User identity conditions moral wrongness ratings in non-reasoning large language models
This study adopts a behavioural bottom-up approach to AI value alignment to investigate whether an implicitly conveyed user identity shifts the moral evaluations of large language models (LLMs). Through a structured, multi-turn conversational protocol across 12,000 interactions, we evaluate AI value alignment in two non-reasoning models, gpt-4.1-mini-2025-04-14 and gemini-2.5-flash-lite. Rather than instructing the models to adopt a persona or prompting them with explicit moral stances, the user
Record details
Published: 8 July 2026
Source: arXiv
Category: Research
Topics: Safety & alignment · Finance, VC & PE
Retrieved: 14 July 2026
Related evidence
These records share source-supplied organisations, an exact publisher byline, automatic topics or regions. The reason is shown on every link; related does not mean supporting, agreeing with or verifying this record.
DiaLLM: An Investigation into the Robustness-Generation Gap in English Dialect Adaptation
arXiv · 8 July 2026
RAG-GNN: retrieval-augmented graph neural networks for protein interaction network embeddings
Frontiers in Artificial Intelligence · 10 July 2026
ReGen: Hierarchical Multi-Prompt Representation Generation for Efficient Waveform Diffusion Models
arXiv · 10 July 2026
ManiScope: LLM-Assisted Visual Analytics of Cryptocurrency Manipulation Risk
arXiv cs.HC · 13 July 2026
Can Dialects Be Steered Like Languages? Sparse Neurons and Distributed Directions in Arabic LLMs
HuggingFace Daily Papers · 3 July 2026
Internal Pluralism and the Limits of Pairwise Comparisons
arXiv · 2 July 2026
How to cite this record
ethics.ai (8 July 2026), “User identity conditions moral wrongness ratings in non-reasoning large language models,” evidence record 121, https://ethics.ai/record/121 (originally published by arXiv).
Use and limitations
This page is a stable index and citation surface for a source record. ethics.ai did not author the underlying report and has not independently verified every claim. Automatic topics may be imperfect. For consequential use, quote and cite the original publisher.