Knowledge Graph-Guided Multi-Agent Distillation for Reliable Industrial Question Answering with Datasets

• URL: http://arxiv.org/abs/2510.06240v1
• Date: Fri, 03 Oct 2025 06:52:59 GMT
• Title: Knowledge Graph-Guided Multi-Agent Distillation for Reliable Industrial Question Answering with Datasets
• Abstract summary: Industrial question-answering systems require higher safety and reliability than general-purpose dialogue models.<n>We propose Knowledge Graph-guided Multi-Agent System Distillation (KG-MASD)<n> Experiments on an industrial QA dataset show that KG-MASD improves accuracy by 2.4 per cent to 20.1 per cent over baselines.
• Score: 1.0221654398821483
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Industrial question-answering (QA) systems require higher safety and reliability than general-purpose dialogue models, as errors in high-risk scenarios such as equipment fault diagnosis can have severe consequences. Although multi-agent large language models enhance reasoning depth, they suffer from uncontrolled iterations and unverifiable outputs, and conventional distillation methods struggle to transfer collaborative reasoning capabilities to lightweight, deployable student models. To address these challenges, we propose Knowledge Graph-guided Multi-Agent System Distillation (KG-MASD). Our approach formulates distillation as a Markov Decision Process and incorporates a knowledge graph as a verifiable structured prior to enrich state representation and ensure convergence. By integrating collaborative reasoning with knowledge grounding, KG-MASD generates high-confidence instruction-tuning data and jointly distills reasoning depth and verifiability into compact student models suitable for edge deployment. Experiments on an industrial QA dataset show that KG-MASD improves accuracy by 2.4 per cent to 20.1 per cent over baselines and significantly enhances reliability, enabling trustworthy AI deployment in safety-critical industrial scenarios. Code and data are available at https://github.com/erwinmsmith/KG-MAD/.

Related papers

• Explainable and Fine-Grained Safeguarding of LLM Multi-Agent Systems via Bi-Level Graph Anomaly Detection [76.91230292971115]
  Large language model (LLM)-based multi-agent systems (MAS) have shown strong capabilities in solving complex tasks.<n>XG-Guard is an explainable and fine-grained safeguarding framework for detecting malicious agents in MAS.
  arXiv  Detail & Related papers  (2025-12-21T13:46:36Z)
• Adjudicator: Correcting Noisy Labels with a KG-Informed Council of LLM Agents [0.0]
  noisy labels can degrade performance and erode user trust.<n>This paper presents Adjudicator, a system that addresses the critical data mining challenge of automatically identifying and correcting label noise.<n>We validate our system on a 1,000-item balanced subset of the AlleNoise benchmark.
  arXiv  Detail & Related papers  (2025-12-05T06:13:00Z)
• Divide-Then-Align: Honest Alignment based on the Knowledge Boundary of RAG [51.120170062795566]
  We propose Divide-Then-Align (DTA) to endow RAG systems with the ability to respond with "I don't know" when the query is out of the knowledge boundary.<n>DTA balances accuracy with appropriate abstention, enhancing the reliability and trustworthiness of retrieval-augmented systems.
  arXiv  Detail & Related papers  (2025-05-27T08:21:21Z)
• EIAD: Explainable Industrial Anomaly Detection Via Multi-Modal Large Language Models [23.898938659720503]
  Industrial Anomaly Detection (IAD) is critical to ensure product quality during manufacturing.<n>We propose a novel approach that introduces a dedicated multi-modal defect localization module to decouple the dialog functionality from the core feature extraction.<n>We also contribute to the first multi-modal industrial anomaly detection training dataset, named Defect Detection Question Answering (DDQA)
  arXiv  Detail & Related papers  (2025-03-18T11:33:29Z)
• Harnessing Diverse Perspectives: A Multi-Agent Framework for Enhanced Error Detection in Knowledge Graphs [29.44542764343831]
  We propose a novel Multi-Agent framework for Knowledge Graph Error Detection (MAKGED)<n>By concatenating fine-grained, bidirectional subgraph embeddings with LLM-based query embeddings during training, our framework integrates these representations to produce four specialized agents.<n>Experiments on FB15K and WN18RR demonstrate that MAKGED outperforms state-of-the-art methods, enhancing the accuracy and robustness of KG evaluation.
  arXiv  Detail & Related papers  (2025-01-27T05:35:25Z)
• ADKGD: Anomaly Detection in Knowledge Graphs with Dual-Channel Training [38.3788247358102]
  This paper presents an anomaly detection algorithm in knowledge graphs with dual-channel learning (ADKGD)<n>We introduce a kullback-leibler (KL)-loss component to improve the accuracy of the scoring function between the dual channels.<n> Experimental results demonstrate that ADKGD outperforms the state-of-the-art anomaly detection algorithms.
  arXiv  Detail & Related papers  (2025-01-13T06:22:52Z)
• Uncertainty Management in the Construction of Knowledge Graphs: a Survey [3.5639148953570845]
  Knowledge Graphs (KGs) are a major asset for companies thanks to their great flexibility in data representation. To build a KG it is a common practice to rely on automatic methods for extracting knowledge from various heterogeneous sources. In a noisy and uncertain world, knowledge may not be reliable and conflicts between data sources may occur.
  arXiv  Detail & Related papers  (2024-05-27T08:22:52Z)
• Improving the Robustness of Knowledge-Grounded Dialogue via Contrastive Learning [71.8876256714229]
  We propose an entity-based contrastive learning framework for improving the robustness of knowledge-grounded dialogue systems. Our method achieves new state-of-the-art performance in terms of automatic evaluation scores.
  arXiv  Detail & Related papers  (2024-01-09T05:16:52Z)
• Model Stealing Attack against Graph Classification with Authenticity, Uncertainty and Diversity [80.16488817177182]
  GNNs are vulnerable to the model stealing attack, a nefarious endeavor geared towards duplicating the target model via query permissions. We introduce three model stealing attacks to adapt to different actual scenarios.
  arXiv  Detail & Related papers  (2023-12-18T05:42:31Z)
• KAT: A Knowledge Augmented Transformer for Vision-and-Language [56.716531169609915]
  We propose a novel model - Knowledge Augmented Transformer (KAT) - which achieves a strong state-of-the-art result on the open-domain multimodal task of OK-VQA. Our approach integrates implicit and explicit knowledge in an end to end encoder-decoder architecture, while still jointly reasoning over both knowledge sources during answer generation. An additional benefit of explicit knowledge integration is seen in improved interpretability of model predictions in our analysis.
  arXiv  Detail & Related papers  (2021-12-16T04:37:10Z)
• Anomaly Detection Based on Selection and Weighting in Latent Space [73.01328671569759]
  We propose a novel selection-and-weighting-based anomaly detection framework called SWAD. Experiments on both benchmark and real-world datasets have shown the effectiveness and superiority of SWAD.
  arXiv  Detail & Related papers  (2021-03-08T10:56:38Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.