A new paper from MBZUAI researchers explores using ChatGPT to combat the spread of fake news. The researchers, including Preslav Nakov and Liangming Pan, demonstrate that ChatGPT can be used to fact-check published information. Their paper, "Fact-Checking Complex Claims with Program-Guided Reasoning," was accepted at ACL 2023. Why it matters: This research highlights the potential of large language models to address the growing challenge of misinformation, with implications for maintaining information integrity in the digital age.
EURECOM researchers developed data-driven verification methods using structured datasets to assess statistical and property claims. The approach translates text claims into SQL queries on relational databases for statistical claims. For property claims, they use knowledge graphs to verify claims and generate explanations. Why it matters: The methods aim to support fact-checkers by efficiently labeling claims with interpretable explanations, potentially combating misinformation in the region and beyond.
Iryna Gurevych from TU Darmstadt discussed challenges in using NLP for misinformation detection, highlighting the gap between current fact-checking research and real-world scenarios. Her team is working on detecting emerging misinformation topics and has constructed two corpora for fact checking using larger evidence documents. They are also collaborating with cognitive scientists to detect and respond to vaccine hesitancy using effective communication strategies. Why it matters: Addressing misinformation is crucial in the Middle East, especially regarding public health and socio-political issues, making advancements in NLP-based fact-checking highly relevant.
MBZUAI NLP master's graduate Hasan Iqbal developed OpenFactCheck, a framework for fact-checking and evaluating the factual accuracy of large language models. The framework consists of three modules: ResponseEvaluator, LLMEvaluator, and CheckerEvaluator. OpenFactCheck was published at EMNLP 2024 and accepted at NAACL 2025 and COLING 2025, with Iqbal playing an active role at COLING in Abu Dhabi. Why it matters: The development of automated fact-checking frameworks is crucial for ensuring the reliability and trustworthiness of information generated by increasingly prevalent LLMs, especially in the Arabic-speaking world.
MBZUAI researchers presented new resources at EMNLP for improving the factuality of LLMs, including a web application for fact-checking LLM-generated text and benchmarks for evaluating automated fact-checkers. They found that current automated fact-checkers miss nearly 40% of false claims generated by LLMs. The study breaks down the fact-checking process into eight tasks, including decomposition and decontextualization, to identify where systems fail. Why it matters: This work addresses a critical challenge in the deployment of LLMs by providing tools and methods for improving their reliability and trustworthiness, which is essential for widespread adoption in sensitive applications.
This paper introduces ProgramFC, a fact-checking model that decomposes complex claims into simpler sub-tasks using a library of functions. The model uses LLMs to generate reasoning programs and executes them by delegating sub-tasks, enhancing explainability and data efficiency. Experiments on fact-checking datasets demonstrate ProgramFC's superior performance compared to baseline methods, with publicly available code and data.
A new methodology emulating fact-checker criteria assesses news outlet factuality and bias using LLMs. The approach uses prompts based on fact-checking criteria to elicit and aggregate LLM responses for predictions. Experiments demonstrate improvements over baselines, with error analysis on media popularity and region, and a released dataset/code at https://github.com/mbzuai-nlp/llm-media-profiling.
The UrduFake@FIRE2021 shared task focused on fake news detection in the Urdu language, framed as a binary classification problem. 34 teams registered, with 18 submitting results and 11 providing technical reports, showcasing diverse approaches. The top-performing system utilized the stochastic gradient descent (SGD) algorithm, achieving an F-score of 0.679.