5 citations · 5 across the 10 of their papers we have counts for
7 papers · 1 filter
In-Context Neurofeedback: Can LLMs Control Their Internal Representations through Privileged Access?
Koshiro Aoki, Ryota Takatsuki, Gouki Minegishi +2
Whether large language models (LLMs) can control their own internal representations matters for both machine metacognition and AI safety. A recent study applied neurofeedback to LL…
Synth-JDoc: Synthesizing a Japanese Document Image Dataset for OCR with Diverse Layouts and Embedded Images
Keito Sasagawa, Shuhei Kurita, Daisuke Kawahara
The ability of Large Vision Language Models (LVLMs) to read text within document images is crucial, as it enables various applications such as Document Visual Question Answering. T…
Measuring Task-Agnostic Training Data Influence Across Language Model Pretraining
Yuto Nishida, Hirokazu Kiyomaru, Yusuke Oda +6
Measuring training data influence consistently across language model pretraining is challenging. It is difficult to select downstream tasks or validation sets representative of a m…
Human-LLM Alignment in Language Attitudes Toward Non-Native Japanese
Naho Orita, Hayato Ogawa, Daisuke Kawahara
Large language models (LLMs) increasingly evaluate human writing in high-stakes domains such as hiring and academic assessment, putting non-native speakers at particular risk. Draw…
Detecting Sensitive Personal Information in Japanese Pre-Training Corpora for Large Language Models
Rei Minamoto, Yusuke Oda, Daisuke Kawahara
Sensitive personal information can appear in large-scale pre-training corpora for large language models (LLMs). Detecting and filtering such information is therefore essential to e…
JAMMEval: A Refined Collection of Japanese Benchmarks for Reliable VLM Evaluation
Issa Sugiura, Koki Maeda, Shuhei Kurita +3
Reliable evaluation is essential for the development of vision-language models (VLMs). However, Japanese VQA benchmarks have undergone far less iterative refinement than their Engl…