相关论文: Mitigating the Alignment Tax of RLHF

Building helpful and harmless large language models (LLMs) requires effective model alignment approach based on human instructions and feedback, which necessitates high-quality human-labeled data. Constructing such datasets is often…

Language model alignment is a critical step in training modern generative language models. Alignment targets to improve win rate of a sample from the aligned model against the base model. Today, we are increasingly using inference-time…

Machine learning techniques applied to the problem of financial market forecasting struggle with dynamic regime switching, or underlying correlation and covariance shifts in true (hidden) market variables. Drawing inspiration from the…

Reinforcement Learning from Human Feedback (RLHF) aims to align language models (LMs) with human values by training reward models (RMs) on binary preferences and using these RMs to fine-tune the base LMs. Despite its importance, the…

The importance of Reinforcement Learning from Human Feedback (RLHF) in aligning large language models (LLMs) with human values cannot be overstated. RLHF is a three-stage process that includes supervised fine-tuning (SFT), reward learning,…

Sampling algorithms drive probabilistic machine learning, and recent years have seen an explosion in the diversity of tools for this task. However, the increasing sophistication of sampling algorithms is correlated with an increase in the…

Training Large Language Models (LLMs) incurs significant cost; hence, any strategy that accelerates model convergence is helpful. In this paper, we investigate the ability of a simple idea checkpoint averaging along the trajectory of a…

Reinforcement learning has seen wide success in finetuning large language models to better align with instructions via human feedback. The so-called algorithm, Reinforcement Learning with Human Feedback (RLHF) demonstrates impressive…

Re-inforcement learning from human feedback (RLHF) has been effective in the task of AI alignment. However, one of the key assumptions of RLHF is that the annotators (referred to as workers from here on out) have a homogeneous response…

Data-Free Meta-Learning (DFML) aims to derive knowledge from a collection of pre-trained models without accessing their original data, enabling the rapid adaptation to new unseen tasks. Current methods often overlook the heterogeneity among…

Meta-reinforcement learning (meta-RL) algorithms allow for agents to learn new behaviors from small amounts of experience, mitigating the sample inefficiency problem in RL. However, while meta-RL agents can adapt quickly to new tasks at…

Large Language Models (LLMs) have become increasingly popular due to their ability to process and generate natural language. However, as they are trained on massive datasets of text, LLMs can inherit harmful biases and produce outputs that…

Reinforcement Learning from Human Feedback (RLHF) is a powerful paradigm for aligning foundation models to human values and preferences. However, current RLHF techniques cannot account for the naturally occurring differences in individual…

In this paper, we introduce a method for fine-tuning Large Language Models (LLMs), inspired by Multi-Task learning in a federated manner. Our approach leverages the structure of each client's model and enables a learning scheme that…

Federated Learning (FL) empowers multiple clients to collaboratively train machine learning models without sharing local data, making it highly applicable in heterogeneous Internet of Things (IoT) environments. However, intrinsic…

While Reinforcement Learning from Human Feedback (RLHF) effectively aligns pretrained Large Language and Vision-Language Models (LLMs, and VLMs) with human preferences, its computational cost and complexity hamper its wider adoption. To…

Reward models trained on human preference data have been proven to effectively align Large Language Models (LLMs) with human intent within the framework of reinforcement learning from human feedback (RLHF). However, current reward models…

Reinforcement learning from human feedback (RLHF) has become a key factor in aligning model behavior with users' goals. However, while humans integrate multiple strategies when making decisions, current RLHF approaches often simplify this…

Large Language Models (LLMs) have revolutionized natural language processing but can exhibit biases and may generate toxic content. While alignment techniques like Reinforcement Learning from Human Feedback (RLHF) reduce these issues, their…

Model averaging is a widely adopted technique in federated learning (FL) that aggregates multiple client models to obtain a global model. Remarkably, model averaging in FL yields a superior global model, even when client models are trained…