moral foundations theory
PulseAugur coverage of moral foundations theory — every cluster mentioning moral foundations theory across labs, papers, and developer communities, ranked by signal.
3 day(s) with sentiment data
-
LLM steering vectors reflect human value geometry, study finds · 3 sources tracked
Researchers are exploring activation steering in large language models (LLMs) as a method for behavioral control, offering an alternative to fine-tuning techniques like RLHF and DPO. A new study, "Steering Geometry: Val…
-
LLMs structure moral knowledge geometrically, research finds
A new research paper explores how large language models (LLMs) organize moral knowledge, moving beyond simple moral content detection. The study found that LLMs distinguish between different moral foundations, such as c…
-
AI moral reasoning evaluations miss key aspects, research finds · 2 sources tracked
Two new research papers from arXiv highlight critical gaps in evaluating the moral reasoning of AI systems. The first paper argues that current evaluations focus too heavily on aligning AI outputs with human values, neg…
-
New dataset explores moral valence in AI ethics research
Researchers have proposed a new dataset for annotating moral valence in natural language, aiming to better align AI with human ethics by incorporating affective considerations. The dataset, comprising 500 annotations ac…
-
New AI framework enhances hate speech detection with moral rationales
Researchers have developed a novel framework called Supervised Moral Rationale Attention (SMRA) to improve the interpretability and robustness of hate speech detection models. Unlike previous methods that relied on surf…
-
LLMs' Moral Reasoning Enhanced by Pragmatic Inference Approach
Researchers have developed a new approach to enhance moral reasoning in large language models (LLMs) by focusing on pragmatic inference and metapragmatic links. This method aims to bridge the gap between explicit statem…
-
New benchmark tests LLMs' ability to compose moral judgments
Researchers have developed a new benchmark called the Moral Trolley Arena to evaluate how large language models compose moral judgments. This benchmark assesses models' ability to combine multiple moral signals within a…
-
LLM personas aligned with cultural values and moral frameworks
Researchers have developed a method to create large language model (LLM) personas that are grounded in specific cultural values. These personas are then analyzed using socio-psychological frameworks like the World Value…
-
Moral Foundations Theory explored for AI decision-making
Jonathan Haidt, a social psychologist, is exploring how Moral Foundations Theory can be applied to AI. He is posing questions about which moral principles should guide AI decision-making, linking this to social psycholo…