Search papers, labs, and topics across Lattice.
The paper introduces BD-FDG, a framework for generating high-quality supervised fine-tuning (SFT) datasets for adapting LLMs to complex engineering domains, specifically Space Situational Awareness (SSA). BD-FDG employs structured knowledge organization, cognitively layered question modeling based on Bloom's Taxonomy, and automated quality control to address limitations in existing SFT data construction. Fine-tuning Qwen3-8B with the SSA-SFT dataset generated by BD-FDG yields SSA-LLM-8B, which significantly outperforms baselines on domain-specific tasks while maintaining general performance.
Forget generic fine-tuning data — Bloom's Taxonomy-based data generation can boost LLM performance in complex engineering domains like space situational awareness by up to 176%.
Large language models (LLMs) demonstrate exceptional performance on general-purpose tasks. however, transferring them to complex engineering domains such as space situational awareness (SSA) remains challenging owing to insufficient structural alignment with mission chains, the absence of higher-order cognitive supervision, and poor correspondence between data quality criteria and engineering specifications. The core bottleneck is the construction of high-quality supervised fine-tuning (SFT) datasets. To this end, we propose BD-FDG (Bloom's Taxonomy-based Domain-specific Fine-tuning Data Generation), a framework that addresses incomplete knowledge coverage, shallow cognitive depth, and limited quality controllability through three mechanisms: structured knowledge organization, cognitively layered question modeling, and automated quality control. The framework uses a knowledge tree to ensure structured corpus coverage, designs a question generation scheme spanning nine categories and six cognitive levels from Remember to Create to produce samples with a continuous difficulty gradient, and applies a multidimensional scoring pipeline to enforce domain rigor and consistency. Using BD-FDG, we construct SSA-SFT, a domain dataset of approximately 230K samples, and fine-tune Qwen3-8B to obtain SSA-LLM-8B. Experiments show that SSA-LLM-8B achieves relative BLEU-1 improvements of 144\% (no-think) and 176\% (think) on the domain test set and a win rate of 82.21\% over the baseline in arena comparisons, while largely preserving general benchmark performance (MMLU-Pro, MATH-500). These results validate SFT data construction driven by cognitive layering as an effective paradigm for complex engineering domains and provide a transferable framework for domain-specific LLM adaptation.
