62 citations · 140 across the 16 of their papers we have counts for
19 papers
Rethinking Semantic Alignment in LLM-Enhanced Collaborative Filtering: A Spectral Decoupling Approach
Yedong Jin, Shaowen Peng, Tsunenori Mine +2
Recent advances in LLM-enhanced recommendation commonly align semantic representations with collaborative embeddings in a shared space, yet how alignment affects LLM-encoded inform…
What Does Activation Steering Control? Attribution Across Answer Encodings and Output-Sensitive Subspaces
Zhiwei Gao, Shaowen Peng, Shoko Wakamiya +1
Activation steering is often evaluated under the answer encoding used to construct the direction. A reported gain may reflect the intended judgment or compatibility with answer ide…
Can Large Language Models Imitate Human Speech for Clinical Assessment? LLM-Driven Data Augmentation for Cognitive Score Prediction
Si-Belkacem Yamine Ketir, Lenard Paulo Tamayo, Shohei Hisada +3
Accurate assessment of cognitive decline from spontaneous speech remains challenging due to limited dataset size and class imbalance. In this work, we propose a large language mode…
Filling in the Clinical Gaps in Benchmark: Case for HealthBench for the Japanese medical system
Shohei Hisada, Endo Sunao, Himi Yamato +2
This study investigates the applicability of HealthBench, a large-scale, rubric-based medical benchmark, to the Japanese context. Although robust evaluation frameworks are essentia…
Arukikata Travelogue Dataset with Geographic Entity Mention, Coreference, and Link Annotation
Shohei Higashiyama, Hiroki Ouchi, Hiroki Teranishi +9
Geoparsing is a fundamental technique for analyzing geo-entity information in text. We focus on document-level geoparsing, which considers geographic relatedness among geo-entity m…
NAIST Academic Travelogue Dataset
Hiroki Ouchi, Hiroyuki Shindo, Shoko Wakamiya +5
We have constructed NAIST Academic Travelogue Dataset (ATD) and released it free of charge for academic research. This dataset is a Japanese text dataset with a total of over 31 mi…
Crowdsourced Hypothesis Generation and their Verification: A Case Study on Sleep Quality Improvement
Shoko Wakamiya, Toshiki Mera, Eiji Aramaki +2
A clinical study is often necessary for exploring important research questions; however, this approach is sometimes time and money consuming. Another extreme approach, which is to…
Annotation-Scheme Reconstruction for "Fake News" and Japanese Fake News Dataset
Taichi Murayama, Shohei Hisada, Makoto Uehara +2
Fake news provokes many societal problems; therefore, there has been extensive research on fake news detection tasks to counter it. Many fake news datasets were constructed as reso…
Mitigation of Diachronic Bias in Fake News Detection Dataset
Taichi Murayama, Shoko Wakamiya, Eiji Aramaki
Fake news causes significant damage to society.To deal with these fake news, several studies on building detection models and arranging datasets have been conducted. Most of the fa…
Single Model for Influenza Forecasting of Multiple Countries by Multi-task Learning
Taichi Murayama, Shoko Wakamiya, Eiji Aramaki
The accurate forecasting of infectious epidemic diseases such as influenza is a crucial task undertaken by medical institutions. Although numerous flu forecasting methods and model…
End-to-end Biomedical Entity Linking with Span-based Dictionary Matching
Shogo Ujiie, Hayate Iso, Shuntaro Yada +2
Disease name recognition and normalization, which is generally called biomedical entity linking, is a fundamental process in biomedical text mining. Recently, neural joint learning…
Influenza Surveillance using Search Engine, SNS, On-line Shopping, Q&A Service and Past Flu Patients
Taichi Murayama, Nobuyuki Shimizu, Sumio Fujita +2
Influenza, an infectious disease, causes many deaths worldwide. Predicting influenza victims during epidemics is an important task for clinical, hospital, and community outbreak pr…
KART: Parameterization of Privacy Leakage Scenarios from Pre-trained Language Models
Yuta Nakamura, Shouhei Hanaoka, Yukihiro Nomura +5
For the safe sharing pre-trained language models, no guidelines exist at present owing to the difficulty in estimating the upper bound of the risk of privacy leakage. One problem i…
Universal Fake News Collection System using Debunking Tweets
Taichi Murayama, Shoko Wakamiya, Eiji Aramaki
Large numbers of people use Social Networking Services (SNS) for easy access to various news, but they have more opportunities to obtain and share ``fake news'' carrying false info…
Fake News Detection using Temporal Features Extracted via Point Process
Taichi Murayama, Shoko Wakamiya, Eiji Aramaki
Many people use social networking services (SNSs) to easily access various news. There are numerous ways to obtain and share ``fake news,'' which are news carrying false informatio…
Modeling the spread of fake news on Twitter
Taichi Murayama, Shoko Wakamiya, Eiji Aramaki +1
Fake news can have a significant negative impact on society because of the growing use of mobile devices and the worldwide increase in Internet access. It is therefore essential to…
Syndromic surveillance using search query logs and user location information from smartphones against COVID-19 clusters in Japan
Shohei Hisada, Taichi Murayama, Kota Tsubouchi +4
[Background] Two clusters of coronavirus disease 2019 (COVID-19) were confirmed in Hokkaido, Japan in February 2020. To capture the clusters, this study employs Web search query lo…
NAIST COVID: Multilingual COVID-19 Twitter and Weibo Dataset
Zhiwei Gao, Shuntaro Yada, Shoko Wakamiya +1
Since the outbreak of coronavirus disease 2019 (COVID-19) in the late 2019, it has affected over 200 countries and billions of people worldwide. This has affected the social life o…
Density Estimation for Geolocation via Convolutional Mixture Density Network
Hayate Iso, Shoko Wakamiya, Eiji Aramaki
Nowadays, geographic information related to Twitter is crucially important for fine-grained applications. However, the amount of geographic information avail- able on Twitter is lo…