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.
The study investigates how large language models encode moral knowledge by training linear probes for each category of Moral Foundations Theory. It finds that the model’s representations for different moral foundations occupy distinct, largely independent dimensions yet share a common positive component, indicating an integrated but nuanced moral structure. This geometry is consistent across model architectures and scales, emerges early in pre‑training, and reflects corpus statistics rather than the individualizing/binding distinction of the theory.
By Orion Reblitz-Richardson
arXiv:2606. 15507v1 Announce Type: new Abstract: Behavioral audits of Large Language Models on moral prompts measure what the model says, not the internal computation producing it.
By Ali Dasdan, Manan Shah, W. Russell Neuman, Chad Coleman, Kund Meghani, Safinah Ali
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 argues that aligning large language models (LLMs) at the level of latent representations—specifically by matching their internal categorization of moral concepts to human prototype-based judgments—improves safety. Current alignment methods that focus on observable responses fail to preserve fine-grained moral categorization, leaving models vulnerable to adversarial rephrasings. By optimizing representational similarity, the authors demonstrate that LLMs can maintain more robust moral categorization and exhibit better adversarial robustness across multiple benchmarks and model sizes.
By Lingyu Li, Yan Teng, Yingchun Wang, Xia Hu
arXiv:2606. 11635v1 Announce Type: cross Abstract: For highly capable AI systems to operate safely in dynamic, open-ended environments, they must be able to identify, understand, and respond to moral reasons for action, and constrain their behaviour accordingly.
By Menghang Zhu, Seth Lazar
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
arXiv:2510. 16380v2 Announce Type: replace-cross Abstract: As AI systems progress, we rely more on them to make decisions with us and for us.
By Yu Ying Chiu, Michael S. Lee, Rachel Calcott, Brandon Handoko, Paul de Font-Reaulx, Rapha\"el Milli\`ere, Paula Rodriguez, Chen Bo Calvin Zhang, Ziwen Han, Udari Madhushani Sehwag, Yash Maurya, Christina Q Knight, Harry R. Lloyd, Florence Bacus, Conor Downey, Mantas Mazeika, Bing Liu, Yejin Choi, Mitchell L Gordon, Sydney Levine
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
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
The paper introduces CHARM, a lightweight fine‑tuned language model framework for detecting moral foundations in text. CHARM combines MAC cross‑attention, rationale alignment, and hate‑speech modulation to operationalize distinct psychological constructs, achieving up to 15.3% higher AUC in‑domain and outperforming supervised baselines on all out‑of‑domain datasets. The authors demonstrate CHARM’s scalability by applying it to large‑scale COVID‑19 Twitter data, revealing a strong link between moral value alignment and online endorsement behavior.
By Huixiang Fu, Marian-Andrei Rizoiu
Large Language Models (LLMs) often struggle to navigate value conflicts when trained with the compressed scalar rewards of Reinforcement Learning from Human Feedback (RLHF). To address this challenge, we investigate how chain-of-thought (CoT) reasoning can help improve performance in this domain.