This study model heterogeneity in humor preferences in Oogiri by clustering users with voting logs and estimating cluster-specific weights over interpretable preference factors using Bradley-Terry-Luce models and finds that user clusters exhibit distinct preference patterns and that the LLM results can resemble those o...
This work introduces SVD-MBR, which frames the pairwise utility matrix as a noisy information signal, and reveals that this denoising is metric-dependent: neural metrics encode a robust low-rank consensus ideal for SVD, whereas surface-level metrics struggle to separate signal from metric noise.
Riza Setiawan Soetedjo, Yusuke Sakai, Hidetaka Kamigaito et al.· 0 citations
This work proposes a framework that efficiently exploits factual information from a knowledge graph via retrieval-augmented generation via retrieval-augmented generation (RAG), with the goal of enabling LVLMs to generate detailed and accurate image explanations.
Y. Kato, Shintaro Ozaki, Kazuki Hayashi et al.· 0 citations
This work finds that models cannot reliably reconstruct the original meaning and layer-wise probe classifiers fail to detect the harmful intent of perturbed prompts, and perturbations can occasionally reduce attack success by inducing off-topic or incoherent responses.
