对比不同微调方法在识别服务条款不公条款中的效果与成本
Text to Trust: Evaluating Fine-Tuning and LoRA Trade-offs in Language Models for Unfair Terms of Service Detection
- 比较全量微调、LoRA等高效方法在法律文本上的表现
- 全微调精度召回平衡最优，LoRA内存消耗降低3倍仍保持高召回
- 适合法律AI研究者和需要低成本部署的实践者参考
大型语言模型（LLMs）已显著提升文本理解能力，但其在专业法律领域适配仍受限于全量微调的成本。本研究系统评估了全微调、参数高效适配（LoRA、QLoRA）及零样本提示策略在服务条款（ToS）中不公平条款检测中的表现，涵盖BERT、DistilBERT、TinyLlama、LLaMA 3B/7B、SaulLM等模型，并在CLAUDETTE-ToS基准与多语种爬取语料上进行测试。结果表明，全微调在精度与召回之间达到最佳平衡；而基于4位低秩适配（LoRA）的模型在保持较高召回率的同时，内存占用降低最多达3倍。研究揭示了高效且领域适配的模型设计权衡，为法律文本处理的微调研究提供了开源基线。
原文摘要 · Abstract (English)
Large Language Models (LLMs) have transformed text understanding, yet their adaptation to specialized legal domains remains constrained by the cost of full fine-tuning. This study provides a systematic evaluation of fine tuning, parameter efficient adaptation (LoRA, QLoRA), and zero-shot prompting strategies for unfair clause detection in Terms of Service (ToS) documents, a key application in legal NLP. We finetune BERT and DistilBERT, apply 4-bit Low-Rank Adaptation (LoRA) to models such as TinyLlama, LLaMA 3B/7B, and SaulLM, and evaluate GPT-4o and O-versions in zero-shot settings. Experiments on the CLAUDETTE-ToS benchmark and the Multilingual Scraper Corpus show that full fine-tuning achieves the strongest precision recall balance, while LoRA-based models provide competitive recall with up to 3x lower memory cost. These findings highlight practical design trade-offs for efficient and domain-adapted LLMs, contributing open baselines for fine-tuning research in legal text processing.
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。