Multi-objective Reinforcement learning from AI Feedback
- URL: http://arxiv.org/abs/2406.07295v2
- Date: Wed, 12 Jun 2024 13:55:30 GMT
- Title: Multi-objective Reinforcement learning from AI Feedback
- Authors: Marcus Williams,
- Abstract summary: This paper presents a novel approach to improve 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 simpler principles, such as toxicity, factuality, and sycophancy.
Our experiments indicate that MORLAIF outperforms the standard RLAIF baselines and that MORLAIF can be used to align larger language models using smaller ones.
- Score: 0.0
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: 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.
Related papers
- Feasible Learning [78.6167929413604]
We introduce Feasible Learning (FL), a sample-centric learning paradigm where models are trained by solving a feasibility problem that bounds the loss for each training sample.
Our empirical analysis, spanning image classification, age regression, and preference optimization in large language models, demonstrates that models trained via FL can learn from data while displaying improved tail behavior compared to ERM, with only a marginal impact on average performance.
arXiv Detail & Related papers (2025-01-24T20:39:38Z) - Few-shot Steerable Alignment: Adapting Rewards and LLM Policies with Neural Processes [50.544186914115045]
Large language models (LLMs) are increasingly embedded in everyday applications.
Ensuring their alignment with the diverse preferences of individual users has become a critical challenge.
We present a novel framework for few-shot steerable alignment.
arXiv Detail & Related papers (2024-12-18T16:14:59Z) - SPaR: Self-Play with Tree-Search Refinement to Improve Instruction-Following in Large Language Models [88.29990536278167]
We introduce SPaR, a self-play framework integrating tree-search self-refinement to yield valid and comparable preference pairs free from distractions.
Our experiments show that a LLaMA3-8B model, trained over three iterations guided by SPaR, surpasses GPT-4-Turbo on the IFEval benchmark without losing general capabilities.
arXiv Detail & Related papers (2024-12-16T09:47:43Z) - Joint Training for Selective Prediction [5.662924503089369]
Selective Prediction methods determine when to adopt a classifier's output versus defer to a human.
One previous method involves learning a deferral model based on engineered features.
We introduce a novel joint-training approach that simultaneously optimize learned representations used by the classifier module and a learned deferral policy.
arXiv Detail & Related papers (2024-10-31T15:28:26Z) - Self-supervised Preference Optimization: Enhance Your Language Model with Preference Degree Awareness [27.43137305486112]
We propose a novel Self-supervised Preference Optimization (SPO) framework, which constructs a self-supervised preference degree loss combined with the alignment loss.
The results demonstrate that SPO can be seamlessly integrated with existing preference optimization methods to achieve state-of-the-art performance.
arXiv Detail & Related papers (2024-09-26T12:37:26Z) - Personalizing Reinforcement Learning from Human Feedback with Variational Preference Learning [12.742158403867002]
Reinforcement Learning from Human Feedback is a powerful paradigm for aligning foundation models to human values and preferences.
Current RLHF techniques cannot account for the naturally occurring differences in individual human preferences across a diverse population.
We develop a class of multimodal RLHF methods to address the need for pluralistic alignment.
arXiv Detail & Related papers (2024-08-19T15:18:30Z) - Aligning Large Language Models via Fine-grained Supervision [20.35000061196631]
Pre-trained large-scale language models (LLMs) excel at producing coherent articles, yet their outputs may be untruthful, toxic, or fail to align with user expectations.
Current approaches focus on using reinforcement learning with human feedback to improve model alignment.
We propose a method to enhance LLM alignment through fine-grained token-level supervision.
arXiv Detail & Related papers (2024-06-04T20:21:45Z) - Self-Exploring Language Models: Active Preference Elicitation for Online Alignment [88.56809269990625]
We propose a bilevel objective optimistically biased towards potentially high-reward responses to actively explore out-of-distribution regions.
Our experimental results demonstrate that when fine-tuned on Zephyr-7B-SFT and Llama-3-8B-Instruct models, Self-Exploring Language Models (SELM) significantly boosts the performance on instruction-following benchmarks.
arXiv Detail & Related papers (2024-05-29T17:59:07Z) - SALMON: Self-Alignment with Instructable Reward Models [80.83323636730341]
This paper presents a novel approach, namely SALMON, to align base language models with minimal human supervision.
We develop an AI assistant named Dromedary-2 with only 6 exemplars for in-context learning and 31 human-defined principles.
arXiv Detail & Related papers (2023-10-09T17:56:53Z) - Beyond One-Preference-Fits-All Alignment: Multi-Objective Direct Preference Optimization [76.09576643028362]
We present Multi-Objective Direct Preference Optimization (MODPO) for multiple alignment objectives.
MODPO folds language modeling directly into reward modeling, training language models as implicit collective reward models.
It theoretically yields the same optimal solutions as MORLHF but is practically more stable and efficient.
arXiv Detail & Related papers (2023-10-05T17:35:26Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.