Related papers: Improving Reasoning Capabilities in Small Models t…
Chain-of-Thought (CoT) reasoning is a critical capability for large language models (LLMs), enabling them to tackle com- plex multi-step tasks. While base LLMs, pre-trained on general text corpora, often struggle with reasoning due to a…
Knowledge Distillation (KD) can transfer the reasoning abilities of large models to smaller ones, which can reduce the costs to generate Chain-of-Thoughts for reasoning tasks. KD methods typically ask the student to mimic the teacher's…
Chain-of-Thought (CoT) is a critical technique in enhancing the reasoning ability of Large Language Models (LLMs), and latent reasoning methods have been proposed to accelerate the inefficient token-level reasoning chain. We notice that…
Multi-step reasoning ability of large language models is crucial in tasks such as math and tool utilization. Current researches predominantly focus on enhancing model performance in these multi-step reasoning tasks through fine-tuning with…
Chain-of-thought (CoT) distillation trains a smaller model to imitate a teacher's reasoning trace, but it is typically evaluated by final-answer metrics including accuracy. We ask whether gains in answer quality are accompanied by…
Large Language Models (LLMs) excel at multi-step reasoning problems with explicit chain-of-thought (CoT), but verbose traces incur significant computational costs and memory overhead, and often carry redundant, stylistic artifacts. Latent…
Chain-of-Thought (CoT) prompting has emerged as a powerful approach to enhancing the reasoning capabilities of Large Language Models (LLMs). However, existing implementations, such as in-context learning and fine-tuning, remain costly and…
Chain-of-thought (CoT) reasoning has exhibited impressive performance in language models for solving complex tasks and answering questions. However, many real-world questions require multi-modal information, such as text and images.…
Few-shot Chain-of-Thought (CoT) prompting has demonstrated strong performance in improving the reasoning capabilities of large language models (LLMs). While theoretical investigations have been conducted to understand CoT, the underlying…
While large audio language models excel at tasks like ASR and emotion recognition, they still struggle with complex reasoning due to the modality gap between audio and text as well as the lack of structured intermediate supervision. To…
Recent advancements in large language models (LLMs) have demonstrated remarkable reasoning capabilities through long chain-of-thought (CoT) reasoning. The R1 distillation scheme has emerged as a promising approach for training…
The rapid advancement of large language models (LLMs) has significantly enhanced their reasoning abilities, enabling increasingly complex tasks. However, these capabilities often diminish in smaller, more computationally efficient models…
Distilling large reasoning models is essential for making Long-CoT reasoning practical, as full-scale inference remains computationally prohibitive. Existing curation-based approaches select complete reasoning traces post-hoc, overlooking…
Reasoning-enhanced large language models (RLLMs), whether explicitly trained for reasoning or prompted via chain-of-thought (CoT), have achieved state-of-the-art performance on many complex reasoning tasks. However, we uncover a surprising…
Accurate clinical diagnosis requires extensive domain knowledge and complex clinical reasoning capabilities. Although large language models (LLMs) hold great potential for clinical reasoning, their high computational and memory requirements…
Reasoning distillation transfers complex reasoning abilities from large language models (LLMs) to smaller ones, yet its success depends on how well the training data align with the student model. This paper introduces the Data-Model…
This work addresses the challenge of democratizing advanced Large Language Models (LLMs) by compressing their mathematical reasoning capabilities into sub-billion parameter Small Language Models (SLMs) without compromising performance. We…
Knowledge distillation (KD) is a technique for transferring knowledge from complex teacher models to simpler student models, significantly enhancing model efficiency and accuracy. It has demonstrated substantial advancements in various…
Distilling reasoning traces from strong large language models into smaller ones is a promising route to improve intelligence in resource-constrained settings. Existing approaches face a fundamental trade-off: offline distillation from…
Knowledge distillation is considered as a training and compression strategy in which two neural networks, namely a teacher and a student, are coupled together during training. The teacher network is supposed to be a trustworthy predictor…