{"ID":2859101,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.05498","arxiv_id":"2510.05498","title":"Prototype-Based Dynamic Steering for Large Language Models","abstract":"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 Dynamic Steering (PDS), a test-time method that amplifies large language model (LLM) reasoning without adding or altering instructions. We introduce \"reasoning prototypes\" by clustering activation differences between Chain-of-Thought (CoT) and neutral prompts. At inference, an input's hidden state is projected onto these prototypes to form an instance-specific steering vector. Evaluated on GSM8K, AQuA-RAT, and BIG-Bench tasks, PDS consistently improves accuracy without fine-tuning or prompt engineering. Notably, the gains persist even when CoT is explicitly suppressed to improve cost-efficiency, indicating that the intervention strengthens latent reasoning processes rather than inducing a superficial behavioral shift. These results position dynamic, prototype-guided steering as a lightweight alternative to training-time approaches for enhancing LLM reasoning.","short_abstract":"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 Dynamic Steering (PDS), a test-time method that amplifies large language model (LLM) reasoning without...","url_abs":"https://arxiv.org/abs/2510.05498","url_pdf":"https://arxiv.org/pdf/2510.05498v1","authors":"[\"Ceyhun Efe Kayan\",\"Li Zhang\"]","published":"2025-10-07T01:34:28Z","proceeding":"cs.CL","tasks":"[\"cs.CL\"]","methods":"[\"Large Language Model\",\"Language Model\"]","has_code":false}