mlsanityData to 7 Oct 2026

Dependency-Aware Chain-of-Thought Compression for Financial Reasoning

arXiv 2609.00413 ↗First posted 10 Jul 2026cs.AIcited by 0

On the map: LLM reasoning → Test-time compute and efficient thinking

Abstract (arXiv)

Chain of thought prompting improves complex reasoning, but its long intermediate traces create substantial inference cost and hinder practical deployment in financial settings. We present a Hierarchical Semantic Distillation Network, HSDN, for compressing reasoning chains while preserving answer accuracy and logical coherence. The framework combines semantic segmentation, dependency graph construction, dual encoder importance scoring, constrained segment selection, and local boundary rewriting. A frozen Qwen3 4B model is used only for feature extraction and final answer generation, while the compression process remains structured and interpretable. On the AFAC2025 benchmark, HSDN achieves 91.0% accuracy with 68.4% compression, outperforming strong compression baselines in overall score and reasoning coherence. The results show that graph guided compression is effective for high stakes financial reasoning tasks.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Test-time compute and efficient thinking, one of 17 directions in LLM reasoning. Builds on 11 of its 17 references that are in the map. First posted on arXiv 10 Jul 2026.

Builds on

11 of 17 references.

Closest ancestors · 1

Same direction, newest first

  1. 2023Tree of Thoughts: Deliberate Problem Solving with Large Language Models17 May

Other references · 10

  1. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
  2. 2022Large Language Models are Zero-Shot Reasonerscited by 4,323
  3. 2020Longformer: The Long-Document Transformercited by 3,362
  4. 2020Big Bird: Transformers for Longer Sequencescited by 1,673
  5. 2020Heterogeneous Graph Neural Networks for Extractive Document Summarizationcited by 90
  6. 2021PRIMERA: Pyramid-based Masked Sentence Pre-training for Multi-document Summarizationcited by 62
  7. 2022FactPEGASUS: Factuality-Aware Pre-training and Fine-tuning for Abstractive Summarizationcited by 49
  8. 2021TR-BERT: Dynamic Token Reduction for Accelerating BERT Inferencecited by 40
  9. 2026Resilient Routing: Risk-Aware Dynamic Routing in Smart Logistics via Spatiotemporal Graph Learningcited by 12
  10. 2026EAGLE: Edge-Aware Graph Learning for Proactive Delivery Delay Prediction in Smart Logistics Networkscited by 2

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026SYNLAT: Syntax-Aligned Text-Latent Compression for Chain-of-Thought Reasoning
  2. 2026Memory Augmentation Unlocks Efficient Chain-of-Thought Reasoning
  3. 2026Chain Of Thought Compression: A Theoretical Analysis
  4. 2026Towards Efficient Large Language Reasoning Models via Extreme-Ratio Chain-of-Thought Compression
  5. 2025How Well do LLMs Compress Their Own Chain-of-Thought? A Token Complexity Approach
  6. 2026RuPLaR : Efficient Latent Compression of LLM Reasoning Chains with Rule-Based Priors From Multi-Step to One-Step
  7. 2025ConCISE: Confidence-guided Compression in Step-by-step Efficient Reasoning
  8. 2026Every Token Leaves a Ripple in the Stream of Thought: Eliciting Model-Internal Token Saliency for Chain-of-Thought Compression