针对大模型领域问答中的知识冲突问题，提出加权微调方法提升性能。
KaFT: Knowledge-aware Fine-tuning for Boosting LLMs' Domain-specific Question-Answering Performance
- 按知识冲突程度动态调整训练样本权重，避免错误信息干扰。
- 在四个大模型上验证，显著提升领域问答准确率并减少幻觉。
- 适合需要高可靠问答的医疗、法律等专业领域应用。
监督微调（SFT）是提升大语言模型（LLMs）领域特定问答（QA）性能的常用方法。然而，近期研究表明，由于模型内部知识与训练数据上下文知识存在冲突，使用完整训练集进行原始SFT通常效果不佳。本文首先设计了一种查询多样化策略以实现鲁棒的冲突检测，并通过一系列实验分析知识冲突的影响。发现：1）具有不同冲突程度的训练样本贡献不均，高冲突数据上的SFT会导致性能急剧下降；2）相比直接过滤冲突数据，合理利用冲突数据更具优势。受此启发，我们提出一种简单而有效的知识感知微调方法（KaFT），其核心是根据冲突水平为不同训练样本分配差异化权重。大量实验表明，KaFT在四个大模型上均带来一致且显著的性能提升。进一步分析证明，KaFT有效增强了模型泛化能力并缓解了幻觉现象。
原文摘要 · Abstract (English)
Supervised fine-tuning (SFT) is a common approach to improve the domain-specific question-answering (QA) performance of large language models (LLMs). However, recent literature reveals that due to the conflicts between LLMs' internal knowledge and the context knowledge of training data, vanilla SFT using the full QA training set is usually suboptimal. In this paper, we first design a query diversification strategy for robust conflict detection and then conduct a series of experiments to analyze the impact of knowledge conflict. We find that 1) training samples with varied conflicts contribute differently, where SFT on the data with large conflicts leads to catastrophic performance drops; 2) compared to directly filtering out the conflict data, appropriately applying the conflict data would be more beneficial. Motivated by this, we propose a simple-yet-effective Knowledge-aware Fine-tuning (namely KaFT) approach to effectively boost LLMs' performance. The core of KaFT is to adapt the training weight by assigning different rewards for different training samples according to conflict level. Extensive experiments show that KaFT brings consistent and significant improvements across four LLMs. More analyses prove that KaFT effectively improves the model generalization and alleviates the hallucination.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。