mlsanityData to 14 Oct 2026

ReqBrain: Task-Specific Instruction Tuning of LLMs for AI-Assisted Requirements Generation

arXiv 2505.17632 ↗First posted 23 May 2025cs.SE cs.AI cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Requirements elicitation and specification remains a labor-intensive, manual process prone to inconsistencies and gaps, presenting a significant challenge in modern software engineering. Emerging studies underscore the potential of employing large language models (LLMs) for automated requirements generation to support requirements elicitation and specification; however, it remains unclear how to implement this effectively. In this work, we introduce ReqBrain, an Al-assisted tool that employs a fine-tuned LLM to generate authentic and adequate software requirements. Software engineers can engage with ReqBrain through chat-based sessions to automatically generate software requirements and categorize them by type. We curated a high-quality dataset of ISO 29148-compliant requirements and fine-tuned five 7B-parameter LLMs to determine the most effective base model for ReqBrain. The top-performing model, Zephyr-7b-beta, achieved 89.30% Fl using the BERT score and a FRUGAL score of 91.20 in generating authentic and adequate requirements. Human evaluations further confirmed ReqBrain's effectiveness in generating requirements. Our findings suggest that generative Al, when fine-tuned, has the potential to improve requirements elicitation and specification, paving the way for future extensions into areas such as defect identification, test case generation, and agile user story creation.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 33 of its 68 references that are in the map. First posted on arXiv 23 May 2025.

Builds on

33 of 68 references.

References · 33

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2020Language Models are Few-Shot Learnerscited by 32,419
  3. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,380
  4. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 13,028
  5. 2019BERTScore: Evaluating Text Generation with BERTcited by 5,512
  6. 2016Overcoming catastrophic forgetting in neural networkscited by 4,787
  7. 2023Mistral 7Bcited by 3,164
  8. 2022Training Compute-Optimal Large Language Modelscited by 3,019
  9. 2022Fine-Tuning can Distort Pretrained Features and Underperform Out-of-Distributioncited by 739
  10. 2020Intrinsic Dimensionality Explains the Effectiveness of Language Model Fine-Tuningcited by 671
  11. 2023Zephyr: Direct Distillation of LM Alignmentcited by 506
  12. 2023Large Language Models for Software Engineering: A Systematic Literature Reviewcited by 399
21 more
  1. 2022Selection-Inference: Exploiting Large Language Models for Interpretable Logical Reasoningcited by 334
  2. 2017Why We Need New Evaluation Metrics for NLGcited by 233
  3. 2021PPT: Pre-trained Prompt Tuning for Few-shot Learningcited by 232
  4. 2022Efficient Few-Shot Learning Without Promptscited by 137
  5. 2023Continual Pre-Training of Large Language Models: How to (re)warm your model?cited by 137
  6. 2023Investigating the Catastrophic Forgetting in Multimodal Large Language Modelscited by 119
  7. 2023Context-faithful Prompting for Large Language Modelscited by 80
  8. 2023Maybe Only 0.5% Data is Needed: A Preliminary Exploration of Low Training Data Instruction Tuningcited by 58
  9. 2023Advancing Requirements Engineering through Generative AI: Assessing the Role of LLMscited by 42
  10. 2022Two-stage LLM Fine-tuning with Less Specialization and More Generalizationcited by 41
  11. 2023Building Real-World Meeting Summarization Systems using Large Language Models: A Practical Perspectivecited by 34
  12. 2023Task Arithmetic with LoRA for Continual Learningcited by 32
  13. 2023Investigating ChatGPT's Potential to Assist in Requirements Elicitation Processescited by 25
  14. 2024Mitigating Large Language Model Hallucination with Faithful Finetuningcited by 24
  15. 2021FrugalScore: Learning Cheaper, Lighter and Faster Evaluation Metricsfor Automatic Text Generationcited by 19
  16. 2023Prompt-MIL: Boosting Multi-Instance Learning Schemes via Task-specific Prompt Tuningcited by 15
  17. 2024Towards Evaluation Guidelines for Empirical Studies involving LLMscited by 15
  18. 2022Extracting Software Requirements from Unstructured Documentscited by 3
  19. 2018The REquirements TRacing On target (RETRO).NET Datasetcited by 2
  20. 2021Detecting Requirements Smells With Deep Learning: Experiences, Challenges and Future Workcited by 2
  21. 2018ELICA: An Automated Tool for Dynamic Extraction of Requirements Relevant Informationcited by 1

Built on by

Not cited yet.