eSapiens: A Real-World NLP Framework for Multimodal Document Understanding and Enterprise Knowledge Processing
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908414841454592 |
|---|---|
| author | Shi, Isaac Li, Zeyuan Wang, Wenli He, Lewei Yang, Yang Shi, Tianyu |
| author_facet | Shi, Isaac Li, Zeyuan Wang, Wenli He, Lewei Yang, Yang Shi, Tianyu |
| contents | We introduce eSapiens, a unified question-answering system designed for enterprise settings, which bridges structured databases and unstructured textual corpora via a dual-module architecture. The system combines a Text-to-SQL planner with a hybrid Retrieval-Augmented Generation (RAG) pipeline, enabling natural language access to both relational data and free-form documents. To enhance answer faithfulness, the RAG module integrates dense and sparse retrieval, commercial reranking, and a citation verification loop that ensures grounding consistency. We evaluate eSapiens on the RAGTruth benchmark across five leading large language models (LLMs), analyzing performance across key dimensions such as completeness, hallucination, and context utilization. Results demonstrate that eSapiens outperforms a FAISS baseline in contextual relevance and generation quality, with optional strict-grounding controls for high-stakes scenarios. This work provides a deployable framework for robust, citation-aware question answering in real-world enterprise applications. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_16768 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | eSapiens: A Real-World NLP Framework for Multimodal Document Understanding and Enterprise Knowledge Processing Shi, Isaac Li, Zeyuan Wang, Wenli He, Lewei Yang, Yang Shi, Tianyu Information Retrieval We introduce eSapiens, a unified question-answering system designed for enterprise settings, which bridges structured databases and unstructured textual corpora via a dual-module architecture. The system combines a Text-to-SQL planner with a hybrid Retrieval-Augmented Generation (RAG) pipeline, enabling natural language access to both relational data and free-form documents. To enhance answer faithfulness, the RAG module integrates dense and sparse retrieval, commercial reranking, and a citation verification loop that ensures grounding consistency. We evaluate eSapiens on the RAGTruth benchmark across five leading large language models (LLMs), analyzing performance across key dimensions such as completeness, hallucination, and context utilization. Results demonstrate that eSapiens outperforms a FAISS baseline in contextual relevance and generation quality, with optional strict-grounding controls for high-stakes scenarios. This work provides a deployable framework for robust, citation-aware question answering in real-world enterprise applications. |
| title | eSapiens: A Real-World NLP Framework for Multimodal Document Understanding and Enterprise Knowledge Processing |
| topic | Information Retrieval |
| url | https://arxiv.org/abs/2506.16768 |