FactoryLLM: A Safe and Open-Source AI Playground for Evaluating LLMs in Smart Factories
Quick Answer
FactoryLLM is an open-source AI platform for evaluating retrieval-augmented generation models in smart factories, achieving groundedness scores above 0.88 across three LLMs on 30 maintenance queries from 600 pages of documentation.
Quick Take
It ensures data safety by allowing local execution without sharing sensitive information.
Key Points
- FactoryLLM evaluates using RAGAS and NVIDIA's LLM-as-a-Judge metrics.
- Users can configure LLMs to analyze documents from multiple machines.
- The platform demonstrated effectiveness with a case study involving an Autonomous Intelligent Vehicle.
- All evaluated models achieved groundedness scores above 0.88.
- Full code and documentation are publicly available for community use.
Paper Resources
Article Content
From source RSS / original summaryarXiv:2606. 14119v1 Announce Type: new Abstract: Fault diagnostics and recovery in smart factories is challenging because critical information is dispersed across manuals of multiple machines which are interconnected through the manufacturing process. (LLMs) can provide a promising approach.
In this paper, we propose FactoryLLM, a safe and open-source AI playground designed for evaluating different LLM-based (RAG) models by analysing documents from multiple machines across the manufacturing process. FactoryLLM enables the user to configure the LLM, and assess performance when reasoning over multiple documents, through a dual evaluation setup using both RAGAS and NVIDIA's LLM-as-a-Judge metrics.
FactoryLLM is safe because it allows users to run local or open-source LLMs without sharing sensitive industrial data, providing a controlled environment for experimentation. We demonstrate the efficacy of FactoryLLM through a case study which involves an Autonomous Intelligent Vehicle and its Mobile Planner software, evaluating three LLMs across 30 maintenance queries derived from approximately 600 pages of cross-machine documentation.
The results suggest that FactoryLLM is effective in cross-machine document reasoning: every model achieved a groundedness score above 0. 88. The full code and documentation for community to test FactoryLLM with their manufacturing specific scenarios are publicly available.
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from arXiv cs.AI
See more →HOBA: Hierarchical On-Policy Bidding Agents for Adaptive Online Advertising
HOBA (Hierarchical On-policy Bidding Agents) is a novel hierarchical reinforcement learning framework that enhances online advertising bidding systems by improving adaptability and reducing hyperparameter tuning costs. It utilizes a for hyperparameter inference, a SARSA agent for expert model selection, and a dynamic expert pool for bid execution, achieving a +3.6% increase in target cost during large-scale deployment and outperforming state-of-the-art baselines on AuctionNet.