{"ID":2849951,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.22531","arxiv_id":"2510.22531","title":"Text to Trust: Evaluating Fine-Tuning and LoRA Trade-offs in Language Models for Unfair Terms of Service Detection","abstract":"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.","short_abstract":"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...","url_abs":"https://arxiv.org/abs/2510.22531","url_pdf":"https://arxiv.org/pdf/2510.22531v1","authors":"[\"Noshitha Padma Pratyusha Juttu\",\"Sahithi Singireddy\",\"Sravani Gona\",\"Sujal Timilsina\"]","published":"2025-10-26T04:46:06Z","proceeding":"cs.CL","tasks":"[\"cs.CL\",\"cs.AI\",\"cs.LG\"]","methods":"[\"Large Language Model\",\"Language Model\",\"LoRA\"]","has_code":false}