A Review of the Evolution of Bias Detection Pathways and Fairness Evaluation Dilemmas in Large Language Models: From Surface-Level Auditing to Mechanism-Driven Contextualized Evaluation
Journal of Intelligence and Knowledge Engineering · 2026-09 · 4 (3) · 54-66
DOI: 10.62517/jike.202604307 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Intelligence and Knowledge Engineering, 2026-09. Verfasst von Bowen Deng. Die Arbeit nennt 38 Literaturangaben.
Abstract (Originalsprache)
As large language models (LLMs) become deeply integrated into various sectors of society, their potential algorithmic bias and unfairness have emerged as core risks constraining safe deployment. From the distinctive perspective of the "evolution of detection pathways," this review systematically examines the transition of LLM bias evaluation from early surface-level output auditing to mechanism-driven contextualized evaluation. First, it develops a comprehensive taxonomy covering endogenous and exogenous bias, as well as representational and allocational harms, and compares the fundamental differences between LLMs and traditional NLP systems in how bias is manifested. Second, it analyzes five core detection pathways-surface-level output auditing, counterfactual consistency testing, internal mechanism analysis, attitude probing, and adversarial elicitation-in terms of their measurement dimensions, explanatory power, and limitations. Through analysis of CBBQ, TWBias, and cross-cultural benchmarks, this review identifies three major gaps in current evaluation infrastructure: cultural coverage, dynamic interaction, and harm linkage. The findings show that a significant "harm gap" exists between detection scores and real-world social harm, and that there is a deep circularity challenge between detection methods and definitions of bias. Finally, this review proposes future research directions, including the construction of a layered bias ontology, a tiered fairness evaluation system, and full-lifecycle monitoring, thereby providing theoretical support for building a more inclusive and culturally responsive AI governance framework.
Zitieren
APA
Deng, B. (2026). A Review of the Evolution of Bias Detection Pathways and Fairness Evaluation Dilemmas in Large Language Models: From Surface-Level Auditing to Mechanism-Driven Contextualized Evaluation. Journal of Intelligence and Knowledge Engineering, 4(3), 54-66. https://doi.org/10.62517/jike.202604307
Vancouver
Deng B. A Review of the Evolution of Bias Detection Pathways and Fairness Evaluation Dilemmas in Large Language Models: From Surface-Level Auditing to Mechanism-Driven Contextualized Evaluation. Journal of Intelligence and Knowledge Engineering. 2026;4(3):54-66. doi:10.62517/jike.202604307
BibTeX
@article{Deng2026,
author = {Deng, Bowen},
title = {A Review of the Evolution of Bias Detection Pathways and Fairness Evaluation Dilemmas in Large Language Models: From Surface-Level Auditing to Mechanism-Driven Contextualized Evaluation},
journal = {Journal of Intelligence and Knowledge Engineering},
year = {2026},
volume = {4},
number = {3},
pages = {54--66},
doi = {10.62517/jike.202604307}
}
EUVIMED