arXiv:2511.17012v1 Announce Type: cross Abstract: Large language models and knowledge graphs offer strong potential for advancing research on historical culture by supporting the extraction, analysis, and interpretation of cultural heritage. Using Hunan’s modern historical celebrities shaped by Huxiang culture as a case study, pre-trained large models can help researchers efficiently extract key information, including biographical […]
Mesh RAG: Retrieval Augmentation for Autoregressive Mesh Generation
arXiv:2511.16807v1 Announce Type: cross Abstract: 3D meshes are a critical building block for applications ranging from industrial design and gaming to simulation and robotics. Traditionally, meshes are crafted manually by artists, a process that is time-intensive and difficult to scale. To automate and accelerate this asset creation, autoregressive models have emerged as a powerful paradigm […]
ManifoldFormer: Geometric Deep Learning for Neural Dynamics on Riemannian Manifolds
arXiv:2511.16828v1 Announce Type: cross Abstract: Existing EEG foundation models mainly treat neural signals as generic time series in Euclidean space, ignoring the intrinsic geometric structure of neural dynamics that constrains brain activity to low-dimensional manifolds. This fundamental mismatch between model assumptions and neural geometry limits representation quality and cross-subject generalization. ManifoldFormer addresses this limitation through […]
Detecting and Steering LLMs’ Empathy in Action
arXiv:2511.16699v1 Announce Type: cross Abstract: We investigate empathy-in-action — the willingness to sacrifice task efficiency to address human needs — as a linear direction in LLM activation space. Using contrastive prompts grounded in the Empathy-in-Action (EIA) benchmark, we test detection and steering across Phi-3-mini-4k (3.8B), Qwen2.5-7B (safety-trained), and Dolphin-Llama-3.1-8B (uncensored). Detection: All models show AUROC […]
Prompt-Based Value Steering of Large Language Models
arXiv:2511.16688v1 Announce Type: cross Abstract: Large language models are increasingly used in applications where alignment with human values is critical. While model fine-tuning is often employed to ensure safe responses, this technique is static and does not lend itself to everyday situations involving dynamic values and preferences. In this paper, we present a practical, reproducible, […]
How Well Do LLMs Understand Tunisian Arabic?
arXiv:2511.16683v1 Announce Type: cross Abstract: Large Language Models (LLMs) are the engines driving today’s AI agents. The better these models understand human languages, the more natural and user-friendly the interaction with AI becomes, from everyday devices like computers and smartwatches to any tool that can act intelligently. Yet, the ability of industrial-scale LLMs to comprehend […]
DDTime: Dataset Distillation with Spectral Alignment and Information Bottleneck for Time-Series Forecasting
arXiv:2511.16715v1 Announce Type: cross Abstract: Time-series forecasting is fundamental across many domains, yet training accurate models often requires large-scale datasets and substantial computational resources. Dataset distillation offers a promising alternative by synthesizing compact datasets that preserve the learning behavior of full data. However, extending dataset distillation to time-series forecasting is non-trivial due to two fundamental […]
SafeR-CLIP: Mitigating NSFW Content in Vision-Language Models While Preserving Pre-Trained Knowledge
arXiv:2511.16743v1 Announce Type: cross Abstract: Improving the safety of vision-language models like CLIP via fine-tuning often comes at a steep price, causing significant drops in their generalization performance. We find this trade-off stems from rigid alignment strategies that force unsafe concepts toward single, predefined safe targets, disrupting the model’s learned semantic structure. To address this, […]
Large language models for automated PRISMA 2020 adherence checking
arXiv:2511.16707v1 Announce Type: cross Abstract: Evaluating adherence to PRISMA 2020 guideline remains a burden in the peer review process. To address the lack of shareable benchmarks, we constructed a copyright-aware benchmark of 108 Creative Commons-licensed systematic reviews and evaluated ten large language models (LLMs) across five input formats. In a development cohort, supplying structured PRISMA […]
AutoBackdoor: Automating Backdoor Attacks via LLM Agents
arXiv:2511.16709v1 Announce Type: cross Abstract: Backdoor attacks pose a serious threat to the secure deployment of large language models (LLMs), enabling adversaries to implant hidden behaviors triggered by specific inputs. However, existing methods often rely on manually crafted triggers and static data pipelines, which are rigid, labor-intensive, and inadequate for systematically evaluating modern defense robustness. […]
Concept-Based Interpretability for Toxicity Detection
arXiv:2511.16689v1 Announce Type: cross Abstract: The rise of social networks has not only facilitated communication but also allowed the spread of harmful content. Although significant advances have been made in detecting toxic language in textual data, the exploration of concept-based explanations in toxicity detection remains limited. In this study, we leverage various subtype attributes present […]
Hierarchical Retrieval with Out-Of-Vocabulary Queries: A Case Study on SNOMED CT
arXiv:2511.16698v1 Announce Type: cross Abstract: SNOMED CT is a biomedical ontology with a hierarchical representation of large-scale concepts. Knowledge retrieval in SNOMED CT is critical for its application, but often proves challenging due to language ambiguity, synonyms, polysemies and so on. This problem is exacerbated when the queries are out-of-vocabulary (OOV), i.e., having no equivalent […]