Search, Verify and Feedback: Towards Next Generation Post-training Paradigm of Foundation Models via Verifier Engineering

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Guan, Xinyan, Liu, Yanjiang, Lu, Xinyu, Cao, Boxi, He, Ben, Han, Xianpei, Sun, Le, Lou, Jie, Yu, Bowen, Lu, Yaojie, Lin, Hongyu
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866929595480014848
author Guan, Xinyan
Liu, Yanjiang
Lu, Xinyu
Cao, Boxi
He, Ben
Han, Xianpei
Sun, Le
Lou, Jie
Yu, Bowen
Lu, Yaojie
Lin, Hongyu
author_facet Guan, Xinyan
Liu, Yanjiang
Lu, Xinyu
Cao, Boxi
He, Ben
Han, Xianpei
Sun, Le
Lou, Jie
Yu, Bowen
Lu, Yaojie
Lin, Hongyu
contents The evolution of machine learning has increasingly prioritized the development of powerful models and more scalable supervision signals. However, the emergence of foundation models presents significant challenges in providing effective supervision signals necessary for further enhancing their capabilities. Consequently, there is an urgent need to explore novel supervision signals and technical approaches. In this paper, we propose verifier engineering, a novel post-training paradigm specifically designed for the era of foundation models. The core of verifier engineering involves leveraging a suite of automated verifiers to perform verification tasks and deliver meaningful feedback to foundation models. We systematically categorize the verifier engineering process into three essential stages: search, verify, and feedback, and provide a comprehensive review of state-of-the-art research developments within each stage. We believe that verifier engineering constitutes a fundamental pathway toward achieving Artificial General Intelligence.
format Preprint
id arxiv_https___arxiv_org_abs_2411_11504
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Search, Verify and Feedback: Towards Next Generation Post-training Paradigm of Foundation Models via Verifier Engineering
Guan, Xinyan
Liu, Yanjiang
Lu, Xinyu
Cao, Boxi
He, Ben
Han, Xianpei
Sun, Le
Lou, Jie
Yu, Bowen
Lu, Yaojie
Lin, Hongyu
Artificial Intelligence
Computation and Language
Machine Learning
The evolution of machine learning has increasingly prioritized the development of powerful models and more scalable supervision signals. However, the emergence of foundation models presents significant challenges in providing effective supervision signals necessary for further enhancing their capabilities. Consequently, there is an urgent need to explore novel supervision signals and technical approaches. In this paper, we propose verifier engineering, a novel post-training paradigm specifically designed for the era of foundation models. The core of verifier engineering involves leveraging a suite of automated verifiers to perform verification tasks and deliver meaningful feedback to foundation models. We systematically categorize the verifier engineering process into three essential stages: search, verify, and feedback, and provide a comprehensive review of state-of-the-art research developments within each stage. We believe that verifier engineering constitutes a fundamental pathway toward achieving Artificial General Intelligence.
title Search, Verify and Feedback: Towards Next Generation Post-training Paradigm of Foundation Models via Verifier Engineering
topic Artificial Intelligence
Computation and Language
Machine Learning
url https://arxiv.org/abs/2411.11504