Towards Understanding Distilled Reasoning Models: A Representational Approach
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.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Effectiveness of Chain-of-Thought in Distilling Reasoning Capability from Large Language Models
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 DistillationDeepDistill: Enhancing LLM Reasoning Capabilities via Large-Scale Difficulty-Graded Data Training
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 ReasoningDistilled Dual-Encoder Model for Vision-Language Understanding
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+3Beyond Isolated Capabilities: Bridging Long CoT Reasoning and Long-Context Understanding
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 UnderstandingLayer Importance for Mathematical Reasoning is Forged in Pre-Training and Invariant after Post-Training
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