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 natural language processing (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 artificial intelligence (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.

In an era dominated by web-based intelligent customer services, the applications of Sentence Pair Matching are profoundly broad. Web agents, for example, automatically respond to customer queries by finding similar past questions, significantly reducing customer service expenses. While current large language models (LLMs) offer powerful text generation capabilities, they often struggle with opacity, potential text toxicity, and difficulty managing domain-specific and confidential business inquiries. Consequently, the widespread adoption of web-based intelligent customer services in real-world business still greatly relies on query-based interactions. In this paper, we introduce a series of model-agnostic techniques aimed at enhancing both the accuracy and interpretability of Chinese pairwise sentence-matching models. Our contributions include (1) An Edit-distance-weighted fine-tuning method, (2) A Bayesian Iterative Prediction algorithm, (3) A Lexical-based Dual Ranking Interpreter, and (4) A Bi-criteria Denoising strategy. Experimental results on the Large-scale Chinese Question Matching Corpus (LCQMC) with a disturbed test demonstrate that our fine-tuning and prediction methods can steadily improve matching accuracy, building on the current state-of-the-art models. Besides, our interpreter with denoising strategy markedly enhances token-level interpretation in rationality and loyalty. In both matching accuracy and interpretation, our approaches outperform classic methods and even LLMs.

Rett Syndrome (RTT) is a severe neurodevelopmental disorder caused by loss of function of the X-linked Methyl-CpG-binding protein 2 ( MECP2 ). Several case studies report that gross motor function can be improved in children with RTT through treadmill walking, but whether the MeCP2-deficient motor circuit can support actual motor learning remains unclear. We used two-photon calcium imaging to simultaneously observe layer (L) 2/3 and L5a excitatory neuronal activity in the motor cortex (M1) while mice adapted to changing speeds on a computerized running wheel. Despite circuit hypoactivity and weakened functional connectivity across L2/3 and L5a, the Mecp2 -null circuit’s firing pattern evolved with improved performance over two weeks. Moreover, trained mice became less anxious and lived 20% longer than untrained mice. Since motor deficits and anxiety are core symptoms of Rett, which is not diagnosed until well after symptom onset, these results underscore the benefit of motor learning.