paper-with-me

홈 › Papers

Towards Understanding Distilled Reasoning Models: A Representational Approach

2025-03-05 · David D. Baek, Max Tegmark

In this paper, we investigate how model distillation impacts the development of reasoning features in large language models (LLMs). To explore this, we train a crosscoder on Qwen-series models and their fine-tuned variants. Our results suggest that the crosscoder learns features corresponding to various types of reasoning, including self-reflection and computation verification. Moreover, we observe that distilled models contain unique reasoning feature directions, which could be used to steer the model into over-thinking or incisive-thinking mode. In particular, we perform analysis on four specific reasoning categories: (a) self-reflection, (b) deductive reasoning, (c) alternative reasoning, and (d) contrastive reasoning. Finally, we examine the changes in feature geometry resulting from the distillation process and find indications that larger distilled models may develop more structured representations, which correlate with enhanced distillation performance. By providing insights into how distillation modifies the model, our study contributes to enhancing the transparency and reliability of AI systems.

📄 PDF Abstract BibTeX arXiv:2503.03730

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Effectiveness of Chain-of-Thought in Distilling Reasoning Capability from Large Language Models

2025-11-07 · Cong-Thanh Do, Rama Doddipatla, Kate Knill arxiv

Chain-of-Thought (CoT) prompting is a widely used method to improve the reasoning capability of Large Language Models (LLMs). More recently, CoT has been leveraged in Knowledge Distillation (KD) to transfer reasoning cap…

Knowledge Distillation

DeepDistill: Enhancing LLM Reasoning Capabilities via Large-Scale Difficulty-Graded Data Training

2025-04-24 · Xiaoyu Tian, Sitong Zhao, Haotian Wang, Shuaiting Chen 외

Although large language models (LLMs) have recently achieved remarkable performance on various complex reasoning benchmarks, the academic community still lacks an in-depth understanding of base model training processes a…

Mathematical Reasoning

Distilled Dual-Encoder Model for Vision-Language Understanding

2021-12-16 · Zekun Wang, Wenhui Wang, Haichao Zhu, Ming Liu 외

We propose a cross-modal attention distillation framework to train a dual-encoder model for vision-language understanding tasks, such as visual reasoning and visual question answering. Dual-encoder models have a faster i…

Image to textmodelQuestion AnsweringVisual Entailment+3

Beyond Isolated Capabilities: Bridging Long CoT Reasoning and Long-Context Understanding

2025-07-20 · Yifei Wang arxiv

Reasoning distillation has emerged as an effective approach to enhance the reasoning capabilities of smaller language models. However, the impact of large-scale reasoning distillation on other critical abilities, particu…

Long-Context Understanding

Layer Importance for Mathematical Reasoning is Forged in Pre-Training and Invariant after Post-Training

2025-06-27 · Aadim Nepal, Safal Shrestha, Anubhav Shrestha, Minwu Kim 외

Large language models can exhibit improved mathematical reasoning capabilities following post-training with instruction tuning, reinforcement learning, or knowledge distillation. However, it remains unclear whether these…

Knowledge DistillationMathematical Reasoningreinforcement-learningReinforcement Learning