Work

RAG, CAG, and Long-Context Prompting with a 4-bit Quantized 7B Language Model for Question Answering on Higher-Education Regulations: Data, Code, and Results

Year: 2026
Type: preprint
Abstract: Data, code, and analysis outputs for a comparison of retrieval-augmented generation (RAG), cache-augmented generation (CAG), and long-context prompting (LC) with 4-bit (NF4) quantized Qwen2.5-7B-Instruct on question answering over 17 Indonesian higher-education regulations (105 single-article questions; reference answers are verbatim quotations verified by script; no human raters or LLM judge). The archive contains the corpus, the QA set, raw outputs and per-item metrics of the main run and of a protocol-equalized rerun, analysis scripts, the system prompt, and environment versions. Greedy decoding; NVIDIA Tesla T4 (16 GB). This archive is not a preregistration.
Language: English
Open Access status: green
OpenAlex ID: W7225874971
Cites:
Cited by:
Related to: 10