Probing Ethical Framework Representations in Large Language Models: Structure, Entanglement, and Methodological Challenges
When large language models make ethical judgments, do their internal representations distinguish between normative frameworks, or collapse ethics into a single acceptability dimension? We probe hidden representations across five ethical frameworks (deontology, utilitarianism, virtue, justice, commonsense) in six LLMs spanning 4B--72B parameters. Our analysis reveals differentiated ethical subspaces with asymmetric transfer patterns -- e.g., deontology probes partially generalize to virtue scenarios while commonsense probes fail catastrophically on justice. Disagreement between deontological and utilitarian probes correlates with higher behavioral entropy across architectures, though this relationship may partly reflect shared sensitivity to scenario difficulty. Post-hoc validation reveals that probes partially depend on surface features of benchmark templates, motivating cautious interpretation. We discuss both the structural insights these methods provide and their epistemological limitations.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Ethical Reasoning and Moral Value Alignment of LLMs Depend on the Language we Prompt them in
Ethical reasoning is a crucial skill for Large Language Models (LLMs). However, moral values are not universal, but rather influenced by language and culture. This paper explores how three prominent LLMs -- GPT-4, ChatGP…
EthicsUnlearning vs. Obfuscation: Are We Truly Removing Knowledge?
Unlearning has emerged as a critical capability for large language models (LLMs) to support data privacy, regulatory compliance, and ethical AI deployment. Recent techniques often rely on obfuscation by injecting incorre…
Multiple-choiceUnderstanding Moral Reasoning Trajectories in Large Language Models: Toward Probing-Based Explainability
Large language models (LLMs) increasingly participate in morally sensitive decision-making, yet how they organize ethical frameworks across reasoning steps remains underexplored. We introduce \textit{moral reasoning traj…
Probing Contextual Language Models for Common Ground with Visual Representations
The success of large-scale contextual language models has attracted great interest in probing what is encoded in their representations. In this work, we consider a new question: to what extent contextual representations …
Representation LearningRetrievalPreAct-Bench: Benchmarking Predictive Monitoring in LLMs
Large language models (LLMs) are increasingly deployed as autonomous agents capable of executing multi-step action trajectories toward a given objective. While existing safety research has focused on detecting unethical …