Contextual Moral Value Alignment Through Context-Based Aggregation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Dognin, Pierre, Rios, Jesus, Luss, Ronny, Padhi, Inkit, Riemer, Matthew D, Liu, Miao, Sattigeri, Prasanna, Nagireddy, Manish, Varshney, Kush R., Bouneffouf, Djallel
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929282276655104
author Dognin, Pierre
Rios, Jesus
Luss, Ronny
Padhi, Inkit
Riemer, Matthew D
Liu, Miao
Sattigeri, Prasanna
Nagireddy, Manish
Varshney, Kush R.
Bouneffouf, Djallel
author_facet Dognin, Pierre
Rios, Jesus
Luss, Ronny
Padhi, Inkit
Riemer, Matthew D
Liu, Miao
Sattigeri, Prasanna
Nagireddy, Manish
Varshney, Kush R.
Bouneffouf, Djallel
contents Developing value-aligned AI agents is a complex undertaking and an ongoing challenge in the field of AI. Specifically within the domain of Large Language Models (LLMs), the capability to consolidate multiple independently trained dialogue agents, each aligned with a distinct moral value, into a unified system that can adapt to and be aligned with multiple moral values is of paramount importance. In this paper, we propose a system that does contextual moral value alignment based on contextual aggregation. Here, aggregation is defined as the process of integrating a subset of LLM responses that are best suited to respond to a user input, taking into account features extracted from the user's input. The proposed system shows better results in term of alignment to human value compared to the state of the art.
format Preprint
id arxiv_https___arxiv_org_abs_2403_12805
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Contextual Moral Value Alignment Through Context-Based Aggregation
Dognin, Pierre
Rios, Jesus
Luss, Ronny
Padhi, Inkit
Riemer, Matthew D
Liu, Miao
Sattigeri, Prasanna
Nagireddy, Manish
Varshney, Kush R.
Bouneffouf, Djallel
Artificial Intelligence
Computation and Language
Developing value-aligned AI agents is a complex undertaking and an ongoing challenge in the field of AI. Specifically within the domain of Large Language Models (LLMs), the capability to consolidate multiple independently trained dialogue agents, each aligned with a distinct moral value, into a unified system that can adapt to and be aligned with multiple moral values is of paramount importance. In this paper, we propose a system that does contextual moral value alignment based on contextual aggregation. Here, aggregation is defined as the process of integrating a subset of LLM responses that are best suited to respond to a user input, taking into account features extracted from the user's input. The proposed system shows better results in term of alignment to human value compared to the state of the art.
title Contextual Moral Value Alignment Through Context-Based Aggregation
topic Artificial Intelligence
Computation and Language
url https://arxiv.org/abs/2403.12805