Aligning large language models (LLMs) with multiple, potentially conflicting human values remains challenging, as existing multi-objective alignment methods often require costly fine-tuning and provide limited insight into the internal mechanisms underlying value-related behaviors. In this work, we investigate multi-va...
Xue-Qi Ma, Yan-Bei Jiang, Xingjun Ma et al.· 0 citations
Out-of-distribution detection in continual learning (OOD-CL) is highly challenging, as it requires (i) learning a sequence of tasks without catastrophic forgetting, and (ii) identifying unknown samples (OOD) without access to known (in-distribution (ID)) data from past tasks, where standard confidence-based OOD scores...
Nimeshika Udayangani, F. Salim, C. Leckie et al.· 0 citations
Feedback-conditioned control over activations is demonstrated and it is suggested that latent monitoring should be treated as an interactive process in which agents can observe and respond to oversight measures.
Hugo Lyons Keenan, C. Leckie, S. Erfani· arXiv.org· 3 citations
The VEX-Bench is introduced, a unified benchmark for evaluating the verification complexity of LLM-generated misinformation, as perceived during screening, across models and generation methods, and shows that no single method dominates all dimensions, underscoring the need for multi-dimensional evaluation.
Hanxun Huang, Yu-Tao Wu, Qi-Zhou Wang et al.· 0 citations
We propose LAYERSCOPE, a label-free, layerwise framework that aims to characterize a model's learned representations in video and multimodal settings. Evaluating downstream performance using representations from final or intermediate layers typically requires large amounts of labeled data, repeated task-specific evalua...
Sandra Arcos-Holzinger, Debashish Chakraborty, Rohita Mocharla et al.· 0 citations
Theoretical analysis shows that under this anisotropic structure, adversarial attacks increase the expected geometric separation between clean and adversarial examples (AEs), and proposes GeoDetect, which leverages these off-manifold deviations via geometric scores to identify AEs.
Afsaneh Hasanebrahimi, Hanxun Huang, Christopher Leckie et al.· arXiv.org· 0 citations
VisER is proposed, a training-free two-sided metric for object-level hallucination detection that improves AUROC and AUPR over a range of baselines and measures whether object-context compatibility is backed by object-specific evidence from image tokens.
Afsaneh Hasanebrahimi, Hanxun Huang, Christopher Leckie et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.