相关论文: Self-play with Execution Feedback: Improving Instr…

Reinforcement Learning from Human Feedback (RLHF) is popular in large language models (LLMs), whereas traditional Reinforcement Learning (RL) often falls short. Current autonomous driving methods typically utilize either human feedback in…

Large "instruction-tuned" language models (i.e., finetuned to respond to instructions) have demonstrated a remarkable ability to generalize zero-shot to new tasks. Nevertheless, they depend heavily on human-written instruction data that is…

Language model (LM) post-training relies on two stages of human supervision: task demonstrations for supervised finetuning (SFT), followed by preference comparisons for reinforcement learning from human feedback (RLHF). As LMs become more…

Following the initial flourishing of large language models (LLMs), there has been a surge in proposed large vision-language models (LVLMs) that integrate LLMs with vision capabilities. However, it has been observed that LVLMs, after tuning…

Large Language Models (LLMs) have demonstrated remarkable progress in complex reasoning tasks through both post-training and test-time scaling laws. While prevalent test-time scaling approaches are often realized by using external reward…

Prior work has shown that finetuning large language models (LLMs) using machine-generated instruction-following data enables such models to achieve remarkable zero-shot capabilities on new tasks, and no human-written instructions are…

As applications of large language models (LLMs) become increasingly complex, the demand for robust complex instruction following capabilities is growing accordingly. We argue that a thorough understanding of the instruction itself,…

The promise of generative AI to revolutionize education is constrained by the pedagogical limits of large language models (LLMs). A major issue is the lack of access to high-quality training data that reflect the learning of actual…

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 (LLMs) could be valuable personal AI agents across various domains, provided they can precisely follow user instructions. However, recent studies have shown significant limitations in LLMs' instruction-following…

Instruction fine-tuning is crucial for today's large language models (LLMs) to learn to follow instructions and align with human preferences. Conventionally, supervised data, including the instruction and the correct response, is required…

Human preference alignment can greatly enhance Multimodal Large Language Models (MLLMs), but collecting high-quality preference data is costly. A promising solution is the self-evolution strategy, where models are iteratively trained on…

Despite rapid advances in the capabilities of Large Language Models (LLMs), they continue to struggle with following relatively simple and unambiguous instructions, particularly when compositional structure is involved. Recent work suggests…

Training large language model (LLM) agents to acquire necessary skills and perform diverse tasks within an environment is gaining interest as a means to enable open-endedness. However, creating the training dataset for their skill…

The rapid advancement of large language models (LLMs) has led to growing interest in using synthetic data to train future models. However, this creates a self-consuming retraining loop, where models are trained on their own outputs and may…

Personalized alignments for individual users have been a long-standing goal in large language models (LLMs). We introduce Drift, a novel framework that personalizes LLMs at decoding time with implicit user preferences. Traditional…

Large language models (LLMs) hold the promise of solving diverse tasks when provided with appropriate natural language prompts. However, prompting often leads models to make predictions with lower accuracy compared to finetuning a model…

Large language models (LLMs) often generate inaccurate or fabricated information and generally fail to indicate their confidence, which limits their broader applications. Previous work elicits confidence from LLMs by direct or…

Recent large language models (LLMs) are promising for making decisions in grounded environments. However, LLMs frequently fail in complex decision-making tasks due to the misalignment between the pre-trained knowledge in LLMs and the actual…

Aligning large language models (LLMs) with human preferences is crucial for enhancing their utility in terms of helpfulness, truthfulness, safety, harmlessness, and interestingness. Existing methods for achieving this alignment often…