Dimensions overall score 8.0

GitHub Code Pulse

No public code linked for this paper yet.

• CtrlCoT is a dual-granularity chain-of-thought compression framework that harmonizes semantic abstraction and token-level pruning.method 70%
• CtrlCoT achieves 30.7% fewer tokens on MATH-500 with Qwen2.5-7B-Instruct.result 70%
• CtrlCoT achieves 7.6 percentage points higher accuracy than the strongest baseline on MATH-500 with Qwen2.5-7B-Instruct.result 70%
• Existing CoT compression methods struggle to combine semantic shortening and aggressive token pruning effectively.limitation 70%
• CtrlCoT's Hierarchical Reasoning Abstraction component produces CoTs at multiple semantic granularities.method 70%
• CtrlCoT's Logic-Preserving Distillation component trains a logic-aware pruner to retain indispensable reasoning cues.method 70%
• CtrlCoT's Distribution-Alignment Generation component aligns compressed traces with fluent inference-time reasoning styles.method 70%
• The approach may not generalize to all LLM applications and risks losing critical information in reasoning for tasks outside tested domains.limitation 70%

Competitive landscape

Competitor map is still being generated for this paper. Enable generation or check back soon.

Startup potential card