一句话：提出隐私保护且可定制的 RAG 工具 EvidenceBot，以增强 LLM 交互并缓解商业平台限制。
大语言模型在文档分析、内容生成和对话辅助等任务中日益关键，但商业 LLM 平台存在数据隐私、上下文长度限制、参数不可配置和评估能力不足等问题，尤其在敏感信息、大规模文档分析和定制输出场景中影响显著。为此，作者提出 EvidenceBot，一个基于检索增强生成（RAG）的隐私保护、可定制工具，目标是结合 LLM 能力并提升隐私性、灵活性与可用性。摘要未给出具体实现细节与实验结果，主要贡献在于工具定位与需求论证。
Large Language Models (LLMs) have become pivotal in reshaping the world by enabling advanced natural language processing tasks such as document analysis, content generation, and conversational assistance. Their ability to process and generate human-like text has unlocked unprecedented opportunities across different domains such as healthcare, education, finance, and more. However, commercial LLM platforms face several limitations, including data privacy concerns, context size restrictions, lack of parameter configurability, and limited evaluation capabilities. These shortcomings hinder their effectiveness, particularly in scenarios involving sensitive information, large-scale document analysis, or the need for customized output. This underscores the need for a tool that combines the power of LLMs with enhanced privacy, flexibility, and usability.
@inproceedings{paperbot9104,
title = {EvidenceBot: A Privacy-Preserving, Customizable RAG-Based Tool for Enhancing Large Language Model Interactions},
author = {Nafiz Imtiaz Khan and Vladimir Filkov},
booktitle = {FSE},
year = {2025},
doi = {10.1145/3696630.3728607}
}