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

• URL: http://arxiv.org/abs/2603.09231v1
• Date: Tue, 10 Mar 2026 06:04:53 GMT
• Title: Cognitively Layered Data Synthesis for Domain Adaptation of LLMs to Space Situational Awareness
• Abstract summary: BD-FDG is a framework that addresses incomplete knowledge coverage, shallow cognitive depth, and limited quality controllability.<n>We construct SSA-SFT, a domain dataset of approximately 230K samples, and fine-tune Qwen3-8B to obtain SSA-LLM-8B.<n>Results show that SSA-LLM-8B achieves relative BLEU-1 improvements of 144% (no-think) and 176% (think) on the domain test set.
• Score: 8.378095304375154
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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.

Related papers

• CORTEX: High-Quality Cross-Domain Organization of Web-Scale Corpora through Ontological Corpus Graph [54.98647797362972]
  Existing corpus construction pipelines confine the resulting corpora to flat, undifferentiated document collections.<n>We present Cortex, to our knowledge the first framework that elevates web-scale corpus construction from flat document filtering to structured knowledge organization.
  arXiv  Detail & Related papers  (2026-06-29T11:51:00Z)
• The Illusion of Multi-Agent Advantage [63.92466143571383]
  We show that expert-architected Multi-Agent Systems (MAS) consistently outperforms automatically generated architectures in raw performance and cost-efficiency.<n>Existing evaluation frameworks mask critical architectural gaps and inefficiencies by failing to account for the marginal utility of increased computational cost.
  arXiv  Detail & Related papers  (2026-06-11T07:39:24Z)
• Automating Geometry-Intensive Compliance Checking in BIM: Graph-Based Semantic Reasoning Framework [3.270227506638339]
  This research provides a graph-based semantic reasoning paradigm, enhancing the transparency and flexibility of automated geometric compliance check.<n>The framework achieves 84.3% accuracy, representing an 8.6% improvement over enhanced-tool single-agent baselines.
  arXiv  Detail & Related papers  (2026-06-10T13:31:43Z)
• GeoMamba: A Geometry-driven MambaVision Framework and Dataset for Fine-grained Optical-SAR Object Retrieval [54.741349848771144]
  GeoMamba is a geometry-driven framework for optical-SAR fine-grained retrieval.<n>GFI module enhances cross-modal feature interaction and incorporates structural priors.<n>GeoMamba outperforms existing methods, achieving 63.3% mAP and 77.0% Rank-1 accuracy in all-to-all retrieval setting.
  arXiv  Detail & Related papers  (2026-05-19T12:08:09Z)
• Can Large Multimodal Models Inspect Buildings? A Hierarchical Benchmark for Structural Pathology Reasoning [7.005450139695288]
  Large Multimodal Models (LMMs) promise a paradigm shift toward active reasoning.<n>We present textitDefectBench, the first benchmark designed to interrogate LMMs beyond basic semantic recognition.<n>This work provides both a rigorous benchmarking standard and a high-quality open-source database.
  arXiv  Detail & Related papers  (2026-03-20T17:24:46Z)
• Rethinking Federated Graph Foundation Models: A Graph-Language Alignment-based Approach [8.517604507672262]
  Recent studies of federated graph foundational models (FedGFMs) break the idealized and untenable assumption of having centralized data storage to train graph foundation models.<n>Existing studies that project aligned generalizable knowledge onto a discrete token space via vector-quantized backbones suffer from irreversible knowledge loss during the quantization process.
  arXiv  Detail & Related papers  (2026-01-29T07:50:00Z)
• Closed-Loop LLM Discovery of Non-Standard Channel Priors in Vision Models [48.83701310501069]
  Large Language Models (LLMs) offer a transformative approach to Neural Architecture Search (NAS)<n>We formulate the search as a sequence of conditional code generation tasks, where an LLM refines architectural specifications based on performance telemetry.<n>We generate a vast corpus of valid, shape-consistent architectures via Abstract Syntax Tree (AST) mutations.<n> Experimental results on CIFAR-100 validate the efficacy of this approach, demonstrating that the model yields statistically significant improvements in accuracy.
  arXiv  Detail & Related papers  (2026-01-13T13:00:30Z)
• Consolidation or Adaptation? PRISM: Disentangling SFT and RL Data via Gradient Concentration [56.074760766965085]
  PRISM achieves a dynamics-aware framework that arbitrates data based on its degree of cognitive conflict with the model's existing knowledge.<n>Our findings suggest that disentangling data based on internal optimization regimes is crucial for scalable and robust agent alignment.
  arXiv  Detail & Related papers  (2026-01-12T05:43:20Z)
• Knowledge-to-Data: LLM-Driven Synthesis of Structured Network Traffic for Testbed-Free IDS Evaluation [0.4893345190925178]
  This paper investigates whether Large Language Models (LLMs) can operate as controlled knowledge-to-data engines for generating structured synthetic network traffic datasets.<n>We propose a methodology that combines protocol documentation, attack semantics, and explicit statistical rules to condition LLMs without fine-tuning or access to raw samples.<n>Results show that, under explicit constraints, LLM-generated datasets can closely approximate the statistical and structural characteristics of real network traffic.
  arXiv  Detail & Related papers  (2026-01-08T15:31:33Z)
• From Indoor to Open World: Revealing the Spatial Reasoning Gap in MLLMs [65.04549036809557]
  We introduce a benchmark built from pedestrian-perspective videos captured with synchronized stereo cameras, LiDAR, and IMU/GPS sensors.<n>This dataset provides metrically precise 3D information, enabling the automatic generation of spatial reasoning questions.<n> Evaluations reveal that the performance gains observed in structured indoor benchmarks vanish in open-world settings.
  arXiv  Detail & Related papers  (2025-12-22T18:58:12Z)
• CoT-Saliency: Unified Chain-of-Thought Reasoning for Heterogeneous Saliency Tasks [96.64597365827046]
  We present the first unified framework that jointly handles three operationally heterogeneous saliency tasks.<n>We introduce a Chain-of-Thought (CoT) reasoning process in a Vision-Language Model (VLM) to bridge task heterogeneity.<n>We show our model matches or outperforms specialized SOTA methods and strong closed-source VLMs across all tasks.
  arXiv  Detail & Related papers  (2025-11-01T04:37:01Z)
• Loong: Synthesize Long Chain-of-Thoughts at Scale through Verifiers [103.4410890572479]
  We introduce the Loong Project: an open-source framework for scalable synthetic data generation and verification.<n>LoongBench is a curated seed dataset containing 8,729 human-vetted examples across 12 domains.<n>LoongEnv is a modular synthetic data generation environment that supports multiple prompting strategies to produce new question-answer-code triples.
  arXiv  Detail & Related papers  (2025-09-03T06:42:40Z)
• LMAR: Language Model Augmented Retriever for Domain-specific Knowledge Indexing [42.51773265892766]
  Retrieval Augmented Generation (RAG) systems often struggle with domain-specific knowledge due to performance deterioration of pre-trained embeddings.<n>We propose LMAR (Language Model Augmented Retriever), a model-agnostic framework that addresses these challenges by combining LLM-guided data synthesis with contrastive embedding adaptation and efficient text clustering.
  arXiv  Detail & Related papers  (2025-08-04T16:59:43Z)
• DREAMS: Density Functional Theory Based Research Engine for Agentic Materials Simulation [1.3821435284269523]
  We introduce the DFT-based Research Engine for Agentic Materials Screening (DREAMS)<n>DREAMS is a hierarchical, multi-agent framework for DFT simulation that combines a central Large Language Model (LLM) planner agent with domain-specific LLM agents.<n>We validate DREAMS capabilities on the Sol27LC lattice-constant benchmark, achieving average errors below 1% compared to the results of human DFT experts.
  arXiv  Detail & Related papers  (2025-07-18T15:26:04Z)
• A Large Language Model-Empowered Agent for Reliable and Robust Structural Analysis [14.754785659805869]
  Large language models (LLMs) have exhibited remarkable capabilities across diverse open-domain tasks, yet their application in specialized domains such as civil engineering remains largely unexplored.<n>This paper starts bridging this gap by evaluating and enhancing the reliability and robustness of LLMs in structural analysis of beams.<n> Experimental results demonstrate that the agent achieves accuracy exceeding 99.0% on the benchmark dataset, exhibiting reliable and robust performance across diverse conditions.
  arXiv  Detail & Related papers  (2025-06-27T04:16:53Z)
• TopoFR: A Closer Look at Topology Alignment on Face Recognition [58.45515807380505]
  We propose TopoFR, a novel FR model that leverages a topological structure alignment strategy called PTSA and a hard sample mining strategy named SDE.<n> PTSA uses persistent homology to align the topological structures of the input and latent spaces, effectively preserving the structure information and improving the generalization performance of FR model.<n> Experimental results on popular face benchmarks demonstrate the superiority of our TopoFR over the state-of-the-art methods.
  arXiv  Detail & Related papers  (2024-10-14T14:58:30Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.