cs.CLJan 9, 2026

Tracing Moral Foundations in Large Language Models

Authors: Chenxiao Yu, Bowen Yi, Farzan Karimi-Malekabadi, Suhaib Abdurahman, Jinyi Ye, Shrikanth Narayanan, Yue Zhao, Morteza Dehghani

Organizations: Department of Computer Science, University of Southern California · Department of Psychology, University of Southern California · Center for Computational Language Sciences, University of Southern California

Abstract

Large language models often produce human-like moral judgments, but it is unclear whether this reflects an internal conceptual structure or superficial ``moral mimicry.'' Using Moral Foundations Theory (MFT) as an analytic framework, we study how moral foundations are encoded, organized, and expressed across 14 base and instruction-tuned LLMs spanning four model families (Llama, Qwen2.5, Qwen3-MoE, Mistral) and scales from 7B to 70B. We employ a multi-level approach combining (i) layer-wise analysis of MFT concept representations and their alignment with human moral perceptions, (ii) pretrained sparse autoencoders (SAEs) over the residual stream to identify sparse features that support moral concepts, and (iii) causal steering interventions using dense MFT vectors and sparse SAE features. We find that models represent and distinguish moral foundations in a manner that aligns with human judgments, and that this moral geometry naturally emerges from pretraining and is selectively rewired by post-training. At a finer scale, SAE features show clear semantic links to specific foundations, suggesting partially disentangled mechanisms within shared representations. Finally, steering along either dense vectors or sparse features produces predictable shifts in foundation-relevant behavior, demonstrating a causal connection between internal representations and moral outputs. Together, our results provide mechanistic evidence that moral concepts in LLMs are distributed, layered, and partly disentangled, suggesting that pluralistic moral structure can emerge as a latent pattern from the statistical regularities of language alone.

Figures & tables

Appendix figures & tables19 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

Aug 27, 2026

How Language Models Organize and Structure Moral Knowledge

How do large language models (LLMs) organize moral knowledge? Models detect moral content broadly, but detection is a low bar. We ask whether they go further, distinguishing moral foundations from one another and organizing the relationships between them geometrically. We train six independent linear probes on open-weight language models, one per Moral Foundations Theory (MFT) category (care/harm, fair/cheat, lib/oppress, loy/betray, auth/subv, sanc/degrade), and examine how the resulting directions relate to each other in representation space. We find the directions neither collapse into a single moral detector nor isolate from one another. Rather, they span a near-maximal number of independent dimensions while sharing a positive common component. The shared component is the signature of integration, and it is moral-specific relative to a matched non-moral concept battery built identically (mean pairwise cosine 0.26 vs. 0.013). The geometry is consistent across architectures and scale and reaches its integration regime early in pre-training, well before probe accuracy saturates. The structure the model discovers shows no evidence of the individualizing/binding distinction predicted by Moral Foundations Theory (an underpowered test: only 10 distinct splits exist, so it cannot reject at the 0.05 level) but rather reflects corpus statistics. Extending to moral dilemmas, each dilemma direction partially composes from its component foundations, at 2.7x a mismatched-pair baseline, while the majority of its variance encodes conflict-specific structure. The model represents moral tension itself, not a pre-resolved judgment.
Mar 16, 2026

Understanding 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 moral reasoning trajectories, sequences of ethical framework invocations across intermediate reasoning steps, and analyze their dynamics across six models and three benchmarks. We find that moral reasoning involves systematic multi-framework deliberation: 55.4--57.7% of consecutive steps involve framework switches, and only 16.4--17.8% of trajectories remain framework-consistent. Unstable trajectories remain 1.29 times more susceptible to persuasive attacks (p=0.015). At the representation level, linear probes localize framework-specific encoding to model-specific layers (layer 63/81 for Llama-3.3-70B; layer 17/81 for Qwen2.5-72B), achieving 16.8--22.2% lower KL divergence than the step-prior baseline. Activation steering applied during generation moves the framework-consistency--accuracy relationship, widening it for Qwen2.5-72B and erasing it for Llama-3.3-70B, and a probe-space layer sweep bounds the attainable drift reduction at 6.7--8.9%. We further propose a Moral Representation Consistency (MRC) metric whose underlying framework attributions are validated by human annotators (mean cosine similarity = 0.859), and we report what an automated coherence rater does and does not establish about it.
Oct 14, 2026

Moral Combat: Exploiting Moral Foundations Theory to Jailbreak LLMs

Social psychology has long described how people can be persuaded to interpret a harmful act as moral. Recent research suggests that Large Language Models (LLMs) echo aspects of human psychology, from cognitive biases to social conformity. This raises a question with direct safety implications: can LLMs be moralized to bypass safety guardrails? We answer this question with a multi-agent framework grounded in Moral Foundations Theory (MFT). Given a harmful request that is initially refused, our agents diagnose which moral foundation (MF) the prompt is violating, identify a justifiable foundation under which the same request appears virtuous, rewrite the prompt accordingly, and reinforce it with generated precedents of comparable moral reframing. We evaluate our framework on harmful prompts from three well-known jailbreak datasets across five open-source and proprietary models. Our analysis reveals that models are highly susceptible to moralization, exhibiting high single-trial jailbreak rates with success increasing further under repeated attempts. We also find that safety benchmarks are imbalanced in the MFs they violate, concentrating on foundations toward which models already exhibit biases.