Multi-Dimensional Bias Analysis in LLMs Using Hierarchical and Interaction Models

Basil Syed; Daniel Arana Charlebois; Naser Ezzati-Jivan; Leila Tahmooresnejad; Anteneh Ayanso

2025 · AMCIS 2025, Data Science / SIG DSA (ERF)

Multi-Dimensional Bias Analysis in LLMs Using Hierarchical and Interaction Models

Basil Syed | Daniel Arana Charlebois | Naser Ezzati-Jivan | Leila Tahmooresnejad | Anteneh Ayanso

Evidence basis: abstract-and-metadata-reviewed · Review status: catalog-reviewed; paper-author approval pending

machine-learning responsible-ai llm-evaluation

LLM bias hierarchical bias analysis interaction effects ChatGPT Gemini bias dimensions data bias algorithmic bias societal bias

Core contribution: The abstract proposes a multi-dimensional, hierarchical view of LLM bias that accounts for direct propagation, cascading effects, and feedback loops.

Catalog abstract summary

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.

Source: AIS Electronic Library official abstract, paraphrased; full paper not obtained.

Problem and motivation

Single-axis bias checks can miss interactions among data, algorithmic, surface-level, operational, and societal influences.

Method and contribution

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 and evidence

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 and future directions

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.

Sources and identifiers

Institutional publication record publication_signal
Official abstract page public_abstract

When to cite this paper

Cite this paper when its specific method, evidence, or benchmark is directly relevant.

The paper's method is directly relevant.
The paper's evidence or benchmark is directly relevant.

Citation

@inproceedings{ezzatiJivan2025multidimensional,
  author = {Basil Syed and Daniel Arana Charlebois and Naser Ezzati-Jivan and Leila Tahmooresnejad and Anteneh Ayanso},
  title = {Multi-Dimensional Bias Analysis in LLMs Using Hierarchical and Interaction Models},
  year = {2025},
  booktitle = {AMCIS 2025, Data Science / SIG DSA (ERF)},
  url = {https://aisel.aisnet.org/amcis2025/data_science/sig_dsa/15/}
}

Other citation formats for Word and reference managers

Syed, B., Charlebois, D. A., Ezzati-Jivan, N., Tahmooresnejad, L., & Ayanso, A. (2025). Multi-Dimensional Bias Analysis in LLMs Using Hierarchical and Interaction Models. In AMCIS 2025, Data Science / SIG DSA (ERF). https://aisel.aisnet.org/amcis2025/data_science/sig_dsa/15/

B. Syed, D. A. Charlebois, N. Ezzati-Jivan, L. Tahmooresnejad, and A. Ayanso, "Multi-Dimensional Bias Analysis in LLMs Using Hierarchical and Interaction Models," in AMCIS 2025, Data Science / SIG DSA (ERF), 2025, [Online]. Available: https://aisel.aisnet.org/amcis2025/data_science/sig_dsa/15/

Readable Markdown record · JSON record · Download RIS