5 papers · 1 filter
When Modality Gap Reduction Fails: Prediction-Level Hubness in CLIP
Shota Sato, Hajime Kiyama, Tosho Hirasawa +1
Reducing the modality gap between image and text representations in CLIP is widely expected to improve cross-modal alignment and downstream performance. However, a smaller average…
Exploring the Effects of Alignment on Numerical Bias in Large Language Models
Ayako Sato, Hwichan Kim, Zhousi Chen +2
"LLM-as-a-judge," which utilizes large language models (LLMs) as evaluators, has proven effective in many evaluation tasks. However, evaluator LLMs exhibit numerical bias, a phenom…
Assessing the Capabilities of LLMs in Humor:A Multi-dimensional Analysis of Oogiri Generation and Evaluation
Ritsu Sakabe, Hwichan Kim, Tosho Hirasawa +1
Computational humor is a frontier for creating advanced and engaging natural language processing (NLP) applications, such as sophisticated dialogue systems. While previous studies…
Pruning Multilingual Large Language Models for Multilingual Inference
Hwichan Kim, Jun Suzuki, Tosho Hirasawa +1
Multilingual large language models (MLLMs), trained on multilingual balanced data, demonstrate better zero-shot learning performance in non-English languages compared to large lang…
Large Language Models Are State-of-the-Art Evaluator for Grammatical Error Correction
Masamune Kobayashi, Masato Mita, Mamoru Komachi
Large Language Models (LLMs) have been reported to outperform existing automatic evaluation metrics in some tasks, such as text summarization and machine translation. However, ther…