Bias in Large Language Models: Origin, Evaluation, and Mitigation
원문 초록
Large Language Models (LLMs) have revolutionized natural language processing, but their susceptibility to biases poses significant challenges. This comprehensive review examines the landscape of bias in LLMs, from its origins to current mitigation strategies. We categorize biases as intrinsic and extrinsic, analyzing their manifestations in various NLP tasks. The review critically assesses a range of bias evaluation methods, including data-level, model-level, and output-level approaches, providing researchers with a robust toolkit for bias detection. We further explore mitigation strategies, categorizing them into pre-model, intra-model, and post-model techniques, highlighting their effectiveness and limitations. Ethical and legal implications of biased LLMs are discussed, emphasizing potential harms in real-world applications such as healthcare and criminal justice. By synthesizing current knowledge on bias in LLMs, this review contributes to the ongoing effort to develop fair and responsible AI systems. Our work serves as a comprehensive resource for researchers and practitioners working towards understanding, evaluating, and mitigating bias in LLMs, fostering the development of more equitable AI technologies.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
To Bias or Not to Bias: Detecting bias in News with bias-detector
Can Global XAI Methods Reveal Injected Bias in LLMs? SHAP vs Rule Extraction vs RuleSHAP
Robust Bias Detection in MLMs and its Application to Human Trait Ratings
ViLBias: A Comprehensive Framework for Bias Detection through Linguistic and Visual Cues , presenting Annotation Strategies, Evaluation, and Key Challenges
MT-LENS: An all-in-one Toolkit for Better Machine Translation Evaluation
The Promises and Pitfalls of LLM Annotations in Dataset Labeling: a Case Study on Media Bias Detection
토론
이 논문과 연결된 포럼 글이 아직 없습니다.