Enhancing HR Support in a Thai Organization with LLM-Based Question Answering
| dc.contributor.author | Taemkaeo, Chinnatip | |
| dc.contributor.author | Saetia, Chanatip | |
| dc.contributor.author | Chalothorn, Tawunrat | |
| dc.contributor.author | Titijaroonroj, Taravichet | |
| dc.date.accessioned | 2026-08-06T10:53:51Z | |
| dc.date.available | 2026-08-06T10:53:51Z | |
| dc.date.issued | 2026-01-01 | |
| dc.description.abstract | Large language models (LLMs) enhanced with retrieval-augmented generation (RAG) and multimodal inputs are increasingly used as interfaces to organizational knowledge. However, their effectiveness in specialized, non-English enterprise settings-such as Thai HR support-remains largely unclear. In many Thai organizations, employees frequently ask detailed HR-related questions, but the relevant information is scattered across internal webpages, PDF manuals, announcements, and images, making it difficult for generic LLMs to provide accurate, policy-consistent responses. To address this issue, we develop a multimodal RAG pipeline that combines hybrid dense-sparse retrieval over a vector database and evaluate six LLM models on a private Thai Visual Question Answering (VQA) HR dataset consisting of 226 questions and reference images across five HR topics. The results show that recent multimodal models, especially Qwen2.5-VL, achieve the best performance, with the highest averages in correctness (0.54), relevance (0.75), and helpfulness (0.64), clearly outperforming older vision-language systems and a text-only reasoning model. For large-scale answer evaluation, we apply an LLM-as-a-judge approach using GPT-4.1 and Gemini 2.5 Flash. We found that it serves as a generally reliable, though imperfect, substitute for human evaluation. | |
| dc.identifier.citation | Kst 2026 18th International Conference on Knowledge and Smart Technology, 503-508, 2026 | |
| dc.identifier.doi | 10.1109/KST67832.2026.11431871 | |
| dc.identifier.other | 2-s2.0-105036822491 | |
| dc.identifier.uri | https://dspace.kmitl.ac.th/handle/123456789/17672 | |
| dc.source | Kst 2026 18th International Conference on Knowledge and Smart Technology | |
| dc.subject | Human-LLM Agreement Differences | |
| dc.subject | LLM-as-a-Judge Evaluation | |
| dc.subject | Multimodal Question Answering | |
| dc.subject | Retrieval-Augmented Generation (RAG) | |
| dc.subject | Thai HR Support Systems | |
| dc.title | Enhancing HR Support in a Thai Organization with LLM-Based Question Answering | |
| dc.type | Conference Paper |