Embedding-Aligned Language Models

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Tennenholtz, Guy, Chow, Yinlam, Hsu, Chih-Wei, Shani, Lior, Liang, Ethan, Boutilier, Craig
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916456517599232
author Tennenholtz, Guy
Chow, Yinlam
Hsu, Chih-Wei
Shani, Lior
Liang, Ethan
Boutilier, Craig
author_facet Tennenholtz, Guy
Chow, Yinlam
Hsu, Chih-Wei
Shani, Lior
Liang, Ethan
Boutilier, Craig
contents We propose a novel approach for training large language models (LLMs) to adhere to objectives defined within a latent embedding space. Our method leverages reinforcement learning (RL), treating a pre-trained LLM as an environment. Our embedding-aligned guided language (EAGLE) agent is trained to iteratively steer the LLM's generation towards optimal regions of the latent embedding space, w.r.t. some predefined criterion. We demonstrate the effectiveness of the EAGLE agent using the MovieLens 25M and Amazon Review datasets to surface content gaps that satisfy latent user demand. We also demonstrate the benefit of using an optimal design of a state-dependent action set to improve EAGLE's efficiency. Our work paves the way for controlled and grounded text generation using LLMs, ensuring consistency with domain-specific knowledge and data representations.
format Preprint
id arxiv_https___arxiv_org_abs_2406_00024
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Embedding-Aligned Language Models
Tennenholtz, Guy
Chow, Yinlam
Hsu, Chih-Wei
Shani, Lior
Liang, Ethan
Boutilier, Craig
Computation and Language
Artificial Intelligence
Emerging Technologies
Machine Learning
We propose a novel approach for training large language models (LLMs) to adhere to objectives defined within a latent embedding space. Our method leverages reinforcement learning (RL), treating a pre-trained LLM as an environment. Our embedding-aligned guided language (EAGLE) agent is trained to iteratively steer the LLM's generation towards optimal regions of the latent embedding space, w.r.t. some predefined criterion. We demonstrate the effectiveness of the EAGLE agent using the MovieLens 25M and Amazon Review datasets to surface content gaps that satisfy latent user demand. We also demonstrate the benefit of using an optimal design of a state-dependent action set to improve EAGLE's efficiency. Our work paves the way for controlled and grounded text generation using LLMs, ensuring consistency with domain-specific knowledge and data representations.
title Embedding-Aligned Language Models
topic Computation and Language
Artificial Intelligence
Emerging Technologies
Machine Learning
url https://arxiv.org/abs/2406.00024