Focused Chain-of-Thought: Efficient LLM Reasoning via Structured Input Information
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917108500135936 |
|---|---|
| author | Struppek, Lukas Hintersdorf, Dominik Struppek, Hannah Neider, Daniel Kersting, Kristian |
| author_facet | Struppek, Lukas Hintersdorf, Dominik Struppek, Hannah Neider, Daniel Kersting, Kristian |
| contents | Recent large language models achieve strong reasoning performance by generating detailed chain-of-thought traces, but this often leads to excessive token use and high inference latency. Existing efficiency approaches typically focus on model-centric interventions, such as reinforcement learning or supervised fine-tuning, to reduce verbosity. In contrast, we propose a training-free, input-centric approach. Inspired by cognitive psychology, we introduce Focused Chain-of-Thought (F-CoT), which separates information extraction from the reasoning process. F-CoT first organizes the essential information from a query into a concise, structured context and then guides the model to reason exclusively over this context. By preventing attention to irrelevant details, F-CoT naturally produces shorter reasoning paths. On arithmetic word problems, F-CoT reduces generated tokens by 2-3x while maintaining accuracy comparable to standard zero-shot CoT. These results highlight structured input as a simple yet effective lever for more efficient LLM reasoning. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_22176 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Focused Chain-of-Thought: Efficient LLM Reasoning via Structured Input Information Struppek, Lukas Hintersdorf, Dominik Struppek, Hannah Neider, Daniel Kersting, Kristian Computation and Language Artificial Intelligence Recent large language models achieve strong reasoning performance by generating detailed chain-of-thought traces, but this often leads to excessive token use and high inference latency. Existing efficiency approaches typically focus on model-centric interventions, such as reinforcement learning or supervised fine-tuning, to reduce verbosity. In contrast, we propose a training-free, input-centric approach. Inspired by cognitive psychology, we introduce Focused Chain-of-Thought (F-CoT), which separates information extraction from the reasoning process. F-CoT first organizes the essential information from a query into a concise, structured context and then guides the model to reason exclusively over this context. By preventing attention to irrelevant details, F-CoT naturally produces shorter reasoning paths. On arithmetic word problems, F-CoT reduces generated tokens by 2-3x while maintaining accuracy comparable to standard zero-shot CoT. These results highlight structured input as a simple yet effective lever for more efficient LLM reasoning. |
| title | Focused Chain-of-Thought: Efficient LLM Reasoning via Structured Input Information |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2511.22176 |