因果引导的主动学习用于大语言模型去偏
Causal-Guided Active Learning for Debiasing Large Language Models
AI总结：
针对大语言模型易受数据集偏差影响的问题，本文提出因果引导的主动学习框架CAL，利用模型自身自动识别偏差样本并归纳偏差模式，结合上下文学习实现高效去偏。
摘要：
尽管当前生成式大语言模型（LLMs）取得了令人瞩目的性能，近期分析表明它们仍可能捕捉数据集偏差并利用这些偏差进行生成，导致大语言模型的泛化能力差并产生有害输出。然而，由于数据集偏差的多样性以及过度优化问题，以往基于先验知识的去偏方法和基于微调的去偏方法可能不适用于当前的大语言模型。为解决这一问题，我们探索将主动学习与因果机制相结合，并提出一个因果引导的主动学习（CAL）框架，该框架利用大语言模型自身自动且自主地识别有信息量的偏差样本并归纳偏差模式。随后采用一种成本效益高且高效的基于上下文学习的方法，防止大语言模型在生成过程中利用数据集偏差。实验结果表明，CAL能够有效识别典型的偏差实例，并归纳出多种偏差模式用于大语言模型去偏。
英文摘要：
Although achieving promising performance, recent analyses show that current generative large language models (LLMs) may still capture dataset biases and utilize them for generation, leading to poor generalizability and harmfulness of LLMs. However, due to the diversity of dataset biases and the over-optimization problem, previous prior-knowledge-based debiasing methods and fine-tuning-based debiasing methods may not be suitable for current LLMs. To address this issue, we explore combining active learning with the causal mechanisms and propose a casual-guided active learning (CAL) framework, which utilizes LLMs itself to automatically and autonomously identify informative biased samples and induce the bias patterns. Then a cost-effective and efficient in-context learning based method is employed to prevent LLMs from utilizing dataset biases during generation. Experimental results show that CAL can effectively recognize typical biased instances and induce various bias patterns for debiasing LLMs.
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。
