Advancing Risk and Quality Assurance: A RAG Chatbot for Improved Regulatory Compliance
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866912497309581312 |
|---|---|
| author | Hillebrand, Lars Berger, Armin Uedelhoven, Daniel Berghaus, David Warning, Ulrich Dilmaghani, Tim Kliem, Bernd Schmid, Thomas Loitz, Rüdiger Sifa, Rafet |
| author_facet | Hillebrand, Lars Berger, Armin Uedelhoven, Daniel Berghaus, David Warning, Ulrich Dilmaghani, Tim Kliem, Bernd Schmid, Thomas Loitz, Rüdiger Sifa, Rafet |
| contents | Risk and Quality (R&Q) assurance in highly regulated industries requires constant navigation of complex regulatory frameworks, with employees handling numerous daily queries demanding accurate policy interpretation. Traditional methods relying on specialized experts create operational bottlenecks and limit scalability. We present a novel Retrieval Augmented Generation (RAG) system leveraging Large Language Models (LLMs), hybrid search and relevance boosting to enhance R&Q query processing. Evaluated on 124 expert-annotated real-world queries, our actively deployed system demonstrates substantial improvements over traditional RAG approaches. Additionally, we perform an extensive hyperparameter analysis to compare and evaluate multiple configuration setups, delivering valuable insights to practitioners. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_16711 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Advancing Risk and Quality Assurance: A RAG Chatbot for Improved Regulatory Compliance Hillebrand, Lars Berger, Armin Uedelhoven, Daniel Berghaus, David Warning, Ulrich Dilmaghani, Tim Kliem, Bernd Schmid, Thomas Loitz, Rüdiger Sifa, Rafet Computation and Language Artificial Intelligence Risk and Quality (R&Q) assurance in highly regulated industries requires constant navigation of complex regulatory frameworks, with employees handling numerous daily queries demanding accurate policy interpretation. Traditional methods relying on specialized experts create operational bottlenecks and limit scalability. We present a novel Retrieval Augmented Generation (RAG) system leveraging Large Language Models (LLMs), hybrid search and relevance boosting to enhance R&Q query processing. Evaluated on 124 expert-annotated real-world queries, our actively deployed system demonstrates substantial improvements over traditional RAG approaches. Additionally, we perform an extensive hyperparameter analysis to compare and evaluate multiple configuration setups, delivering valuable insights to practitioners. |
| title | Advancing Risk and Quality Assurance: A RAG Chatbot for Improved Regulatory Compliance |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2507.16711 |