Too Long, Do Re-weighting for Efficient LLM Reasoning Compression

ACL ARR 2026 January Submission9428 Authors

Keywords: LLM, Reasoning

Abstract: Large Language Models (LLMs) have recently achieved remarkable progress on complex reasoning tasks by leveraging extended Chain-of-Thought (CoT) techniques. These reasoning processes can be roughly categorized into System-1 (fast and intuitive) and System-2 (slow and deliberate) paradigms. However, excessive reliance on lengthy System-2-style reasoning during inference can produce extremely long outputs, thereby reducing efficiency. In this work, we propose Thinking Length Data Re-weighting (TLDR), that does not rely on sophisticated data annotations or interpolation between multiple models. We continuously balance the weights between the model's System-1 and System-2 data to eliminate redundant reasoning processes while preserving the model's reasoning capability. We validate our method across multiple base models, including Deepseek-R1-Distilled Qwen models, as well as on a diverse benchmarks with varying difficulty levels. Our method significantly reduces the number of output tokens by nearly 40\% while maintaining the accuracy of the reasoning. Our code and data are at link: https://anonymous.4open.science/r/TLDR_Review-BBE5/.

Paper Type: Long

Research Area: NLP Applications

Research Area Keywords: LLM Reasoning, Efficient LLM

Contribution Types: Model analysis & interpretability, NLP engineering experiment, Approaches low compute settings-efficiency

Languages Studied: English

Submission Number: 9428