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
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:2609.04022v1 Announce Type: cross
Abstract: Aligning large language models (LLMs) is essential for their safe deployment. Current alignment methods mainly optimize observable responses, yet mod...
By Lingyu Li, Yan Teng, Yingchun Wang, Xia Hu
The paper introduces WSF-ARG+, a new dataset that pairs hate speech with check‑worthiness annotations, and presents an LLM‑in‑the‑loop framework to streamline the annotation process. Experiments with 12 open‑weight large language models demonstrate that the framework cuts human effort while maintaining annotation quality. The study also shows that incorporating check‑worthiness labels improves hate‑speech detection performance, boosting macro‑F1 scores for large models by up to 0.213 and averaging 0.154 across models.
By Nicol\'as Benjam\'in Ocampo, Tommaso Caselli, Davide Ceolin
arXiv:2608.23264v1 Announce Type: new
Abstract: Although Large Language Models (LLMs) are aligned to optimize for both helpfulness and harmlessness, these dual objectives may conflict, inevitably lea...
By Or Biton, Tomer Krichli, Itai Allouche, Joseph Keshet
The paper introduces FAID, a fine‑grained adaptive framework for detecting implicit hate speech. It first classifies samples into Shallow, Targeted, or Context‑Dependent categories and then applies tailored strategies—prompt‑tuning for shallow cases, knowledge augmentation for targeted ones, and an agentic prompt‑generation system for context‑dependent posts. Experiments on four benchmark datasets show that FAID outperforms state‑of‑the‑art baselines by allocating computational effort only where needed.
By Han Wang, Yuhu Cheng, Xuesong Wang, Yi Zhu
arXiv:2601. 21433v2 Announce Type: replace Abstract: Language models are increasingly consulted on ethically consequential questions, yet the stance a model expresses may not survive a change in framing.
By Katherine Elkins, Jon Chun
arXiv:2607. 20444v1 Announce Type: cross Abstract: Large language models (LLMs) can produce deceptive responses: outputs that mislead users in service of a contextually or experimentally induced goal.
By Ali Asad, Stephen Obadinma, Anshul Pattoo, Wenxuan Zhang, Xiaodan Zhu
arXiv:2605. 22660v2 Announce Type: replace-cross Abstract: Moral language is subtle and culturally variable, making it difficult to translate faithfully across languages.
By Maciej Skorski
arXiv:2606. 02883v1 Announce Type: cross Abstract: Recommender systems have grown from content-organization tools into sophisticated systems that shape daily behavior.
By Amir Ghasemian, Homa Hosseinmardi, Upasana Dutta, Duncan J. Watts
arXiv:2608. 05624v1 Announce Type: new Abstract: Sycophantic responses are becoming pervasive in large language models (LLMs), and prior work has pointed out that some of them could be harmful.
By Bohan Jiang, Dawei Li, Yasin Silva, Huan Liu
Understanding moral values in social media text offers insight into moral judgement formation, and supervised NLP models trained on crowdsourced data have achieved strong classification performance. However, most approaches simplify the problem by aggregating multiple annotators' labels into a single "ground truth", overlooking the inherent subjectivity of the task.