paper-with-me

Papers

Multi-objective Reinforcement learning from AI Feedback

2024-06-11 · Marcus Williams

This paper presents Multi-Objective Reinforcement Learning from AI Feedback (MORLAIF), a novel approach to improving the alignment and performance of language models trained using reinforcement learning from AI feedback (RLAIF). In contrast to standard approaches that train a single preference model to represent all human preferences, MORLAIF decomposes this task into multiple simpler principles, such as toxicity, factuality, and sycophancy. Separate preference models are trained for each principle using feedback from GPT-3.5-Turbo. These preference model scores are then combined using different scalarization functions to provide a reward signal for Proximal Policy Optimization (PPO) training of the target language model. Our experiments indicate that MORLAIF outperforms the standard RLAIF baselines and that MORLAIF can be used to align larger language models using smaller ones. Surprisingly, the choice of scalarization function does not appear to significantly impact the results.

📄 PDF Abstract BibTeX arXiv:2406.07295

Code (1)

carolius/Multi-Objective-Reinforcement-Learning-from-AI-Feedback 공식 구현 pytorch

Tasks

Language ModelingLanguage ModellingMulti-Objective Reinforcement Learningreinforcement-learningReinforcement Learning

Methods 이 논문이 사용한 방법론

Refunds@Expedia|||How do I get a full refund from Expedia? “How do I get a full refund from Expedia? How do I get a full refund from Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Quick Help &…
15 Ways to Contact How can i speak to someone at Delta Airlines 설명 없음
Attention 설명 없음
Cosine Annealing Cosine Annealing is a type of learning rate schedule that has the effect of starting with a large learning rate that is relatively rapidly decreased to a minimum value before…
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
ALIGN In the ALIGN method, visual and language representations are jointly trained from noisy image alt-text data. The image and text encoders are learned via contrastive loss…
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Weight Decay 설명 없음

Similar Papers 제목 키워드 기반

Reinforcement Learning from User Feedback

2025-05-20 · Eric Han, Jun Chen, Karthik Abinav Sankararaman, Xiaoliang Peng 외

As large language models (LLMs) are increasingly deployed in diverse user facing applications, aligning them with real user preferences becomes essential. Existing methods like Reinforcement Learning from Human Feedback …

reinforcement-learningReinforcement Learning

Balancing Multiple Objectives in Urban Traffic Control with Reinforcement Learning from AI Feedback

2026-02-24 · Chenyang Zhao, Vinny Cahill, Ivana Dusparic arxiv

Reward design has been one of the central challenges for real world reinforcement learning (RL) deployment, especially in settings with multiple objectives. Preference-based RL offers an appealing alternative by learning…

Reinforcement Learning

Personalized Soups: Personalized Large Language Model Alignment via Post-hoc Parameter Merging

2023-10-17 · Joel Jang, Seungone Kim, Bill Yuchen Lin, Yizhong Wang 외

While Reinforcement Learning from Human Feedback (RLHF) aligns Large Language Models (LLMs) with general, aggregate human preferences, it is suboptimal for learning diverse, individual perspectives. In this work, we stud…

Language ModelingLanguage ModellingLarge Language ModelMulti-Objective Reinforcement Learning+2

Multi-Agent Reinforcement Learning from Delayed Marketplace Feedback for Objective-Weight Adaptation in Three-Sided Dispatch

2026-06-11 · Haochen Wu, Yi Hou, Shiguang Xie arxiv

Dispatch in three-sided marketplaces provides a natural setting for reinforcement learning from world feedback: decisions are evaluated by delayed operational outcomes such as delivery speed, courier utilization, and mer…

Multi-agent Reinforcement Learning

Eliciting User Preferences for Personalized Multi-Objective Decision Making through Comparative Feedback

2023-02-07 · NeurIPS 2023 11

In classic reinforcement learning (RL) and decision making problems, policies are evaluated with respect to a scalar reward function, and all optimal policies are the same with regards to their expected return. However, …

Decision MakingReinforcement Learning (RL)