| LLM | Large Language Model |
| GEMMA | Gemma-2-9B |
| LLAMA | Llama-3.1-8B |
| QWEN | Qwen2.5-7B |
| MISTRAL | Mistral-7B-Instruct |
| PHI | Phi-3.5-mini-instruct |
| FT | Fine-Tuning |
| RAG | Retrieval-Augmented Generation |
| FT+RAG | Fine-Tuning & Retrieval-Augmented Generation |
| LoRA | Low-Rank Adaptation |
| QLoRA | Quantized Low-Rank Adaptation |
| PPL | Perplexity |
| ROUGE | Recall-Oriented Understudy for Gisting Evaluation |
| BLEU | Bilingual Evaluation Understudy |
| GLEU | Google-Bilingual Evaluation Understudy |
| R-1 | ROUGE-1 |
| R-2 | ROUGE-2 |
| R-L | ROUGE-L |
| BERT | Bidirectional Encoder Representations from Transformers |
| SBERT | Sentence-BERT |
| BS_P | BERTScore Precision |
| BS_R | BERTScore Recall |
| BS_F1 | BERTScore F1 |
| SB_CS | SBERT Cosine Similarity |
| NASS | Negation Aware Semantic Similarity |