Linear Alignment: A Closed-form Solution for Aligning Human Preferences without Tuning and Feedback
- URL: http://arxiv.org/abs/2401.11458v3
- Date: Tue, 2 Jul 2024 03:24:29 GMT
- Title: Linear Alignment: A Closed-form Solution for Aligning Human Preferences without Tuning and Feedback
- Authors: Songyang Gao, Qiming Ge, Wei Shen, Shihan Dou, Junjie Ye, Xiao Wang, Rui Zheng, Yicheng Zou, Zhi Chen, Hang Yan, Qi Zhang, Dahua Lin,
- Abstract summary: Linear alignment is a novel algorithm that aligns language models with human preferences in one single inference step.
Experiments on both general and personalized preference datasets demonstrate that linear alignment significantly enhances the performance and efficiency of LLM alignment.
- Score: 70.32795295142648
- License: http://creativecommons.org/licenses/by-nc-sa/4.0/
- Abstract: The success of AI assistants based on Language Models (LLMs) hinges on Reinforcement Learning from Human Feedback (RLHF) to comprehend and align with user intentions. However, traditional alignment algorithms, such as PPO, are hampered by complex annotation and training requirements. This reliance limits the applicability of RLHF and hinders the development of professional assistants tailored to diverse human preferences. In this work, we introduce \textit{Linear Alignment}, a novel algorithm that aligns language models with human preferences in one single inference step, eliminating the reliance on data annotation and model training. Linear alignment incorporates a new parameterization for policy optimization under divergence constraints, which enables the extraction of optimal policy in a closed-form manner and facilitates the direct estimation of the aligned response. Extensive experiments on both general and personalized preference datasets demonstrate that linear alignment significantly enhances the performance and efficiency of LLM alignment across diverse scenarios. Our code and dataset is published on \url{https://github.com/Wizardcoast/Linear_Alignment.git}.
Related papers
- On-the-fly Preference Alignment via Principle-Guided Decoding [27.50204023448716]
We introduce On-the-fly Preference Alignment via Principle-Guided Decoding (OPAD) to align model outputs with human preferences during inference.
OPAD achieves competitive or superior performance in both general and personalized alignment tasks.
arXiv Detail & Related papers (2025-02-20T02:23:09Z) - PIPA: Preference Alignment as Prior-Informed Statistical Estimation [57.24096291517857]
We introduce Pior-Informed Preference Alignment (PIPA), a unified, RL-free probabilistic framework.
PIPA accommodates both paired and unpaired data, as well as answer and step-level annotations.
By integrating different types of prior information, we developed two variations of PIPA: PIPA-M and PIPA-N.
arXiv Detail & Related papers (2025-02-09T04:31:30Z) - Dynamic Rewarding with Prompt Optimization Enables Tuning-free Self-Alignment of Language Models [54.381650481255235]
We introduce a new tuning-free approach for self-alignment, Dynamic Rewarding with Prompt Optimization (O)
Our approach leverages a search-based optimization framework that allows LLMs to iteratively self-improve and craft the optimal alignment instructions.
Empirical evaluations on eight recent LLMs, both open and closed-sourced, demonstrate that DRPO significantly enhances alignment performance.
arXiv Detail & Related papers (2024-11-13T16:15:38Z) - PAD: Personalized Alignment of LLMs at Decoding-Time [10.347782385286582]
This paper presents a novel framework designed to align LLM outputs with diverse personalized preferences during the inference phase.
The Personalized Alignment at Decoding-time (PAD) framework decouples the text generation process from personalized preferences.
PAD not only outperforms existing training-based alignment methods in terms of aligning with diverse preferences but also shows significant generalizability to preferences unseen during training.
arXiv Detail & Related papers (2024-10-05T08:00:55Z) - SAIL: Self-Improving Efficient Online Alignment of Large Language Models [56.59644677997827]
Reinforcement Learning from Human Feedback is a key method for aligning large language models with human preferences.
Recent literature has focused on designing online RLHF methods but still lacks a unified conceptual formulation.
Our approach significantly improves alignment performance on open-sourced datasets with minimal computational overhead.
arXiv Detail & Related papers (2024-06-21T18:05:35Z) - Learning Reward and Policy Jointly from Demonstration and Preference Improves Alignment [58.049113055986375]
We develop a single stage approach named Alignment with Integrated Human Feedback (AIHF) to train reward models and the policy.
The proposed approach admits a suite of efficient algorithms, which can easily reduce to, and leverage, popular alignment algorithms.
We demonstrate the efficiency of the proposed solutions with extensive experiments involving alignment problems in LLMs and robotic control problems in MuJoCo.
arXiv Detail & Related papers (2024-06-11T01:20:53Z) - ULMA: Unified Language Model Alignment with Human Demonstration and
Point-wise Preference [16.73260713938154]
A typical alignment procedure consists of supervised fine-tuning and preference learning.
We introduce Point-wise Direct Preference Optimization, a novel preference learning method designed to harness point-wise feedback effectively.
Our work also uncovers a novel connection between supervised fine-tuning and point-wise preference learning, culminating in Unified Language Model Alignment.
arXiv Detail & Related papers (2023-12-05T07:52:12Z) - Personalized Soups: Personalized Large Language Model Alignment via
Post-hoc Parameter Merging [148.77027765872006]
We study Reinforcement Learning from Personalized Human Feedback (RLPHF) problem.
LLMs are aligned to multiple preferences by modeling alignment as a Multi-Objective Reinforcement Learning (MORL) problem.
We show that we can achieve personalized alignment by decomposing preferences into multiple dimensions.
arXiv Detail & Related papers (2023-10-17T20:22:13Z) - Aligning Language Models with Offline Learning from Human Feedback [5.539080592071948]
We propose an offline learning from human feedback framework to align language models without interacting with environments.
Specifically, we explore filtering alignment (FA), reward-weighted regression (RWR), and conditional alignment (CA) to align language models to human preferences.
arXiv Detail & Related papers (2023-08-23T10:41:07Z)
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.