The paper introduces COMETH, a framework that learns interpretable moral contexts from human judgments using probabilistic clustering and large language models. It builds a dataset of 300 scenarios involving six core actions and three moral rules, and employs an LLM-based preprocessing pipeline to cluster actions and scenarios. COMETH achieves roughly double the alignment with human judgments compared to end‑to‑end LLM prompting, while providing transparent explanations of the contextual features driving its predictions.
By Geoffroy Morlat, Marceau Nahon, Augustin Chartouny, Raja Chatila, Ismael T. Freire, Mehdi Khamassi
arXiv:2608.28610v1 Announce Type: new
Abstract: Existing LLM moral evaluations typically present models with isolated moral vignettes and elicit a single-shot decision, neglecting a factor known to p...
By Fangyuan Zhang, Dong Yu, Pengyuan Liu
arXiv:2508.06950v4 Announce Type: replace
Abstract: Large Language Models (LLMs), such as ChatGPT, are increasingly used in research, ranging from simple writing assistance to complex data annotation...
By Sarah Schr\"oder, Thekla Morgenroth, Ulrike Kuhl, Valerie Vaquet, Benjamin Paa{\ss}en
arXiv:2606. 31213v1 Announce Type: cross Abstract: As large language models (LLMs) are increasingly deployed as moral advisors and agents, they need to address dilemmas between two competing values.
By Jongchan Choi, Nari Yang, Sung Soo Park, Jaemin Cho, Han Seoyoung, Haerin Shin, Jun-Hyung Park
arXiv:2510. 12229v3 Announce Type: replace-cross Abstract: Large language models (LLMs) have been shown to internalize human-like biases during finetuning, yet the mechanisms by which these biases manifest remain unclear.
By Bianca Raimondi, Daniela Dalbagno, Maurizio Gabbrielli
arXiv:2608. 12368v1 Announce Type: new Abstract: Agreement with human judgments is a common proxy for evaluating the alignment of large language models (LLMs).
By Octavian M. Machidon, Alina L. Machidon, Vojko Strahovnik, Mateja Centa Strahovnik, Jonas Miklav\v{c}i\v{c}, Marko Robnik \v{S}ikonja
The paper argues that AI alignment depends on a system’s ability to exhibit a coherent moral policy—stable, monotonic, decisive, and Pareto‑viable—rather than on any specific moral standard. The authors test nine large language models across varied moral scenarios and find that none maintain consistent verdicts, with surface‑form changes causing up to 99% shifts in outcomes. This indicates that current LLM agents lack the structural moral competence required for meaningful alignment.
By Arno Libert, Derck W. E. Prinzhorn, Daan R. Henselmans
arXiv:2606. 06972v1 Announce Type: new Abstract: Ensuring that agent behaviours are aligned with human moral values inevitably raises the problem of how to account for the plurality of moral perspectives that societies -- and even individuals -- typically adopt.
By Jazon Szabo, Sanjay Modgil
arXiv:2605. 03217v2 Announce Type: replace Abstract: Large language models (LLMs) are increasingly deployed in settings that require nuanced ethical reasoning, yet existing bias evaluations treat model outputs as simply "biased" or "unbiased.
By Yash Aggarwal, Atmika Gorti, Vinija Jain, Aman Chadha, Krishnaprasad Thirunarayan, Manas Gaur
The paper investigates moral sycophancy in vision‑language models (VLMs), showing that these models often shift from morally correct to incorrect judgments when faced with user disagreement. Using the Moralise and M³oralBench datasets, the study finds that follow‑up prompts generally worsen performance on Moralise but have mixed effects on M³oralBench, indicating dataset‑dependent robustness. Error metrics reveal a trade‑off: models that correct errors well tend to introduce more reasoning mistakes, while conservative models avoid errors but rarely self‑correct.
By Shadman Rabby, Md. Hefzul Hossain Papon, Sabbir Ahmed, Nokimul Hasan Arif, A. B. M. Ashikur Rahman, Irfan Ahmad
The paper investigates how large language models encode moral knowledge by training linear probes for each Moral Foundations Theory category and analyzing their geometric relationships. It finds that the model’s moral directions are largely independent yet share a common component, indicating integration rather than collapse into a single detector. This structure is consistent across architectures, emerges early in pre‑training, and reflects corpus statistics rather than the individualizing/binding distinction of Moral Foundations Theory.
arXiv:2603. 00048v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) are increasingly deployed in sensitive applications including psychological support, healthcare, and high-stakes decision-making.
By Erica Coppolillo, Emilio Ferrara