions at scale represents a challenge. Automatic detection and correction of misinformation offers a solution to the misinformation problem. This study documents the development of large language models that accept as input a climate myth and produce a debunking that adheres to the fact-myth-fallacy-fact (``truth sandwich'') structure, by incorporating contrarian claim classification and fallacy detection into an LLM prompting framework. We combine open (Mixtral, Palm2) and proprietary (GPT-4) LLMs with prompting strategies of varying complexity. Experiments reveal promising performance of GPT-4 and Mixtral if combined with structured prompts. We identify specific challenges of debunking generation and human evaluation, and map out avenues for future work. We release a dataset of high-quality truth-sandwich debunkings, source code and a demo of the debunking system.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 31 of its 99 references that are in the map. First posted on arXiv 8 Jul 2024.

Builds on

31 of 99 references.

References · 31

  1. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,049
  2. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
  3. 2018FEVER: a large-scale dataset for Fact Extraction and VERificationcited by 1,362
  4. 2024LLM Evaluators Recognize and Favor Their Own Generationscited by 651
  5. 2021A Survey on Automated Fact-Checkingcited by 376
  6. 2020CLIMATE-FEVER: A Dataset for Verification of Real-World Climate Claimscited by 195
  7. 2019MultiFC: A Real-World Multi-Domain Dataset for Evidence-Based Fact Checking of Claimscited by 169
  8. 2023In-Context Impersonation Reveals Large Language Models' Strengths and Biasescited by 154
  9. 2023Fact-Checking Complex Claims with Program-Guided Reasoningcited by 146
  10. 2021Automated Fact-Checking for Assisting Human Fact-Checkerscited by 144
  11. 2024Pride and Prejudice: LLM Amplifies Self-Bias in Self-Refinementcited by 111
  12. 2023Towards LLM-based Fact Verification on News Claims with a Hierarchical Step-by-Step Prompting Methodcited by 97
19 more
  1. 2021ClimateBert: A Pretrained Language Model for Climate-Related Textcited by 89
  2. 2023LLMs as Narcissistic Evaluators: When Ego Inflates Evaluation Scorescited by 88
  3. 2020Explainable Automated Fact-Checking: A Surveycited by 83
  4. 2019BERT for Evidence Retrieval and Claim Verificationcited by 57
  5. 2020Language Models as Fact Checkers?cited by 51
  6. 2024Can LLMs Produce Faithful Explanations For Fact-checking? Towards Faithful Explainable Fact-Checking via Multi-Agent Debatecited by 48
  7. 2024ClimateGPT: Towards AI Synthesizing Interdisciplinary Research on Climate Changecited by 46
  8. 2023The Perils & Promises of Fact-checking with Large Language Modelscited by 31
  9. 2017Fully Automated Fact Checking Using External Sourcescited by 27
  10. 2022Logical Fallacy Detectioncited by 25
  11. 2023Benchmarking the Generation of Fact Checking Explanationscited by 25
  12. 2023Multitask Instruction-based Prompting for Fallacy Recognitioncited by 22
  13. 2023Assessing Large Language Models on Climate Informationcited by 22
  14. 2023Conflicts, Villains, Resolutions: Towards models of Narrative Media Framingcited by 14
  15. 2024How We Refute Claims: Automatic Fact-Checking through Flaw Identification and Explanationcited by 7
  16. 2021Automatic Claim Review for Climate Science via Explanation Generationcited by 4
  17. 2024Explaining Veracity Predictions with Evidence Summarization: A Multi-Task Model Approachcited by 4
  18. 2024Augmented CARDS: A machine learning approach to identifying triggers of climate change misinformation on Twittercited by 4
  19. 2024Detecting Fallacies in Climate Misinformation: A Technocognitive Approach to Identifying Misleading Argumentationcited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Enhancing Debunking Effectiveness through LLM-based Personality Adaptationcited by 0