Guardado en:
| Autores principales: | , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | https://arxiv.org/abs/2601.17826 |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866915753447391232 |
|---|---|
| author | Yang, Siyuan Bian, Xihan Tang, Jiayin |
| author_facet | Yang, Siyuan Bian, Xihan Tang, Jiayin |
| contents | The increasing frequency and complexity of regulatory updates present a significant burden for multinational pharmaceutical companies. Compliance teams must interpret evolving rules across jurisdictions, formats, and agencies, often manually, at high cost and risk of error. We introduce RegGuard, an industrial-scale AI assistant designed to automate the interpretation of heterogeneous regulatory texts and align them with internal corporate policies. The system ingests heterogeneous document sources through a secure pipeline and enhances retrieval and generation quality with two novel components: HiSACC (Hierarchical Semantic Aggregation for Contextual Chunking) semantically segments long documents into coherent units while maintaining consistency across non-contiguous sections. ReLACE (Regulatory Listwise Adaptive Cross-Encoder for Reranking), a domain-adapted cross-encoder built on an open-source model, jointly models user queries and retrieved candidates to improve ranking relevance. Evaluations in enterprise settings demonstrate that RegGuard improves answer quality specifically in terms of relevance, groundedness, and contextual focus, while significantly mitigating hallucination risk. The system architecture is built for auditability and traceability, featuring provenance tracking, access control, and incremental indexing, making it highly responsive to evolving document sources and relevant for any domain with stringent compliance demands. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_17826 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | RegGuard: AI-Powered Retrieval-Enhanced Assistant for Pharmaceutical Regulatory Compliance Yang, Siyuan Bian, Xihan Tang, Jiayin Artificial Intelligence The increasing frequency and complexity of regulatory updates present a significant burden for multinational pharmaceutical companies. Compliance teams must interpret evolving rules across jurisdictions, formats, and agencies, often manually, at high cost and risk of error. We introduce RegGuard, an industrial-scale AI assistant designed to automate the interpretation of heterogeneous regulatory texts and align them with internal corporate policies. The system ingests heterogeneous document sources through a secure pipeline and enhances retrieval and generation quality with two novel components: HiSACC (Hierarchical Semantic Aggregation for Contextual Chunking) semantically segments long documents into coherent units while maintaining consistency across non-contiguous sections. ReLACE (Regulatory Listwise Adaptive Cross-Encoder for Reranking), a domain-adapted cross-encoder built on an open-source model, jointly models user queries and retrieved candidates to improve ranking relevance. Evaluations in enterprise settings demonstrate that RegGuard improves answer quality specifically in terms of relevance, groundedness, and contextual focus, while significantly mitigating hallucination risk. The system architecture is built for auditability and traceability, featuring provenance tracking, access control, and incremental indexing, making it highly responsive to evolving document sources and relevant for any domain with stringent compliance demands. |
| title | RegGuard: AI-Powered Retrieval-Enhanced Assistant for Pharmaceutical Regulatory Compliance |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2601.17826 |