Saved in:
Bibliographic Details
Main Authors: Yuan, Chenchen, Zhang, Zheyu, Yang, Shuo, Prenkaj, Bardh, Kasneci, Gjergji
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2506.14625
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911426461827072
author Yuan, Chenchen
Zhang, Zheyu
Yang, Shuo
Prenkaj, Bardh
Kasneci, Gjergji
author_facet Yuan, Chenchen
Zhang, Zheyu
Yang, Shuo
Prenkaj, Bardh
Kasneci, Gjergji
contents Large Language Models (LLMs) have shown impressive moral reasoning abilities. Yet they often diverge when confronted with complex, multi-factor moral dilemmas. To address these discrepancies, we propose a framework that synthesizes multiple LLMs' moral judgments into a collectively formulated moral judgment, realigning models that deviate significantly from this consensus. Our aggregation mechanism fuses continuous moral acceptability scores (beyond binary labels) into a collective probability, weighting contributions by model reliability. For misaligned models, a targeted embedding-optimization procedure fine-tunes token embeddings for moral philosophical theories, minimizing JS divergence to the consensus while preserving semantic integrity. Experiments on a large-scale social moral dilemma dataset show our approach builds robust consensus and improves individual model fidelity. These findings highlight the value of data-driven moral alignment across multiple models and its potential for safer, more consistent AI systems.
format Preprint
id arxiv_https___arxiv_org_abs_2506_14625
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Probabilistic Aggregation and Targeted Embedding Optimization for Collective Moral Reasoning in Large Language Models
Yuan, Chenchen
Zhang, Zheyu
Yang, Shuo
Prenkaj, Bardh
Kasneci, Gjergji
Computation and Language
Artificial Intelligence
Large Language Models (LLMs) have shown impressive moral reasoning abilities. Yet they often diverge when confronted with complex, multi-factor moral dilemmas. To address these discrepancies, we propose a framework that synthesizes multiple LLMs' moral judgments into a collectively formulated moral judgment, realigning models that deviate significantly from this consensus. Our aggregation mechanism fuses continuous moral acceptability scores (beyond binary labels) into a collective probability, weighting contributions by model reliability. For misaligned models, a targeted embedding-optimization procedure fine-tunes token embeddings for moral philosophical theories, minimizing JS divergence to the consensus while preserving semantic integrity. Experiments on a large-scale social moral dilemma dataset show our approach builds robust consensus and improves individual model fidelity. These findings highlight the value of data-driven moral alignment across multiple models and its potential for safer, more consistent AI systems.
title Probabilistic Aggregation and Targeted Embedding Optimization for Collective Moral Reasoning in Large Language Models
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2506.14625