Maxwell J. Yin

Maxwell J. Yin, Boyu Wang, Charles Ling

Models trained on real-world data often mirror and exacerbate existing social biases. Traditional methods for mitigating these biases typically require prior knowledge of the specific biases to be addressed, such as gender or racial biases, and the social groups associated with each instance. In this paper, we introduce a novel adversarial training strategy that operates independently of prior bias-type knowledge and protected attribute labels. Our approach proactively identifies biases during model training by utilizing auxiliary models, which are trained concurrently by predicting the performance of the main model without relying on task labels. Additionally, we implement these auxiliary models at various levels of the feature maps of the main model, enabling the detection of a broader and more nuanced range of bias features. Through experiments on racial and gender biases in sentiment and occupation classification tasks, our method effectively reduces social biases without the need for demographic annotations. Moreover, our approach not only matches but often surpasses the efficacy of methods that require detailed demographic insights, marking a significant advancement in bias mitigation techniques.

Maxwell J. Yin, Dingyi Jiang, Yongbing Chen et al.

Chain-of-Thought (CoT) reasoning in smaller language models is a challenging natural language process problem yet highly desirable in many real-life applications. Existing CoT knowledge distillation methods often suffer from overly conservative memorization in smaller LLMs, leading to low generalization confidence. As fully preserving the CoT ability of teacher model is impossible, we hypothesize that adversarial CoT fine-tuning is crucial for developing smaller LLM with robust CoT generalization. To this end, we propose \textit{PRompt-Assisted Domain-Adversarial fine-tuning} (PRADA), a principled fine-tuning framework that integrates diverse CoT domains. Specifically, PRADA pioneers two CoT improvements in smaller LLM: (1) Recovering the domain-invariant feature insight which typically lost during distillation with domain adversarial fine-tuning; (2) Enhancing the domain adaptability of CoT prompt engineering by employing domain-adversarial approaches. We theoretically demonstrate the effectiveness of our approach and empirically show that it significantly outperforms the state of the arts in a wide range of tasks. Moreover, our empirical findings reveal that the smaller LLM, when leveraging PRADA, aligns closely with domain knowledge, thereby improving the explainability of our approach.

Ganyu Wang, Jinjie Fang, Maxwell J. Yin et al.

Black-Box Discrete Prompt Learning is a prompt-tuning method that optimizes discrete prompts without accessing model parameters or gradients, making the prompt tuning on a cloud-based Large Language Model (LLM) feasible. Adapting federated learning to BDPL could further enhance prompt tuning performance by leveraging data from diverse sources. However, all previous research on federated black-box prompt tuning had neglected the substantial query cost associated with the cloud-based LLM service. To address this gap, we conducted a theoretical analysis of query efficiency within the context of federated black-box prompt tuning. Our findings revealed that degrading FedAvg to activate only one client per round, a strategy we called \textit{FedOne}, enabled optimal query efficiency in federated black-box prompt learning. Building on this insight, we proposed the FedOne framework, a federated black-box discrete prompt learning method designed to maximize query efficiency when interacting with cloud-based LLMs. We conducted numerical experiments on various aspects of our framework, demonstrating a significant improvement in query efficiency, which aligns with our theoretical results.