{
  "schema_version": "0.6.0",
  "paper_id": "multi-dimensional-bias-analysis-llms-hierarchical-interactions",
  "page_url": "https://naser.github.io/research-publications/papers/multi-dimensional-bias-analysis-llms-hierarchical-interactions/",
  "title": "Multi-Dimensional Bias Analysis in LLMs Using Hierarchical and Interaction Models",
  "title_variants": [],
  "authors": [
    "Basil Syed",
    "Daniel Arana Charlebois",
    "Naser Ezzati-Jivan",
    "Leila Tahmooresnejad",
    "Anteneh Ayanso"
  ],
  "author_details": [
    {
      "name": "Basil Syed",
      "orcid": null,
      "profile_url": "https://dblp.org/pid/416/4167.html"
    },
    {
      "name": "Daniel Arana Charlebois",
      "orcid": null,
      "profile_url": "https://dblp.org/pid/416/4603.html"
    },
    {
      "name": "Naser Ezzati-Jivan",
      "orcid": "https://orcid.org/0000-0003-1435-6297",
      "profile_url": "https://naser.github.io/"
    },
    {
      "name": "Leila Tahmooresnejad",
      "orcid": null,
      "profile_url": "https://dblp.org/pid/156/2580.html"
    },
    {
      "name": "Anteneh Ayanso",
      "orcid": null,
      "profile_url": "https://dblp.org/pid/06/6552.html"
    }
  ],
  "publication": {
    "year": 2025,
    "venue": "AMCIS 2025, Data Science / SIG DSA (ERF)",
    "type": "conference paper",
    "publication_date": "2025",
    "online_date": null,
    "print_date": null,
    "volume": null,
    "issue": null,
    "pages": null,
    "article_number": null,
    "publisher": null,
    "issn": [],
    "isbn": [],
    "crossref_type": null
  },
  "publication_type": "conference paper",
  "status": "published_with_public_abstract",
  "canonical_source_url": "https://aisel.aisnet.org/amcis2025/data_science/sig_dsa/15/",
  "source_record_id": "multi-dimensional-bias-analysis-in-llms-using-hierarchical-and-interaction-models-aebdb1da27",
  "identifiers": {
    "doi": null
  },
  "abstract": "The official abstract describes a five-layer framework for analyzing interacting bias dimensions in large language models, with ChatGPT and Gemini used as illustrative systems and context-dependent ranking of bias dimensions.",
  "abstract_source": "AIS Electronic Library official abstract, paraphrased; full paper not obtained.",
  "abstract_available": true,
  "scholar_eligibility": {
    "eligible": false,
    "basis": "not-eligible",
    "note": "The page is a discovery record; it does not claim Google Scholar article-host eligibility."
  },
  "description": "The official abstract describes a five-layer framework for analyzing interacting bias dimensions in large language models, with ChatGPT and Gemini used as illustrative systems and context-dependent ranking of bias dimensions.",
  "evidence_level": "metadata-or-abstract-reviewed",
  "evidence": {
    "source_basis": "abstract-and-metadata-reviewed",
    "coverage": "abstract and bibliographic metadata",
    "summary_origin": "AI-assisted catalog editorial summary",
    "review_status": "catalog-reviewed; paper-author approval pending",
    "verified_on": "2026-08-09",
    "sources": [
      {
        "note": "Official AIS paper and abstract page: https://aisel.aisnet.org/amcis2025/data_science/sig_dsa/15/"
      },
      {
        "note": "DBLP identity record: https://dblp.org/rec/conf/amcis/SyedCETA25"
      },
      {
        "note": "Private evidence note: papers/multi-dimensional-bias-analysis-in-llms-using-hierarchical-and-interaction-models-aebdb1da27/pdf-evidence/notes/parallel-batch-01-multi-dimensional-bias-llm.md"
      }
    ]
  },
  "summary": {
    "core_contribution": "The abstract proposes a multi-dimensional, hierarchical view of LLM bias that accounts for direct propagation, cascading effects, and feedback loops.",
    "problem": "Single-axis bias checks can miss interactions among data, algorithmic, surface-level, operational, and societal influences.",
    "method": "At abstract level, the framework organizes analysis into five layers—Data, Algorithmic, Surface-Level, Operational, and Societal Influence—and describes context-dependent ranking of bias dimensions. The detailed statistical model and dataset are not verified.",
    "findings": "The abstract names ChatGPT and Gemini as illustrative case-study systems and claims that the framework can dynamically rank bias dimensions by context. No numeric result is asserted without the full paper.",
    "limitations": "The full PDF, complete page range, statistical procedure, data, baselines, and quantitative results were not available in this audit.",
    "future_work": "The paper-specific future-work section remains unverified and should be added after full-text retrieval."
  },
  "tags": [
    "machine-learning",
    "responsible-ai",
    "llm-evaluation"
  ],
  "keywords": [
    "LLM bias",
    "hierarchical bias analysis",
    "interaction effects",
    "ChatGPT",
    "Gemini",
    "bias dimensions",
    "data bias",
    "algorithmic bias",
    "societal bias"
  ],
  "versions": [
    {
      "id": "institutional-publication-record",
      "label": "Institutional publication record",
      "relation": "version-of-record",
      "title": "Multi-Dimensional Bias Analysis in LLMs Using Hierarchical and Interaction Models",
      "url": "https://aisel.aisnet.org/amcis2025/data_science/sig_dsa/15/",
      "pdf_url": null,
      "status": "publication_signal",
      "canonical_for_citation": true
    },
    {
      "id": "official-abstract-page",
      "label": "Official abstract page",
      "relation": "source-record",
      "title": "Multi-Dimensional Bias Analysis in LLMs Using Hierarchical and Interaction Models",
      "url": "https://aisel.aisnet.org/amcis2025/data_science/sig_dsa/15/",
      "pdf_url": null,
      "status": "public_abstract",
      "canonical_for_citation": false
    }
  ],
  "access": {
    "status": "published_with_public_abstract",
    "note": "The official AIS page verifies the paper and abstract-level contribution. The full PDF was blocked under normal access, so detailed statistics and implementation claims are not asserted.",
    "license": null
  },
  "resources": {
    "code": null,
    "data": null,
    "slides": null,
    "demo": null
  },
  "citation_guidance": {
    "when_to_cite": "Cite this paper when its specific method, evidence, or benchmark is directly relevant.",
    "points": [
      "The paper's method is directly relevant.",
      "The paper's evidence or benchmark is directly relevant."
    ],
    "canonical_version_id": "institutional-publication-record"
  },
  "provenance": {
    "metadata_verified_on": "2026-08-09",
    "metadata_source": [
      "Official AIS paper and abstract page: https://aisel.aisnet.org/amcis2025/data_science/sig_dsa/15/",
      "DBLP identity record: https://dblp.org/rec/conf/amcis/SyedCETA25",
      "Private evidence note: papers/multi-dimensional-bias-analysis-in-llms-using-hierarchical-and-interaction-models-aebdb1da27/pdf-evidence/notes/parallel-batch-01-multi-dimensional-bias-llm.md"
    ],
    "summary_written_by": "AI-assisted",
    "summary_verified_by": "metadata/abstract-grounded catalog review; full-text review and author approval pending",
    "linked_preprint_record": null,
    "author_order_note": null
  },
  "batch": {
    "phase": 2,
    "batch_label": "expanded forty-paper release",
    "status": "included_in_expanded_catalog",
    "selected_at": "2026-08-09"
  }
}