Cognitively Layered Data Synthesis for Domain Adaptation of LLMs to Space Situational Awareness

TL;DR

This paper introduces a cognitively layered data generation framework for fine-tuning large language models, significantly improving their performance in space situational awareness tasks by creating high-quality, domain-specific datasets.

Contribution

The paper presents BD-FDG, a novel knowledge organization and question modeling framework that enhances dataset quality for domain-specific LLM fine-tuning, demonstrated on SSA tasks.

Findings

SSA-LLM-8B outperforms baseline models with 144-176% BLEU-1 improvements.

Achieved 82.21% win rate in domain-specific arena comparisons.

Constructed a 230K sample SSA dataset for effective LLM adaptation.

Abstract

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.