Enhancing the moral alignment of Large Language Models (LLMs) is a critical challenge in AI safety. Current alignment techniques often act as superficial guardrails, leaving the intrinsic moral representations of LLMs largely untouched. In this paper, we bridge this gap by leveraging Moral Foundations Theory (MFT) to map and manipulate the fine-grained moral landscape of LLMs. Through cross-lingual linear probing, we validate the shared nature of moral representations in middle layers and uncover a shared yet different moral subspace between English and Chinese. Building upon this, we extract steerable Moral Vectors and successfully validate their efficacy at both internal and behavioral levels. Leveraging the high generalizability of morality, we propose Adaptive Moral Fusion (AMF), a dynamic inference-time intervention that synergizes probe detection with vector injection to tackle the safety-helpfulness trade-off. Empirical results confirm that our approach acts as a targeted intrinsic defense, effectively reducing incorrect refusals on benign queries while minimizing jailbreak success rates compared to standard baselines.
Jingjie Zeng, Huayang Li, Liang Yang Dalian University of Technology, Yuanyuan Sun Dalian University of Technology, Shaowu Zhang Dalian University of Technology, Hongfei Lin
Human cognition excels at extending knowledge through analogy, where word meanings evolve along structured pathways from concrete prototypes to abstract senses via metaphor and metonymy. Do Large Language Models (LLMs) internalize this generative logic, or merely mimic statistical patterns? To investigate this, we introduce CogEvolve, a cognitive linguistic benchmark designed to test these evolutionary pathways across textual and visual modalities. Our evaluation reveals a distinct cognitive profile: models function as “Super-Associators” expert at static recognition yet fail at causal reasoning. In text, they exhibit a Frequency-Primacy Conflation, confusing statistical prevalence with cognitive basicness. Crucially, this reasoning collapses further in the visual domain. We term this deficit the Ungrounded Arrow: models possess high-fidelity concept representations (the “dots”) but lack the transformational operators (the “arrows”) essential for true relational understanding.
尚无 AI 解读，展示原文摘要
cs.CL · cs.CV
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表
Zekun Wang, Jingjie Zeng, Yingxu Li, Hongfei Lin, Liang Yang Dalian University of Technology
Multimodal Large Language Models (MLLMs) face critical privacy challenges due to the indiscriminate memorization of sensitive data. Existing unlearning methods, largely adapted from Euclidean paradigms, suffer from a geometric mismatch: they fail to disentangle specific instances from general concepts, causing catastrophic forgetting or unsafe substitution. We introduce LOTUS (Lorentz Transport for Unlearning Strategies), a framework for surgical semantic pruning within the Lorentz manifold. Leveraging hyperbolic geometry’s hierarchical nature, LOTUS employs an Inverted Entailment Cone Loss to sever the inheritance of sensitive concepts and a Lorentz Transport mechanism to align pruned features within the tangent space, ensuring compatibility with Euclidean backbones via a safety refusal prior. Experiments on MLLMU-Bench with LLaVA and Qwen show that LOTUS significantly outperforms baselines, effectively erasing targeted visual data while preserving general utility.
尚无 AI 解读，展示原文摘要
cs.CL · cs.CV
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表