Model Releases
Dependency-Aware Chain-of-Thought Compression for Financial Reasoning
arXiv:2609.00413v1 Announce Type: new Abstract: Chain of thought prompting improves complex reasoning, but its long intermediate traces create substantial inference cost and hinder practical deploymen
arXiv:2609.00413v1 Announce Type: new Abstract: 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.
Related
- Does Verbose Chain-of-Thought Really Help? In-Distribution Evidence that Content, Not Length, Matters
- Shorter, but Still Trustworthy? An Empirical Study of Chain-of-Thought Compression
- When Chain-of-Thought Helps and When It Hurts: An Empirical Investigation of the Serial-Depth Bottleneck in LLM Reasoning
- Chain Of Thought Compression: A Theoretical Analysis
Source: arXiv cs.AI | 2026-09-02