9 citations · 21 across the 26 of their papers we have counts for
16 papers · 1 filter
How Reliable are AMR Parser Outputs? Uncertainty Estimation for AMR Parsing
Anuj Kumar, Shintaro Ozaki, Yamuna Prasad +3
Recent advances have significantly improved the performance of Abstract Meaning Representation (AMR) parsers, yet determining when their outputs can be trusted remains largely unex…
Overfitting Mitigation via Singular Value Decomposition in Minimum Bayes Risk Decoding
Riza Setiawan Soetedjo, Yusuke Sakai, Hidetaka Kamigaito +2
Minimum Bayes Risk (MBR) decoding enables high-quality text generation by selecting the hypothesis that maximizes a utility metric over sampled pseudo-references. However, it is hi…
ExpArt-KG: Artwork Image Description Generation through Iterative Exploration of Knowledge Graphs
Yuta Kato, Shintaro Ozaki, Kazuki Hayashi +4
Large Vision-Language Models (LVLMs) achieve strong performance on image-grounded text generation and visual question answering. However, it remains difficult for them to comprehen…
Identifying Influential N-grams in Confidence Calibration via Regression Analysis
Shintaro Ozaki, Wataru Hashimoto, Hidetaka Kamigaito +2
While large language models (LLMs) improve performance by explicit reasoning, their responses are often overconfident, even though they include linguistic expressions demonstrating…
From Formal Language Theory to Statistical Learning: Finite Observability of Subregular Languages
Katsuhiko Hayashi, Hidetaka Kamigaito
We prove that all standard subregular language classes are linearly separable when represented by their deciding predicates. This establishes finite observability and guarantees le…
Diversity of Transformer Layers: One Aspect of Parameter Scaling Laws
Hidetaka Kamigaito, Ying Zhang, Jingun Kwon +3
Transformers deliver outstanding performance across a wide range of tasks and are now a dominant backbone architecture for large language models (LLMs). Their task-solving performa…
TextTIGER: Text-based Intelligent Generation with Entity Prompt Refinement for Text-to-Image Generation
Shintaro Ozaki, Tomoyuki Jinno, Kazuki Hayashi +6
When generating images from prompts that include specific entities, the model must retain as much entity-specific knowledge as possible. However, the number of entities is almost c…
Can Impressions of Music be Extracted from Thumbnail Images?
Takashi Harada, Takehiro Motomitsu, Katsuhiko Hayashi +2
In recent years, there has been a notable increase in research on machine learning models for music retrieval and generation systems that are capable of taking natural language sen…
Understanding the Impact of Confidence in Retrieval Augmented Generation: A Case Study in the Medical Domain
Shintaro Ozaki, Yuta Kato, Siyuan Feng +8
Retrieval Augmented Generation (RAG) complements the knowledge of Large Language Models (LLMs) by leveraging external information to enhance response accuracy for queries. This app…
Diversity Explains Inference Scaling Laws: Through a Case Study of Minimum Bayes Risk Decoding
Hidetaka Kamigaito, Hiroyuki Deguchi, Yusuke Sakai +2
Inference methods play an important role in eliciting the performance of large language models (LLMs). Currently, LLMs use inference methods utilizing generated multiple samples, w…
Towards Cross-Lingual Explanation of Artwork in Large-scale Vision Language Models
Shintaro Ozaki, Kazuki Hayashi, Yusuke Sakai +3
As the performance of Large-scale Vision Language Models (LVLMs) improves, they are increasingly capable of responding in multiple languages, and there is an expectation that the d…
Unified Interpretation of Smoothing Methods for Negative Sampling Loss Functions in Knowledge Graph Embedding
Xincan Feng, Hidetaka Kamigaito, Katsuhiko Hayashi +1
Knowledge Graphs (KGs) are fundamental resources in knowledge-intensive tasks in NLP. Due to the limitation of manually creating KGs, KG Completion (KGC) has an important role in a…
IRR: Image Review Ranking Framework for Evaluating Vision-Language Models
Kazuki Hayashi, Kazuma Onishi, Toma Suzuki +7
Large-scale Vision-Language Models (LVLMs) process both images and text, excelling in multimodal tasks such as image captioning and description generation. However, while these mod…
Does Pre-trained Language Model Actually Infer Unseen Links in Knowledge Graph Completion?
Yusuke Sakai, Hidetaka Kamigaito, Katsuhiko Hayashi +1
Knowledge graphs (KGs) consist of links that describe relationships between entities. Due to the difficulty of manually enumerating all relationships between entities, automaticall…
Model-based Subsampling for Knowledge Graph Completion
Xincan Feng, Hidetaka Kamigaito, Katsuhiko Hayashi +1
Subsampling is effective in Knowledge Graph Embedding (KGE) for reducing overfitting caused by the sparsity in Knowledge Graph (KG) datasets. However, current subsampling approache…
Table and Image Generation for Investigating Knowledge of Entities in Pre-trained Vision and Language Models
Hidetaka Kamigaito, Katsuhiko Hayashi, Taro Watanabe
In this paper, we propose a table and image generation task to verify how the knowledge about entities acquired from natural language is retained in Vision & Language (V&L) models.…