{"ID":2841599,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2511.11087","arxiv_id":"2511.11087","title":"Can LLMs Detect Their Own Hallucinations?","abstract":"Large language models (LLMs) can generate fluent responses, but sometimes hallucinate facts. In this paper, we investigate whether LLMs can detect their own hallucinations. We formulate hallucination detection as a classification task of a sentence. We propose a framework for estimating LLMs' capability of hallucination detection and a classification method using Chain-of-Thought (CoT) to extract knowledge from their parameters. The experimental results indicated that GPT-$3.5$ Turbo with CoT detected $58.2\\%$ of its own hallucinations. We concluded that LLMs with CoT can detect hallucinations if sufficient knowledge is contained in their parameters.","short_abstract":"Large language models (LLMs) can generate fluent responses, but sometimes hallucinate facts. In this paper, we investigate whether LLMs can detect their own hallucinations. We formulate hallucination detection as a classification task of a sentence. We propose a framework for estimating LLMs' capability of hallucinatio...","url_abs":"https://arxiv.org/abs/2511.11087","url_pdf":"https://arxiv.org/pdf/2511.11087v1","authors":"[\"Sora Kadotani\",\"Kosuke Nishida\",\"Kyosuke Nishida\"]","published":"2025-11-14T09:03:09Z","proceeding":"cs.CL","tasks":"[\"cs.CL\"]","methods":"[\"Large Language Model\",\"Language Model\"]","has_code":false}