PolicyBot - Reliable Question Answering over Policy Documents
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866918206122229760 |
|---|---|
| author | Nagarajan, Gautam Kumar, Omir Santhiappan, Sudarsun |
| author_facet | Nagarajan, Gautam Kumar, Omir Santhiappan, Sudarsun |
| contents | All citizens of a country are affected by the laws and policies introduced by their government. These laws and policies serve essential functions for citizens. Such as granting them certain rights or imposing specific obligations. However, these documents are often lengthy, complex, and difficult to navigate, making it challenging for citizens to locate and understand relevant information. This work presents PolicyBot, a retrieval-augmented generation (RAG) system designed to answer user queries over policy documents with a focus on transparency and reproducibility. The system combines domain-specific semantic chunking, multilingual dense embeddings, multi-stage retrieval with reranking, and source-aware generation to provide responses grounded in the original documents. We implemented citation tracing to reduce hallucinations and improve user trust, and evaluated alternative retrieval and generation configurations to identify effective design choices. The end-to-end pipeline is built entirely with open-source tools, enabling easy adaptation to other domains requiring document-grounded question answering. This work highlights design considerations, practical challenges, and lessons learned in deploying trustworthy RAG systems for governance-related contexts. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_13489 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | PolicyBot - Reliable Question Answering over Policy Documents Nagarajan, Gautam Kumar, Omir Santhiappan, Sudarsun Emerging Technologies Information Retrieval All citizens of a country are affected by the laws and policies introduced by their government. These laws and policies serve essential functions for citizens. Such as granting them certain rights or imposing specific obligations. However, these documents are often lengthy, complex, and difficult to navigate, making it challenging for citizens to locate and understand relevant information. This work presents PolicyBot, a retrieval-augmented generation (RAG) system designed to answer user queries over policy documents with a focus on transparency and reproducibility. The system combines domain-specific semantic chunking, multilingual dense embeddings, multi-stage retrieval with reranking, and source-aware generation to provide responses grounded in the original documents. We implemented citation tracing to reduce hallucinations and improve user trust, and evaluated alternative retrieval and generation configurations to identify effective design choices. The end-to-end pipeline is built entirely with open-source tools, enabling easy adaptation to other domains requiring document-grounded question answering. This work highlights design considerations, practical challenges, and lessons learned in deploying trustworthy RAG systems for governance-related contexts. |
| title | PolicyBot - Reliable Question Answering over Policy Documents |
| topic | Emerging Technologies Information Retrieval |
| url | https://arxiv.org/abs/2511.13489 |