Steering Large Reasoning Models towards Concise Reasoning via Flow Matching
Large Reasoning Models (LRMs) excel at complex reasoning tasks, but their efficiency is often hampered by overly verbose outputs. Prior steering methods attempt to address this issue by applying a single, global vector to hidden representations -- an approach grounded in the restrictive linear representation hypothesis. In this work, we introduce FlowSteer, a nonlinear steering method that goes beyond uniform linear shifts by learning a complete transformation between the distributions associated with verbose and concise reasoning. This transformation is learned via Flow Matching as a velocity field, enabling precise, input-dependent control over the model's reasoning process. By aligning steered representations with the distribution of concise-reasoning activations, FlowSteer yields more compact reasoning than the linear shifts. Across diverse reasoning benchmarks, FlowSteer demonstrates strong task performance and token efficiency compared to leading inference-time baselines. Our work demonstrates that modeling the full distributional transport with generative techniques offers a more effective and principled foundation for controlling LRMs.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Activation Steering for Chain-of-Thought Compression
Large language models (LLMs) excel at complex reasoning when they include intermediate steps, known as "chains of thought" (CoTs). However, these rationales are often overly verbose, even for simple problems, leading to …
GSM8KMathCAC-CoT: Connector-Aware Compact Chain-of-Thought for Efficient Reasoning Data Synthesis Across Dual-System Cognitive Tasks
Long chain-of-thought (CoT) prompting helps Large Language Models (LLMs) solve difficult problems, but very long traces often slow or even degrade performance on fast, intuitive "System-1" tasks. We introduce Connector-A…
Concise and Organized Perception Facilitates Reasoning in Large Language Models
Exploiting large language models (LLMs) to tackle reasoning has garnered growing attention. It still remains highly challenging to achieve satisfactory results in complex logical problems, characterized by plenty of prem…
LAMBADAMathKV Cache Steering for Controlling Frozen LLMs
We propose cache steering, a lightweight method for implicit steering of language models via a one-shot intervention applied directly to the key-value cache. To validate its effectiveness, we apply cache steering to indu…
Prototype-Based Dynamic Steering for Large Language Models
Despite impressive breadth, LLMs still rely on explicit reasoning instructions or static, one-fits-all steering methods, leaving a gap for adaptive, instruction-free reasoning amplification. We present Prototype-Based Dy…
Prompt Engineering