相关论文: AIR: Post-training Data Selection for Reasoning vi…

In deep reinforcement learning (RL), data augmentation is widely considered as a tool to induce a set of useful priors about semantic consistency and improve sample efficiency and generalization performance. However, even when the prior is…

Deploying Large Language Models (LLMs) for discriminative workloads is often limited by inference latency, compute, and API costs at scale. Active distillation reduces these costs by querying an LLM oracle to train compact discriminative…

Large language models have demonstrated impressive reasoning capabilities but are inherently limited by their knowledge reservoir. Retrieval-augmented reasoning mitigates this limitation by allowing LLMs to query external resources, but…

Large language models (LLMs) excel in complex reasoning tasks, and distilling their reasoning capabilities into smaller models has shown promise. However, we uncover an interesting phenomenon, which we term the Small Model Learnability Gap:…

Injecting new reasoning knowledge into Large Language Models (LLMs) via post-training often induces catastrophic forgetting. Recent studies emphasize the importance of on-policy data but suggest that KL-divergence fails to mitigate…

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…

Multimodal large language models excel across diverse domains but struggle with complex visual reasoning tasks. To enhance their reasoning capabilities, current approaches typically rely on explicit search or post-training techniques.…

Recent studies have shown that reinforcement learning with verifiable rewards (RLVR) enhances overall accuracy (pass@1) but often fails to improve capability (pass@k) of LLMs in reasoning tasks, while distillation can improve both. In this…

Large Language Models (LLMs) using Chain-of-Thought (CoT) prompting excel at complex reasoning but generate verbose thought processes with considerable redundancy, leading to increased inference costs and reduced efficiency. We introduce a…

The rapid advancement of large language models (LLMs) has significantly advanced the capabilities of artificial intelligence across various domains. However, their massive scale and high computational costs render them unsuitable for direct…

Recent large language models have shown promising capabilities in long-form reasoning, following structured chains of thought before arriving at a final answer. However, we observe that these reasoning paths tend to include substantial…

Distilling the thinking traces of a Large Language Model (LLM) with reasoning capabilities into a smaller model has been proven effective. Yet, there is a scarcity of work done on how model performances scale with the quantity of…

We study distillation for large language models under explicit compute constraints, with the goal of producing student models that are not only cheaper to train, but structurally efficient at inference time. While prior approaches to…

Eliciting "chain of thought" (CoT) rationales -- sequences of token that convey a "reasoning" process -- has been shown to consistently improve LLM performance on tasks like question answering. More recent efforts have shown that such…

Objective: Large Language Models (LLMs) demonstrate significant capabilities in medical text understanding and generation. However, their diagnostic reliability in complex clinical scenarios remains limited. This study aims to enhance LLMs'…

Reasoning models excel at complex tasks such as coding and mathematics, yet their inference is often slow and token-inefficient. To improve the inference efficiency, post-training quantization (PTQ) usually comes with the cost of large…

We present Logics-STEM, a state-of-the-art reasoning model fine-tuned on Logics-STEM-SFT-Dataset, a high-quality and diverse dataset at 10M scale that represents one of the largest-scale open-source long chain-of-thought corpora.…

The prevailing approach to distilling reasoning from Large Language Models (LLMs)-behavioral cloning from textual rationales-is fundamentally limited. It teaches Small Language Models (SLMs) to mimic surface-level patterns rather than the…

Intent, a critical cognitive notion and mental state, is ubiquitous in human communication and problem-solving. Accurately understanding the underlying intent behind questions is imperative to reasoning towards correct answers. However,…

Large Reasoning Language Models (LRLMs or LRMs) demonstrate remarkable capabilities in complex reasoning tasks, but suffer from significant computational inefficiencies due to overthinking phenomena. Existing efficient reasoning methods…