LLMs require curated context for reliable political fact-checking
A recent study highlights the limitations of large language models (LLMs) in political fact-checking. While reasoning capabilities and web search tools have been integrated into mainstream chatbots, their effectiveness remains questionable without curated context. The research indicates that providing LLMs with high-quality, curated information significantly enhances their fact-checking performance.
- ▪Standard models of LLMs perform poorly in political fact-checking tasks.
- ▪Reasoning capabilities offer minimal benefits, while web search provides moderate improvements.
- ▪A curated retrieval-augmented generation (RAG) system using PolitiFact summaries improved performance by 233% on average across model variants.
Hacker News (Newest) files mainly under programming. We currently carry 5,306 of its stories.
Story provenance
Source · retrieval · rights · ranking — open for full record
inspect →
Story provenance
Attribution is not the same as permission. This drawer separates discovery metadata, excerpts, WeSearch-generated summaries, reuse status, and whether the publisher receives the visit. Nothing here claims a legal grant the publisher has not made.
Record
| Original publisher | arXiv.org |
| Canonical URL | https://arxiv.org/abs/2511.18749 |
| Publication time | Mon, 25 May 2026 23:24:36 +0000 |
| Retrieval time | 2026-05-25T23:37:40.769Z |
| Last seen | 2026-05-25T23:37:40.769Z |
| Headline source | Publisher (no WeSearch rewrite) |
| Excerpt source | publisher body |
| Excerpt method | First ~120 words (~800 chars) of extracted publisher body, fair-use limited. |
| Summary | WeSearch · cerebras-chat (WeSearch summarizer) |
| Summary source text | contentText |
| Citation coverage | Summary is a WeSearch-generated derivative; primary citation is the original publisher URL. |
| Cluster | ghdDPTwO7eBP |
| Cluster logic | Grouped by semantic title/content similarity across sources within a rolling window. Same-publisher template collisions are excluded from coverage comparison. |
| Ranking reason | Story pages are not engagement-ranked. Hub feeds use recency, with optional source-diversified chronological ordering (cap consecutive stories per source). No personalized ranking. |
| Publisher visit | Yes — open original |
| Substitutes article? | No — link-out required for full text |
Rights status (four layers)
WeSearch handling by dimension
| Indexing | May the item be indexed (stored, ranked, made findable)? | Allowed |
| Snippet | May a short excerpt of the publisher's text be shown? | Allowed |
| AI summary | May WeSearch generate its own short summary of the article? | Limited |
| Retrieval / RAG | May the content be exposed for third-party retrieval-augmented generation? | Not asserted |
| Model training | May the content be used to train AI models? | Not asserted |
| Commercial reuse | May the content be reused commercially? | Not permitted |
Basis: Derived from the published RSS/Atom feed. Contact: [email protected]. Reviewed: 2026-07-24.
Opening excerpt (first ~120 words) tap to expand
Computer Science > Computation and Language arXiv:2511.18749 (cs) [Submitted on 24 Nov 2025] Title:Large Language Models Require Curated Context for Reliable Political Fact-Checking -- Even with Reasoning and Web Search Authors:Matthew R. DeVerna, Kai-Cheng Yang, Harry Yaojun Yan, Filippo Menczer View a PDF of the paper titled Large Language Models Require Curated Context for Reliable Political Fact-Checking -- Even with Reasoning and Web Search, by Matthew R. DeVerna and 3 other authors View PDF Abstract:Large language models (LLMs) have raised hopes for automated end-to-end fact-checking, but prior studies report mixed results.
…
Excerpt limited to ~120 words for fair-use compliance. The full article is at arXiv.org.
Discussion
0 commentsMore from arXiv.org
