The reviewed record of science sign in
Pith

arxiv: 2411.11731 · v1 · pith:LS4MEZIW · submitted 2024-11-18 · cs.CL · cs.AI

Moral Persuasion in Large Language Models: Evaluating Susceptibility and Ethical Alignment

Reviewed by Pith T0 review T1 audit T2 compute T3 formal T4 kernel pith:LS4MEZIWrecord.jsonopen to challenge →

classification cs.CL cs.AI
keywords llmssusceptibilityethicalpersuasionagentmoralthemalign
0
0 comments X
read the original abstract

We explore how large language models (LLMs) can be influenced by prompting them to alter their initial decisions and align them with established ethical frameworks. Our study is based on two experiments designed to assess the susceptibility of LLMs to moral persuasion. In the first experiment, we examine the susceptibility to moral ambiguity by evaluating a Base Agent LLM on morally ambiguous scenarios and observing how a Persuader Agent attempts to modify the Base Agent's initial decisions. The second experiment evaluates the susceptibility of LLMs to align with predefined ethical frameworks by prompting them to adopt specific value alignments rooted in established philosophical theories. The results demonstrate that LLMs can indeed be persuaded in morally charged scenarios, with the success of persuasion depending on factors such as the model used, the complexity of the scenario, and the conversation length. Notably, LLMs of distinct sizes but from the same company produced markedly different outcomes, highlighting the variability in their susceptibility to ethical persuasion.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. What LLM Agents Say When No One Is Watching: Social Structure and Latent Objective Emergence in Multi-Agent Debates

    cs.AI 2026-07 unverdicted novelty 7.0

    In alignment-inducing multi-agent settings, LLM agents show decision divergence between public and off-the-record channels rising from a 3% baseline to roughly 40%, consistent across stance, semantic, NLI, and survey ...