{"slug": "llms-require-curated-context-for-reliable-political-fact-checking", "title": "LLMs require curated context for reliable political fact-checking", "summary": "A study evaluating 15 large language models from OpenAI, Google, Meta, and DeepSeek on over 6,000 political claims found that standard models performed poorly at fact-checking, with reasoning capabilities offering minimal improvement and web search providing only moderate gains. In contrast, a curated retrieval-augmented generation system using PolitiFact summaries improved macro F1 scores by 233% on average. The findings indicate that automated political fact-checking requires access to curated, high-quality context rather than relying on reasoning or web search alone.", "body_md": "# Computer Science > Computation and Language\n\n[Submitted on 24 Nov 2025]\n\n# Title:Large Language Models Require Curated Context for Reliable Political Fact-Checking -- Even with Reasoning and Web Search\n\n[View PDF](/pdf/2511.18749)\n\nAbstract:Large language models (LLMs) have raised hopes for automated end-to-end fact-checking, but prior studies report mixed results. As mainstream chatbots increasingly ship with reasoning capabilities and web search tools -- and millions of users already rely on them for verification -- rigorous evaluation is urgent. We evaluate 15 recent LLMs from OpenAI, Google, Meta, and DeepSeek on more than 6,000 claims fact-checked by PolitiFact, comparing standard models with reasoning- and web-search variants. Standard models perform poorly, reasoning offers minimal benefits, and web search provides only moderate gains, despite fact-checks being available on the web. In contrast, a curated RAG system using PolitiFact summaries improved macro F1 by 233% on average across model variants. These findings suggest that giving models access to curated high-quality context is a promising path for automated fact-checking.\n\n## Submission history\n\nFrom: Matthew R. DeVerna [[view email](/show-email/fc771b32/2511.18749)]\n\n**[v1]** Mon, 24 Nov 2025 04:22:32 UTC (479 KB)\n\n### Current browse context:\n\ncs.CL\n\n### References & Citations\n\nLoading...\n\n# Bibliographic and Citation Tools\n\nBibliographic Explorer\n\n*(*[What is the Explorer?](https://info.arxiv.org/labs/showcase.html#arxiv-bibliographic-explorer))\nConnected Papers\n\n*(*[What is Connected Papers?](https://www.connectedpapers.com/about))\nLitmaps\n\n*(*[What is Litmaps?](https://www.litmaps.co/))\nscite Smart Citations\n\n*(*[What are Smart Citations?](https://www.scite.ai/))# Code, Data and Media Associated with this Article\n\nalphaXiv\n\n*(*[What is alphaXiv?](https://alphaxiv.org/))\nCatalyzeX Code Finder for Papers\n\n*(*[What is CatalyzeX?](https://www.catalyzex.com))\nDagsHub\n\n*(*[What is DagsHub?](https://dagshub.com/))\nGotit.pub\n\n*(*[What is GotitPub?](http://gotit.pub/faq))\nHugging Face\n\n*(*[What is Huggingface?](https://huggingface.co/huggingface))\nScienceCast\n\n*(*[What is ScienceCast?](https://sciencecast.org/welcome))# Demos\n\n# Recommenders and Search Tools\n\nInfluence Flower\n\n*(*[What are Influence Flowers?](https://influencemap.cmlab.dev/))\nCORE Recommender\n\n*(*[What is CORE?](https://core.ac.uk/services/recommender))# arXivLabs: experimental projects with community collaborators\n\narXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.\n\nBoth individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.\n\nHave an idea for a project that will add value for arXiv's community? [ Learn more about arXivLabs](https://info.arxiv.org/labs/index.html).", "url": "https://wpnews.pro/news/llms-require-curated-context-for-reliable-political-fact-checking", "canonical_source": "https://arxiv.org/abs/2511.18749", "published_at": "2026-05-25 23:24:36+00:00", "updated_at": "2026-05-25 23:37:28.674312+00:00", "lang": "en", "topics": ["large-language-models", "natural-language-processing", "ai-safety", "ai-policy", "ai-research"], "entities": ["OpenAI", "Google", "Meta", "DeepSeek", "PolitiFact", "Matthew R. DeVerna"], "alternates": {"html": "https://wpnews.pro/news/llms-require-curated-context-for-reliable-political-fact-checking", "markdown": "https://wpnews.pro/news/llms-require-curated-context-for-reliable-political-fact-checking.md", "text": "https://wpnews.pro/news/llms-require-curated-context-for-reliable-political-fact-checking.txt", "jsonld": "https://wpnews.pro/news/llms-require-curated-context-for-reliable-political-fact-checking.jsonld"}}