Optimizing Semantic Search in Industrial Knowledge Retrieval: A Novel SHAP-Based Attention Mask Modification Approach

Mahr F, Freese G, Meier S, Kratsch C, Raum C, Thielen N, Franke J, Risch F (2025)

Publication Type: Conference contribution

Publication year: 2025

Publisher: IEEE

City/Town: New York City

Pages Range: 1-9

Conference Proceedings Title: 2025 26th International Conference on Thermal, Mechanical and Multi-Physics Simulation and Experiments in Microelectronics and Microsystems (EuroSimE)

Event location: Utrecht

DOI: 10.1109/EuroSimE65125.2025.11006545

Abstract

Knowledge management in industrial settings faces significant challenges due to information overload and knowledge loss. This investigation examines a RetrievalAugmented Generation (RAG) solution for quality reports at Siemens Electronics Works, where engineers currently spend significant time searching through 4,500+ technical documents, resulting in annual costs of approximately C=200,000. We developed an optimized data preprocessing pipeline for semantic search that combines generalizable components (duplicate removal, HTML cleaning, chunking strategies) with novel domain-specific enhancements. Our key innovation is a systematic approach integrating Shapley Additive exPlanations (SHAP) with attention mask modification (AMM) to identify and downweight tokens that disproportionately influence search results. This method, combined with LLM-based contextual enhancement of domain-specific abbreviations and semantic chunking, achieved a 21.1 % improvement in retrieval accuracy compared to raw data processing, as measured by Mean Reciprocal Rank (MRR). The resulting RAG application operates locally without internet access, ensuring data security while significantly reducing document retrieval time. Our methodology provides a framework for optimizing semantic search in specialized technical domains without requiring extensive model retraining.

Authors with CRIS profile

Involved external institutions

Siemens AG Germany (DE) Hochschule für Technik und Wirtschaft Berlin (HTW) Germany (DE)

How to cite

APA:

Mahr, F., Freese, G., Meier, S., Kratsch, C., Raum, C., Thielen, N.,... Risch, F. (2025). Optimizing Semantic Search in Industrial Knowledge Retrieval: A Novel SHAP-Based Attention Mask Modification Approach. In 2025 26th International Conference on Thermal, Mechanical and Multi-Physics Simulation and Experiments in Microelectronics and Microsystems (EuroSimE) (pp. 1-9). Utrecht, NL: New York City: IEEE.

MLA:

Mahr, Felix, et al. "Optimizing Semantic Search in Industrial Knowledge Retrieval: A Novel SHAP-Based Attention Mask Modification Approach." Proceedings of the 2025 26th International Conference on Thermal, Mechanical and Multi-Physics Simulation and Experiments in Microelectronics and Microsystems (EuroSimE), Utrecht New York City: IEEE, 2025. 1-9.

BibTeX: Download