{
  "abstract": "Large language models (LLMs) produce fluent but factually incorrect statements, known as hallucinations, which are risky in medicine, law and finance. Retrieval-augmented generation (RAG) conditions the input but does not check the output, whereas post-generation verifiers check the output but do not shape generation. We describe a two-layer framework that requires no fine-tuning of the base LLM. A Pre-Generation Control Layer (PGCL) classifies each query by domain and risk, retrieves evidence for high-risk queries, builds a constrained prompt and sets a risk-dependent decoding temperature. A Post-Generation Verification Layer (PGVL) splits the answer into atomic claims, scores each against a hierarchical Tree-RAG index with an LLM judge and a retrieval-similarity signal, and compares the resulting TruthScore with a threshold conditioned on the semantic entropy of sampled answers. Failing claims are handled by a Surgical Self-Correction Loop. We report a small pilot (50 HotpotQA and 25 TruthfulQA questions, Llama-3.3-70B) and, mainly, what it reveals. For 86% of verified claims no evidence was retrieved, so the judge largely assessed its own output. On identical claims, the entropy-conditioned threshold changed 1.6-9.9% of accept decisions, all toward rejection. Of 120 rejected claims, 85 ended as \"cannot verify\" and only 7 of 30 genuine rewrites passed re-verification. The gold HotpotQA answer appeared in 8 of 50 answers before verification and 9 of 50 after. We therefore find no measurable improvement in answer correctness, and we document confounds (a shared fact memory, unstable risk classification, run-to-run variance) that future evaluations must control.",
  "abstract_shown": true,
  "affiliations": [
    "Khwopa College of Engineering"
  ],
  "article_type": null,
  "arxiv": null,
  "author_total": 3,
  "authors": [
    {
      "affs": [
        0
      ],
      "name": "Anish Baral"
    },
    {
      "affs": [
        0
      ],
      "name": "Bijay Kadariya"
    },
    {
      "affs": [
        0
      ],
      "name": "Sushil Sharma"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/7bv7kge4xhqez.bib",
  "cited_by": 0,
  "doi": "10.5281/zenodo.23616052",
  "fulltext_url": null,
  "id": "7bv7kge4xhqez",
  "issns": [],
  "landing_url": "https://zenodo.org/records/23616052",
  "language": "eng",
  "licence": "CC-BY-4.0",
  "licence_label": "CC BY 4.0",
  "licence_source": "article",
  "licence_url": "https://creativecommons.org/licenses/by/4.0/",
  "metadata_licence": null,
  "native_subjects": [],
  "openalex": null,
  "pdf_url": "https://zenodo.org/api/records/23616052/files/llm_hallucination_mitigation.pdf/content",
  "pmcid": null,
  "pmid": null,
  "published": "2026-10-24",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/7bv7kge4xhqez.ris",
  "sources": [
    {
      "first_seen": "2026-11-07T12:20:31Z",
      "native_id": "23616052",
      "source": "zenodo",
      "url": "https://zenodo.org/records/23616052"
    }
  ],
  "subjects": [],
  "title": "A Dual-Layer Framework for LLM Hallucination Mitigation: Design and Preliminary Evaluation",
  "title_text": "A Dual-Layer Framework for LLM Hallucination Mitigation: Design and Preliminary Evaluation",
  "type": "preprint",
  "updated_at": "2026-11-07T12:20:31Z",
  "url": "https://research.draconitic.com/paper/7bv7kge4xhqez",
  "venue": "Zenodo",
  "versions": []
}