相关论文: SLIME: Stabilized Likelihood Implicit Margin Enfor…

Large language models (LLMs) have emerged as a powerful foundation for intelligent reasoning and decision-making, demonstrating substantial impact across a wide range of domains and applications. However, their massive parameter scales and…

For aligning large language models (LLMs), prior work has leveraged reinforcement learning via human feedback (RLHF) or variations of direct preference optimization (DPO). While DPO offers a simpler framework based on maximum likelihood…

Reinforcement learning (RL) has become a predominant technique to align language models (LMs) with human preferences or promote outputs which are deemed to be desirable by a given reward function. Standard RL approaches optimize average…

Aligning Large Language Models (LLMs) to human preferences in content, style, and presentation is challenging, in part because preferences are varied, context-dependent, and sometimes inherently ambiguous. While successful, Reinforcement…

Reinforcement learning from human feedback (RLHF) has become the dominant paradigm for aligning large language models with human preferences. However, policy gradient methods such as PPO suffer from high variance gradient estimates,…

Preference-based reinforcement learning (RL) offers a promising approach for aligning policies with human intent but is often constrained by the high cost of human feedback. In this work, we introduce PrefVLM, a framework that integrates…

Reinforcement Learning from Human Feedback (RLHF) is the standard method to align Large Language Models (LLMs) with human preferences. In this work, we introduce alignment tampering, a potential vulnerability where the LLM undergoing…

As black-box machine learning models grow in complexity and find applications in high-stakes scenarios, it is imperative to provide explanations for their predictions. Although Local Interpretable Model-agnostic Explanations (LIME) [22] is…

Aligning large language models (LLMs) with human values and intentions is crucial for their utility, honesty, and safety. Reinforcement learning from human feedback (RLHF) is a popular approach to achieve this alignment, but it faces…

The generated responses of large language models (LLMs) are often fine-tuned to human preferences through a process called reinforcement learning from human feedback (RLHF). As RLHF relies on a challenging training sequence, whereby a…

Large language model (LLM) alignment is typically achieved through learning from human preference comparisons, making the quality of preference data critical to its success. Existing studies often pre-process raw training datasets to…

Adapting large language models (LLMs) for specific tasks usually involves fine-tuning through reinforcement learning with human feedback (RLHF) on preference data. While these data often come from diverse labelers' groups (e.g., different…

Alignment is vital for safely deploying large language models (LLMs). Existing techniques are either reward-based (training a reward model on preference pairs and optimizing with reinforcement learning) or reward-free (directly fine-tuning…

Large Language Models (LLMs) have demonstrated unprecedented generative capabilities, yet their alignment with human values remains critical for ensuring helpful and harmless deployments. While Reinforcement Learning from Human Feedback…

Standard methods for aligning large language models with human preferences learn from pairwise comparisons among sampled candidate responses and regularize toward a reference policy. Despite their effectiveness, the effects of sampling and…

This paper presents PRISM: an instruction-conditioned refinement method for imitation policies in robotic manipulation. This approach bridges Imitation Learning (IL) and Reinforcement Learning (RL) frameworks into a seamless pipeline, such…

Despite recent advances in Large Video Language Models (LVLMs), they still struggle with fine-grained temporal understanding, hallucinate, and often make simple mistakes on even simple video question-answering tasks, all of which pose…

Preference alignment is pivotal for empowering large language models (LLMs) to generate helpful and harmless responses. However, the performance of preference alignment is highly sensitive to the prevalent noise in the preference data.…

Local Interpretable Model-Agnostic Explanations (LIME) is a popular method to perform interpretability of any kind of Machine Learning (ML) model. It explains one ML prediction at a time, by learning a simple linear model around the…

Applying reinforcement learning (RL) to real-world problems is often made challenging by the inability to interact with the environment and the difficulty of designing reward functions. Offline RL addresses the first challenge by…