相关论文: GIFT: Reconciling Post-Training Objectives via Fin…

Supervised fine-tuning (SFT) and reinforcement learning (RL) are widely used post-training techniques for foundation models. However, their roles in enhancing model generalization capabilities remain unclear. This paper studies the…

Supervised fine-tuning (SFT) on chain-of-thought (CoT) trajectories demonstrations is a common approach for enabling reasoning in large language models. Standard practices typically only retain trajectories with correct final answers…

We present a controlled study of how dataset contamination interacts with the post-training stages now standard in large language model training pipelines. Starting from clean checkpoints of Qwen2.5 (0.5B/1.5B) and Gemma3 (1B/4B), we inject…

We introduce a novel method that averages the logits of a frozen reference policy (e.g., SFT) and a trainable policy, and incorporate the method into Group Relative Policy Optimization (GRPO). In contrast to Reinforcement Learning with…

Large Language Model (LLM) agents show great promise for complex, multi-turn tool-use tasks, but their development is often hampered by the extreme scarcity of high-quality training data. Supervised fine-tuning (SFT) on synthetic data leads…

One fascinating aspect of pre-trained vision-language models~(VLMs) learning under language supervision is their impressive zero-shot generalization capability. However, this ability is hindered by distribution shifts between the training…

Recent studies have shown that supervised fine-tuning of LLMs on a small number of high-quality datasets can yield strong reasoning capabilities. However, full fine-tuning (Full FT), while powerful, is computationally expensive and…

Instruction tuning, a specialized technique to enhance large language model (LLM) performance via instruction datasets, relies heavily on the quality of employed data. Existing quality improvement methods alter instruction data through…

Language models trained on large-scale datasets have been shown to learn features that encode abstract concepts such as factuality or intent. Such features are traditionally used for test-time monitoring or steering. We present an…

Goal-conditioned policies enable decision-making models to execute diverse behaviors based on specified goals, yet their downstream performance is often highly sensitive to the choice of instructions or prompts. To bypass the limitations of…

Current Large Language Models (LLMs) often undergo supervised fine-tuning (SFT) to acquire tool use capabilities. However, SFT struggles to generalize to unfamiliar or complex tool use scenarios. Recent advancements in reinforcement…

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…

Standard training pipelines for large language models (LLMs) are typically unidirectional, progressing from pre-training to post-training. However, the potential for a bidirectional process--where insights from post-training retroactively…

Large language model post-training methods such as supervised fine-tuning (SFT), reinforcement learning (RL), and distillation are often analyzed through their loss functions: maximum likelihood, policy gradients, forward KL, reverse KL, or…

To overcome the sparse reward challenge in reinforcement learning (RL) for agents based on large language models (LLMs), we propose Mutual Information Self-Evaluation (MISE), an RL paradigm that utilizes hindsight generative self-evaluation…

This paper proposes a novel formulation for reinforcement learning (RL) with large language models, explaining why and under what conditions the true sequence-level reward can be optimized via a surrogate token-level objective in policy…

Outcome-reward reinforcement learning (RL) has proven effective at improving the reasoning capabilities of large language models (LLMs). However, standard RL assigns credit only at the level of the final answer, penalizing entire reasoning…

This paper explores a scientific question in supervised fine-tuning (SFT): why SFT is broadly effective for small-scale deep neural networks, yet can produce inconsistent or even detrimental effects when applied to large language models…

The decentralized Federated Learning (FL) setting avoids the role of a potentially unreliable or untrustworthy central host by utilizing groups of clients to collaboratively train a model via localized training and model/gradient sharing.…

Despite the subjective nature of storytelling, past works on automatic story generation (ASG) have relied on limited ground truths for training and evaluation. In this work, we explore reinforcement learning (d-RLAIF) as a post-training…