# Generative Debunking of Climate Misinformation

arXiv: https://arxiv.org/abs/2407.05599 · HTML: https://mlsanity.com/paper/2407.05599/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 31 of its 99 references that are in the map.
- First posted on arXiv 8 Jul 2024.

## Builds on (most cited first, 30 of 31)

- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [FEVER: a large-scale dataset for Fact Extraction and VERification](https://mlsanity.com/paper/1803.05355/) (2018)
- [LLM Evaluators Recognize and Favor Their Own Generations](https://mlsanity.com/paper/2404.13076/) (2024)
- [A Survey on Automated Fact-Checking](https://mlsanity.com/paper/2108.11896/) (2021)
- [CLIMATE-FEVER: A Dataset for Verification of Real-World Climate Claims](https://mlsanity.com/paper/2012.00614/) (2020)
- [MultiFC: A Real-World Multi-Domain Dataset for Evidence-Based Fact Checking of Claims](https://mlsanity.com/paper/1909.03242/) (2019)
- [In-Context Impersonation Reveals Large Language Models' Strengths and Biases](https://mlsanity.com/paper/2305.14930/) (2023)
- [Fact-Checking Complex Claims with Program-Guided Reasoning](https://mlsanity.com/paper/2305.12744/) (2023)
- [Automated Fact-Checking for Assisting Human Fact-Checkers](https://mlsanity.com/paper/2103.07769/) (2021)
- [Pride and Prejudice: LLM Amplifies Self-Bias in Self-Refinement](https://mlsanity.com/paper/2402.11436/) (2024)
- [Towards LLM-based Fact Verification on News Claims with a Hierarchical Step-by-Step Prompting Method](https://mlsanity.com/paper/2310.00305/) (2023)
- [ClimateBert: A Pretrained Language Model for Climate-Related Text](https://mlsanity.com/paper/2110.12010/) (2021)
- [LLMs as Narcissistic Evaluators: When Ego Inflates Evaluation Scores](https://mlsanity.com/paper/2311.09766/) (2023)
- [Explainable Automated Fact-Checking: A Survey](https://mlsanity.com/paper/2011.03870/) (2020)
- [BERT for Evidence Retrieval and Claim Verification](https://mlsanity.com/paper/1910.02655/) (2019)
- [Language Models as Fact Checkers?](https://mlsanity.com/paper/2006.04102/) (2020)
- [Can LLMs Produce Faithful Explanations For Fact-checking? Towards Faithful Explainable Fact-Checking via Multi-Agent Debate](https://mlsanity.com/paper/2402.07401/) (2024)
- [ClimateGPT: Towards AI Synthesizing Interdisciplinary Research on Climate Change](https://mlsanity.com/paper/2401.09646/) (2024)
- [The Perils & Promises of Fact-checking with Large Language Models](https://mlsanity.com/paper/2310.13549/) (2023)
- [Fully Automated Fact Checking Using External Sources](https://mlsanity.com/paper/1710.00341/) (2017)
- [Logical Fallacy Detection](https://mlsanity.com/paper/2202.13758/) (2022)
- [Benchmarking the Generation of Fact Checking Explanations](https://mlsanity.com/paper/2308.15202/) (2023)
- [Multitask Instruction-based Prompting for Fallacy Recognition](https://mlsanity.com/paper/2301.09992/) (2023)
- [Assessing Large Language Models on Climate Information](https://mlsanity.com/paper/2310.02932/) (2023)
- [Conflicts, Villains, Resolutions: Towards models of Narrative Media Framing](https://mlsanity.com/paper/2306.02052/) (2023)
- [How We Refute Claims: Automatic Fact-Checking through Flaw Identification and Explanation](https://mlsanity.com/paper/2401.15312/) (2024)
- [Automatic Claim Review for Climate Science via Explanation Generation](https://mlsanity.com/paper/2107.14740/) (2021)
- [Explaining Veracity Predictions with Evidence Summarization: A Multi-Task Model Approach](https://mlsanity.com/paper/2402.06443/) (2024)
- [Augmented CARDS: A machine learning approach to identifying triggers of climate change misinformation on Twitter](https://mlsanity.com/paper/2404.15673/) (2024)

## Built on by (most cited first, 1 of 1)

- [Enhancing Debunking Effectiveness through LLM-based Personality Adaptation](https://mlsanity.com/paper/2603.09533/) (2026)

## 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.