TASRIC: A Type‐Aware Semantic Retrieval Augmentation Framework With Iterative Correction for Bias Mitigation
Annals of the New York Academy of Sciences · 2026
DOI: 10.1111/nyas.70360 ↗Kurz gefasst
Fachartikel in der Zeitschrift Annals of the New York Academy of Sciences, 2026. Verfasst von Chenyang Li und 1 weiteren Autor:innen. Beteiligte Einrichtung: Faculty of Artificial Intelligence in Education, Central China Normal University, Wuhan, China. Hauptthemen laut MEDLINE: Semantics, Natural Language Processing, Information Storage and Retrieval. Die Arbeit nennt 41 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: National Social Science Fund of China.
Abstract (Originalsprache)
Gender bias in Chinese natural language processing poses significant challenges due to its high degree of metaphorical expression and strong dependence on contextual cues. Existing approaches typically rely on fixed demonstrations or one‐shot generation strategies, which may result in incomplete debiasing or loss of core semantics when handling metaphorical and long‐tail biased expressions. To address these limitations, this paper proposes a type‐aware semantic retrieval augmentation framework with iterative correction (TASRIC), a semi‐parametric generative framework for mitigating bias. First, we construct a unified fine‐grained recognizer based on adversarial training to enable robust fine‐grained bias identification. Second, we introduce a type‐aware semantic retrieval augmentation mechanism that leverages bias type information and dynamic semantic retrieval to impose contextual constraints, thereby alleviating the insufficient coverage of fixed demonstration prompts in complex metaphorical bias scenarios. Finally, an iterative correction strategy is designed to ensure general semantic preservation during the debiasing process. Experimental results demonstrate that, compared with a few‐shot ChatGPT baseline, TASRIC improves the quality of debiased text generation by 3.7% in BLEU, an n‐gram overlap metric, and 3.3% in METEOR, a metric that considers more flexible lexical matching.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Faculty of Artificial Intelligence in Education, Central China Normal University, Wuhan, China.
- Hubei Provincial Key Laboratory of Artificial Intelligence and Smart Learning, Central China Normal University, Wuhan, China.
- School of Computer Science, Central China Normal University, Wuhan, China.
ORCID-Profile: Chenyang Li
Förderung
- National Social Science Fund of China
Zitieren
APA
Li, C., & Zhang, M. (2026). TASRIC: A Type‐Aware Semantic Retrieval Augmentation Framework With Iterative Correction for Bias Mitigation. Annals of the New York Academy of Sciences. https://doi.org/10.1111/nyas.70360
Vancouver
Li C, Zhang M. TASRIC: A Type‐Aware Semantic Retrieval Augmentation Framework With Iterative Correction for Bias Mitigation. Annals of the New York Academy of Sciences. 2026. doi:10.1111/nyas.70360
BibTeX
@article{Li2026,
author = {Li, Chenyang and Zhang, Maoyuan},
title = {TASRIC: A Type‐Aware Semantic Retrieval Augmentation Framework With Iterative Correction for Bias Mitigation},
journal = {Annals of the New York Academy of Sciences},
year = {2026},
doi = {10.1111/nyas.70360}
}
EUVIMED