{
      "department": "FAKULTAS SAINS DAN TEKNOLOGI",
      "subjects": [
        6.3
      ],
      "eprintid": 78779,
      "thesis_type": "masters",
      "date": "2026-08-10",
      "userid": 12460,
      "documents": [
          {
            "language": "id",
            "placement": 1,
            "eprintid": 78779,
            "files": [
                {
                  "hash_type": "MD5",
                  "mtime": "2026-10-07 01:42:53",
                  "datasetid": "document",
                  "fileid": 1876107,
                  "objectid": 1079719,
                  "uri": "http:\/\/digilib.uin-suka.ac.id\/id\/file\/1876107",
                  "mime_type": "application\/pdf",
                  "hash": "db5594d48911a976c3c63a0e4422220f",
                  "filesize": 6756712,
                  "filename": "24206051015_BAB-I_IV-atau-V_DAFTAR-PUSTAKA.pdf"
                }
            ],
            "content": "published",
            "rev_number": 3,
            "uri": "http:\/\/digilib.uin-suka.ac.id\/id\/document\/1079719",
            "main": "24206051015_BAB-I_IV-atau-V_DAFTAR-PUSTAKA.pdf",
            "mime_type": "application\/pdf",
            "docid": 1079719,
            "format": "text",
            "security": "public",
            "pos": 1,
            "formatdesc": "OPTIMALISASI ARSITEKTUR RETRIEVAL-AUGMENTED GENERATION MELALUI FINE-TUNING MODEL EMBEDDING DAN LARGE LANGUAGE MODEL UNTUK ANALISIS NAHWU-SHARAF KITAB KUNING"
          },
          {
            "language": "id",
            "placement": 2,
            "eprintid": 78779,
            "files": [
                {
                  "hash_type": "MD5",
                  "mtime": "2026-10-07 01:42:55",
                  "datasetid": "document",
                  "fileid": 1876110,
                  "objectid": 1079720,
                  "uri": "http:\/\/digilib.uin-suka.ac.id\/id\/file\/1876110",
                  "mime_type": "application\/pdf",
                  "hash": "e71cba23865b36cb9dfd0b1cca467703",
                  "filesize": 13725728,
                  "filename": "24206051015_BAB-II_sampai_SEBELUM-BAB-TERAKHIR.pdf"
                }
            ],
            "content": "published",
            "rev_number": 3,
            "uri": "http:\/\/digilib.uin-suka.ac.id\/id\/document\/1079720",
            "main": "24206051015_BAB-II_sampai_SEBELUM-BAB-TERAKHIR.pdf",
            "mime_type": "application\/pdf",
            "docid": 1079720,
            "format": "text",
            "security": "validuser",
            "pos": 2,
            "formatdesc": "OPTIMALISASI ARSITEKTUR RETRIEVAL-AUGMENTED GENERATION MELALUI FINE-TUNING MODEL EMBEDDING DAN LARGE LANGUAGE MODEL UNTUK ANALISIS NAHWU-SHARAF KITAB KUNING"
          }
      ],
      "rev_number": 10,
      "creators": [
        {
          "name": {
            "lineage": null,
            "given": "NIM.: 24206051015",
            "honourific": null,
            "family": "Subhan Ghufron"
          }
        }
      ],
      "dir": "disk0\/00\/07\/87\/79",
      "keywords": "Retrieval-Augmented Generation, Nahwu-Sharaf, Kitab Kuning, Fine-tuning, Model Embedding, Large Language Model, BGE-M3, E5-Large, Llama3-8B, Mistral-7B",
      "lastmod": "2026-10-07 02:05:38",
      "ispublished": "pub",
      "metadata_visibility": "show",
      "date_type": "published",
      "eprint_status": "archive",
      "status_changed": "2026-10-07 02:05:38",
      "datestamp": "2026-10-07 02:05:38",
      "uri": "http:\/\/digilib.uin-suka.ac.id\/id\/eprint\/78779",
      "thesis_name": "other",
      "note": "Prof. Dr. Ir. Shofwatul 'Uyun,S.T.,M.Kom., IPM., ASEAN Eng.",
      "full_text_status": "restricted",
      "contact_email": "muh.khabib@uin-suka.ac.id",
      "divisions": [
        "S2_inf"
      ],
      "abstract": "Arabic grammatical analysis (Nahwu-Sharaf) of classical Islamic texts (kitab kuning) is a cornerstone of the pesantren education tradition in Indonesia. This process still relies on manual analysis requiring deep expertise and extensive time. This study aims to evaluate the effectiveness of fine-tuning embedding models and Large Language Models (LLMs) within a Retrieval-Augmented Generation (RAG) architecture for automated Nahwu-Sharaf analysis of kitab kuning. Twelve configurations were tested comparatively, involving two embedding models (BGE-M3 and E5-Large) and two LLMs (Llama3-8B and Mistral-7B), each in baseline and fine-tuned conditions using QLoRA on the NahwuAI dataset. Evaluation was conducted using automatic metrics (Recall@K, BLEU, ROUGE-L, F1, Cosine Similarity) and human evaluation by three Arabic grammar experts. Results showed that fine-tuned BGE-M3 outperformed as the embedding model with a Recall@1 of 0.8109 (a 37.7% increase). Fine-tuned Mistral-7B was selected as the best LLM due to its stronger generalization capability on kitab kuning texts compared to Llama3-8B, which tended to overfit to training data. The RAG + fine-tuned Mistral configuration achieved the highest F1 (0.1176) and the highest expert score (3.80 out of 5). RAG was demonstrated to provide the greatest added value when paired with a model already strengthened through fine-tuning.",
      "type": "thesis",
      "title": "OPTIMALISASI ARSITEKTUR RETRIEVAL-AUGMENTED GENERATION MELALUI FINE-TUNING MODEL EMBEDDING DAN LARGE LANGUAGE MODEL UNTUK ANALISIS NAHWU-SHARAF KITAB KUNING",
      "institution": "UIN SUNAN KALIJAGA YOGYAKARTA",
      "pages": 117
    }