信息增益引导的因果干预用于大型语言模型的自主去偏
Information Gain-Guided Causal Intervention for Autonomous Debiasing Large Language Models
AI总结：
提出信息增益引导的因果干预去偏框架（ICD），通过因果干预重写数据以消除指令微调数据集偏差，提升LLM的泛化能力。
摘要：
尽管取得了显著进展，近期研究表明，当前的大型语言模型（LLMs）仍可能捕获数据集偏差并在推理过程中利用这些偏差，导致LLMs的泛化能力较差。然而，由于数据集偏差的多样性以及基于上下文学习的偏差抑制方法的不足，以往基于先验知识的去偏方法和基于上下文学习的自动去偏方法的有效性受到限制。为应对这些挑战，我们探索了因果机制与信息论的结合，并提出了一种信息增益引导的因果干预去偏（ICD）框架。为消除指令微调数据集中的偏差，必须确保这些偏差不提供任何额外信息来预测答案，即这些偏差对预测答案的信息增益需为0。在此指导下，该框架利用基于因果干预的数据重写方法，自动且自主地平衡指令微调数据集的分布，以降低信息增益。随后，它采用标准的监督微调过程，在去偏后的数据集上训练LLMs。实验结果表明，ICD能够有效对LLM进行去偏，提升其在不同任务上的泛化能力。
英文摘要：
Despite significant progress, recent studies indicate that current large language models (LLMs) may still capture dataset biases and utilize them during inference, leading to the poor generalizability of LLMs. However, due to the diversity of dataset biases and the insufficient nature of bias suppression based on in-context learning, the effectiveness of previous prior knowledge-based debiasing methods and in-context learning based automatic debiasing methods is limited. To address these challenges, we explore the combination of causal mechanisms with information theory and propose an information gain-guided causal intervention debiasing (ICD) framework. To eliminate biases within the instruction-tuning dataset, it is essential to ensure that these biases do not provide any additional information to predict the answers, i.e., the information gain of these biases for predicting the answers needs to be 0. Under this guidance, this framework utilizes a causal intervention-based data rewriting method to automatically and autonomously balance the distribution of instruction-tuning dataset for reducing the information gain. Subsequently, it employs a standard supervised fine-tuning process to train LLMs on the debiased dataset. Experimental results show that ICD can effectively debias LLM to improve its generalizability across different tasks.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
