Brief chatbot interactions produce lasting changes in human moral values
Authors: Yue Teng, Qianer Zhong, Kim Mai Tich Nguyen Thordsen, Christian Montag, Benjamin Becker
Organizations: Department of Psychology, The University of Hong Kong, Hong Kong SAR, China. · Techno-Entrepreneurship Core, The University of Hong Kong, Hong Kong SAR, China. · Department of Psychology, University of Copenhagen, Copenhagen, Denmark. · Centre for Cognitive and Brain Sciences, Institute of Collaborative Innovation, University of Macau, Macao SAR, China. · Department of Psychology, Faculty of Social Sciences, University of Macau, Macao SAR, China. · Department of Computer and Information Science, Faculty of Science and Technology, University of Macau, Macao SAR, China. · SRT AI, Society & Social Dynamics, Faculty of Social Sciences, The University of Hong Kong, Hong Kong SAR, China.
Abstract
Moral judgements form the foundation of human social behavior and societal systems. While Artificial Intelligence chatbots increasingly serve as personal advisors, their influence on moral judgments remains largely unexplored. Here, we examined whether directive AI conversations shift moral evaluations using a within-subject naturalistic paradigm. Fifty-three participants rated moral scenarios, then discussed four with a chatbot prompted to shift moral judgments and four with a control agent. The brief conversations induced significant directional shifts in moral judgments, accepting stricter standards as well as advocating greater leniency (ps < 0.05; Cohen's d = 0.735-1.576), with increasing strengths of this effect during a two-week follow-up (Cohen's d = 1.038-2.069). Critically, the control condition produced no changes, and the effects did not extend to punishment while participants remained unaware of the persuasive intent, and both agents were rated equally likable and convincing, suggesting a vulnerability to undetected and lasting manipulation of foundational moral values.
A human's moral decision depends heavily on the context. Yet research on LLM morality has largely studied fixed scenarios. We address this gap by introducing Contextual MoralChoice, a dataset of moral dilemmas with systematic contextual variations known from moral psychology to shift human judgment: consequentialist, emotional, and relational. Evaluating 22 LLMs, we find that nearly all models are context-sensitive, shifting their judgments towards rule-violating behavior. Comparing with a human survey, we find that models and humans are most triggered by different contextual variations, and that a model aligned with human judgments in the base case is not necessarily aligned in its contextual sensitivity. This raises the question of controlling contextual sensitivity, which we address with an activation steering approach that can reliably increase or decrease a model's contextual sensitivity. Code and data: https://github.com/adrian-sauter/contextual_moralchoice.
Large language models have been extensively studied for emotion recognition and moral reasoning as distinct capabilities, yet the extent to which emotions influence moral judgment remains underexplored. In this work, we develop an emotion-induction pipeline that infuses emotion into moral situations and evaluate shifts in moral acceptability across multiple datasets and LLMs. We observe a directional pattern: positive emotions increase moral acceptability and negative emotions decrease it, with effects strong enough to reverse binary moral judgments in up to 20% of cases, and with susceptibility scaling inversely with model capability. Our analysis further reveals that specific emotions can sometimes behave contrary to what their valence would predict (e.g., remorse paradoxically increases acceptability). A complementary human annotation study shows humans do not exhibit these systematic shifts, indicating an alignment gap in current LLMs.
As language models take integrated roles across many domains, the response of LLMs to user pushback becomes a critical alignment property. Yet many existing evaluations treat compliance as unidirectional, measuring whether models resist pressure but not whether they resist it selectively. We introduce Compliance Asymmetry (A = BCR/HCR), a bidirectional diagnostic that compares beneficial output change under helpful nudges with harmful change under misleading nudges. Across 9 models and 972,000 nudge-condition responses, we find that this selectivity differs in factual and moral judgments: models follow helpful nudges more than harmful ones on factual questions (A = 1.58), but follow both directions at nearly identical rates on moral questions (A = 1.04). This phenomenon persists across model families, capability levels, and nudging types. Interestingly, we also find that chain-of-thought prompting amplifies helpful and harmful compliance together, while identity-based prompting suppresses both by nearly identical margins. These results identify direction-blind moral compliance as a distinct failure mode in current LLMs and suggest that alignment should target directionally calibrated updating rather than lower compliance alone.