{
  "id": 9512,
  "url": "https://doi.org/10.2196/53164",
  "title": "Hallucination Rates and Reference Accuracy of ChatGPT and Bard for Systematic Reviews: Comparative Analysis",
  "summary": "Background Large language models (LLMs) have raised both interest and concern in the academic community. They offer the potential for automating literature search and synthesis for systematic reviews but raise concerns regarding their reliability, as the tendency to generate unsupported (hallucinated) content persist. Objective The aim of the study is to assess the performance of LLMs such as ChatGPT and Bard (subsequently rebranded Gemini) to produce references in the context of scientific writ",
  "authors": "Mikaël Chelli, Jules Descamps, Vincent Lavoué, Christophe Trojani, Michel Azar, Marcel Deckert",
  "category": "research",
  "topics": null,
  "orgs": "openai,google",
  "regions": null,
  "published_at": "2024-05-22T00:00:00.000Z",
  "fetched_at": "2026-07-14T16:33:57.576Z",
  "source_slug": "openalex",
  "source_name": "OpenAlex",
  "source_homepage": "https://openalex.org",
  "ethics_ai_record_url": "https://ethics.ai/record/9512",
  "original_url": "https://doi.org/10.2196/53164",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}