Think Silently, Think Fast: Dynamic Latent Compression of LLM Reasoning Chains
원문 초록
Large Language Models (LLMs) achieve superior performance through Chain-of-Thought (CoT) reasoning, but these token-level reasoning chains are computationally expensive and inefficient. In this paper, we introduce Compressed Latent Reasoning (CoLaR), a novel framework that dynamically compresses reasoning processes in latent space through a two-stage training approach. First, during supervised fine-tuning, CoLaR extends beyond next-token prediction by incorporating an auxiliary next compressed embedding prediction objective. This process merges embeddings of consecutive tokens using a compression factor randomly sampled from a predefined range, and trains a specialized latent head to predict distributions of subsequent compressed embeddings. Second, we enhance CoLaR through reinforcement learning (RL) that leverages the latent head's non-deterministic nature to explore diverse reasoning paths and exploit more compact ones. This approach enables CoLaR to: i) perform reasoning at a dense latent level (i.e., silently), substantially reducing reasoning chain length, and ii) dynamically adjust reasoning speed at inference time by simply prompting the desired compression factor. Extensive experiments across four mathematical reasoning datasets demonstrate that CoLaR achieves 14.1% higher accuracy than latent-based baseline methods at comparable compression ratios, and reduces reasoning chain length by 53.3% with only 4.8% performance degradation compared to explicit CoT method. Moreover, when applied to more challenging mathematical reasoning tasks, our RL-enhanced CoLaR demonstrates performance gains of up to 5.4% while dramatically reducing latent reasoning chain length by 82.8%. The code and models will be released upon acceptance.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Reasoning or Memorization? Unreliable Results of Reinforcement Learning Due to Data Contamination
A Practical Two-Stage Recipe for Mathematical LLMs: Maximizing Accuracy with SFT and Efficiency with Reinforcement Learning
Confucius3-Math: A Lightweight High-Performance Reasoning LLM for Chinese K-12 Mathematics Learning
RePO: Replay-Enhanced Policy Optimization
VAR-MATH: Probing True Mathematical Reasoning in Large Language Models via Symbolic Multi-Instance Benchmarks
AdapThink: Adaptive Thinking Preferences for Reasoning Language Model
토론
이 논문과 연결된 포럼 글이 아직 없습니다.