发表机构
Stanford University（斯坦福大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
INDRA平台通过封闭证据沙盒、实时来源标记和系统级协议，整合多档案库，防止LLM幻觉，实现可审计的大规模档案研究。
AI 中文摘要
五十年的诉讼使烟草行业以及药品、化学品、食品、枪支和化石燃料制造商的文件中，数百万页以前保密的商业记录被公开。然而，这些档案实际上无法被通用大型语言模型（LLMs）访问，因为它们从未被编译成LLM可读的语料库。聊天机器人可能熟悉这些档案中包含的一些材料，但由于无法直接访问文档，它们容易产生幻觉和其他缺陷。在此，我们介绍INDRA，一个研究平台，旨在通过将档案史学的惯例嵌入到管理每个输出的系统级协议中来修复此类失败。该平台整合了加州大学旧金山分校的行业文件图书馆、哥伦比亚大学和纽约城市大学的ToxicDocs、斯坦福大学的SRITA以及其他迄今为止孤立的收藏，并提供了三个相互关联的保障措施：（1）封闭的证据沙盒将模型限制在用户选择的语料库中，阻止从可能引入偏见的外部来源检索；（2）实时来源标记区分档案证据和参数推断的边界；（3）由确定性脚本强制执行的系统级协议指导每个输出的结构。这些保障措施共同防止模型混淆“文件说X”与“我认为X”或“我从先前训练中学到X”。结果是一个由LLM驱动的研究伙伴，能够进行大规模多档案调查，其输出旨在被检查而非被信任，其架构使知识生产的条件可见且可审计。三个案例研究展示了该方法的分析价值和局限性，包括我们称之为赫拉克利特效应、垫脚石困境和轻信（或黑手党）问题。
英文摘要
Five decades of litigation have disgorged hundreds of millions of pages of formerly secret business records from the tobacco industry, along with documents from the makers of drugs, chemicals, food, firearms, and fossil fuels. Yet these archives have been effectively inaccessible to general-purpose large language models (LLMs) because they have never been compiled into an LLM-readable corpus. Chatbots may be familiar with some of the materials contained in such archives but, with no direct access to the documents, they are vulnerable to hallucination and other defects. Here we introduce INDRA, a research platform designed to remedy such failures by embedding the conventions of archival historiography into a system-level protocol governing every output. The platform federates UCSF's Industry Documents Library, Columbia and CUNY's ToxicDocs, Stanford's SRITA, and other heretofore siloed collections, and provides three interlinked safeguards: (1) a closed evidentiary sandbox confines the model to a user-selected corpus, blocking retrieval from external sources that could introduce bias; (2) real-time provenance tagging marks the boundary between archival evidence and parametric inference; and (3) a system-level protocol enforced by deterministic scripts guides the structure of every output. Together these safeguards prevent the model from conflating "the documents say X" with "I think X" or "I learned X from prior training." The result is an LLM-powered research partner enabling massive multi-archival investigations, a tool whose outputs are designed to be checked rather than trusted, and whose architecture makes the conditions of knowledge production visible and auditable. Three case studies demonstrate the method's analytical value and limitations, including what we call the Heraclitus effect, the steppingstone dilemma, and the gullibility (or mafia) problem.
Comments35 pages, 6 figures, Appendices available at https://indra.stanford.edu/methods/appendices
