相关论文: ThinkTuning: Instilling Cognitive Reflections with…

Self-training approach for large language models (LLMs) improves reasoning abilities by training the models on their self-generated rationales. Previous approaches have labeled rationales that produce correct answers for a given question as…

Humans learn social norms and behaviors from verbal feedback (e.g., a parent saying "that was rude" or a friend explaining "here's why that hurt"). Yet, learning from feedback for LLMs has largely focused on domains like code and math,…

While Large Language Models (LLMs) have emerged with remarkable capabilities in complex tasks through Chain-of-Thought reasoning, practical resource constraints have sparked interest in transferring these abilities to smaller models.…

Instruction tuning is a widely used approach to improve the instruction-following ability of large language models (LLMs). Instruction-tuning datasets typically include a mixture of context-augmented and context-free examples, yet prior…

Training Large Language Models (LLMs) for chain-of-thought reasoning presents a significant challenge: supervised fine-tuning on a single "golden" rationale hurts generalization as it penalizes equally valid alternatives, whereas…

Large Language Models (LLMs) have exhibited strong reasoning capabilities and achieved remarkable performance in mathematical problem-solving tasks. Recently, distilling reasoning ability from long-form Chains-of-Thought (CoTs) has emerged…

Many state-of-the-art LLMs are trained to think before giving their answer. Reasoning can greatly improve language model capabilities, but it also makes them less interactive: given a new input, a model must stop thinking before it can…

Parallel thinking has emerged as a novel approach for enhancing the reasoning capabilities of large language models (LLMs) by exploring multiple reasoning paths concurrently. However, activating such capabilities through training remains…

Large language models (LLMs) with Chain-of-Thought (CoT) reasoning have achieved strong performance across diverse tasks, including mathematics, coding, and general reasoning. A distinctive ability of these reasoning models is…

Large language models (LLMs) are increasingly used to generate feedback, yet their impact on learning remains underexplored, especially compared to existing feedback methods. This study investigates how on-demand LLM-generated explanatory…

We study the process through which reasoning models trained with reinforcement learning on verifiable rewards (RLVR) can learn to solve new problems. We find that RLVR drives performance in two main ways: (1) by compressing pass@$k$ into…

Current LLM post-training methods optimize complete reasoning trajectories through Supervised Fine-Tuning (SFT) followed by outcome-based Reinforcement Learning (RL). While effective, a closer examination reveals a fundamental gap: this…

Recent years have witnessed significant progress in large language models' (LLMs) reasoning, which is largely due to the chain-of-thought (CoT) approaches, allowing models to generate intermediate reasoning steps before reaching the final…

Large language models (LMs) beyond a certain scale, demonstrate the emergent capability of generating free-text rationales for their predictions via chain-of-thought (CoT) prompting. While CoT can yield dramatically improved performance,…

Enabling Large Language Models (LLMs) to continuously improve from environmental interactions is a central challenge in post-training. While on-policy self-distillation offers a promising paradigm, existing methods predominantly treat…

Recently, reinforcement learning (RL) has been shown to greatly enhance the reasoning capabilities of large language models (LLMs), and RL-based approaches have been progressively applied to visual multimodal tasks. However, the audio…

Large Language Models (LLMs) continue to set new standards in knowledge-intensive and complex reasoning tasks, yet their high computational demands limit widespread adoption. While distilling large models into smaller ones offers a…

Training tool-augmented LLMs has emerged as a promising approach to enhancing language models' capabilities for complex tasks. The current supervised fine-tuning paradigm relies on constructing extensive domain-specific datasets to train…

Tutoring is an effective instructional method for enhancing student learning, yet its success relies on the skill and experience of the tutors. This reliance presents challenges for the widespread implementation of tutoring, particularly in…

The success of RL for LLM post-training stems from an unreasonably uninformative source: a single bit of information per rollout as binary reward or preference label. At the other extreme, distillation offers dense supervision but requires…