Related papers: NFT: Bridging Supervised Learning and Reinforcemen…
Current post-training methodologies for adapting Large Vision-Language Models (LVLMs) generally fall into two paradigms: Supervised Fine-Tuning (SFT) and Reinforcement Learning (RL). Despite their prevalence, both approaches suffer from…
Supervised Fine-Tuning (SFT) has been a go-to and effective method for enhancing long chain-of-thought (CoT) reasoning in relatively small LLMs by fine-tuning them with long CoT responses from larger LLMs. To continually improve reasoning…
Previous study suggest that powerful Large Language Models (LLMs) trained with Reinforcement Learning with Verifiable Rewards (RLVR) only refines reasoning path without improving the reasoning capacity in math tasks while…
Large Reasoning Models (LRMs) have recently shown impressive performance on complex reasoning tasks, often by engaging in self-reflective behaviors such as self-critique and backtracking. However, not all reflections are beneficial-many are…
Extending large language models (LLMs) to low-resource languages often incurs an "alignment tax": improvements in the target language come at the cost of catastrophic forgetting in general capabilities. We argue that this trade-off arises…
Alignment methodologies have emerged as a critical pathway for enhancing language model alignment capabilities. While SFT (supervised fine-tuning) accelerates convergence through direct token-level loss intervention, its efficacy is…
The alignment of large language models (LLMs) is crucial not only for unlocking their potential in specific tasks but also for ensuring that responses meet human expectations and adhere to safety and ethical principles. Current alignment…
As language models (LMs) demonstrate their capabilities in various fields, their application to tasks requiring multi-round interactions has become increasingly popular. These tasks usually have complex dynamics, so supervised fine-tuning…
We investigate the effectiveness of reinforcement learning methods for finetuning large language models when transitioning from offline to semi-online to fully online regimes for both verifiable and non-verifiable tasks. Our experiments…
Reinforcement finetuning (RFT) has become a standard approach for enhancing the reasoning capabilities of large language models (LLMs). However, its impact on model trustworthiness remains underexplored. In this work, we identify and…
We have witnessed that strong LLMs like Qwen-Math, MiMo, and Phi-4 possess immense reasoning potential inherited from the pre-training stage. With reinforcement learning (RL), these models can improve dramatically on reasoning tasks. Recent…
Large Vision-Language Action (VLA) models have shown significant potential for embodied AI. However, their predominant training via supervised fine-tuning (SFT) limits generalization due to susceptibility to compounding errors under…
The recent success of supervised learning methods on ever larger offline datasets has spurred interest in the reinforcement learning (RL) field to investigate whether the same paradigms can be translated to RL algorithms. This research…
We tackle the problem of aligning pre-trained large language models (LMs) with human preferences. If we view text generation as a sequential decision-making problem, reinforcement learning (RL) appears to be a natural conceptual framework.…
Post-training paradigms for Large Language Models (LLMs), primarily Supervised Fine-Tuning (SFT) and Reinforcement Learning (RL), face a fundamental dilemma: SFT provides stability (low variance) but suffers from high fitting bias, while RL…
Alignment, endowing a pre-trained Large language model (LLM) with the ability to follow instructions, is crucial for its real-world applications. Conventional supervised fine-tuning (SFT) methods formalize it as causal language modeling…
Aligning human preference and value is an important requirement for contemporary foundation models. State-of-the-art techniques such as Reinforcement Learning from Human Feedback (RLHF) often consist of two stages: 1) supervised fine-tuning…
Reinforcement learning (RL) has become the dominant paradigm for improving the performance of language models on complex reasoning tasks. Despite the substantial empirical gains demonstrated by RL-based training methods like GRPO, a…
Reinforcement learning with AI feedback (RLAIF) is a popular paradigm for improving the instruction-following abilities of powerful pre-trained language models. RLAIF first performs supervised fine-tuning (SFT) using demonstrations from a…
Large language models often require fine-tuning to better align their behavior with user intent at deployment. Existing approaches are commonly divided into online and offline paradigms. Online methods, such as RL-based alignment, can…