Examining the accuracy of term normalization in large language models.
Daniel B. Hier, Thanh Son Do, Tayo Obafemi-Ajayi
― 5 min read
Cutting edge science explained simply
Examining the accuracy of term normalization in large language models.
Daniel B. Hier, Thanh Son Do, Tayo Obafemi-Ajayi
― 5 min read
Exploring how LLMs can streamline editing structured documents with minimal effort.
Irene Weber
― 7 min read
A closer look at how well large language models perform basic tasks.
Thomas Ball, Shuo Chen, Cormac Herley
― 7 min read
Using customer reviews to create personalized shopping experiences through dynamic recommendation headers.
Shanu Vashishtha, Abhay Kumar, Lalitesh Morishetti
― 7 min read
This article examines methods to identify machine-generated text and their implications.
Matthieu Dubois, François Yvon, Pablo Piantanida
― 7 min read
A new method enhances agents' abilities to complete complex digital tasks efficiently.
Zora Zhiruo Wang, Jiayuan Mao, Daniel Fried
― 7 min read
CoMM enhances machine learning by integrating various data types effectively.
Benoit Dufumier, Javiera Castillo-Navarro, Devis Tuia
― 6 min read
A new approach to improve AI alignment with human intentions using weaker models.
Mehrdad Zakershahrak, Samira Ghodratnama
― 7 min read
AI technology helps journalists uncover important stories through data analysis.
Joris Veerbeek, Nicholas Diakopoulos
― 5 min read
This study examines the link between propaganda and hate in Arabic memes.
Firoj Alam, Md. Rafiul Biswas, Uzair Shah
― 5 min read
Learn how LLMs automate the summarization of user app reviews.
Faiz Ali Shah, Ahmed Sabir, Rajesh Sharma
― 6 min read
Using LLMs to generate clear features from scientific texts for better predictions.
Vojtěch Balek, Lukáš Sýkora, Vilém Sklenák
― 6 min read
A new method improves AI explanations through collaboration between two language models.
Qianli Wang, Tatiana Anikina, Nils Feldhus
― 5 min read
WikiOFGraph enhances G2T generation with high-quality graph-text pairs.
Daehee Kim, Deokhyung Kang, Sangwon Ryu
― 7 min read
Research reveals how false information affects language models' reliability and accuracy.
Alina Fastowski, Gjergji Kasneci
― 5 min read
A new method interprets authorship attribution models for improved accuracy and trust.
Milad Alshomary, Narutatsu Ri, Marianna Apidianaki
― 6 min read
A new model enhances evaluation of speaking skills by focusing on coherence.
Jiun-Ting Li, Bi-Cheng Yan, Tien-Hong Lo
― 5 min read
Examining the impact of prompt languages on LLMs in Arabic tasks.
Mohamed Bayan Kmainasi, Rakif Khan, Ali Ezzat Shahroor
― 6 min read
TheraGen provides 24/7 mental health assistance using advanced AI technology.
Kartikey Doshi, Jimit Shah, Narendra Shekokar
― 6 min read
A new framework improves the detection of false information across social platforms.
Sarah Condran, Michael Bewong, Selasi Kwashie
― 6 min read
Efforts to improve speech technology for the under-resourced Faetar language.
Michael Ong, Sean Robertson, Leo Peckham
― 5 min read
A new approach to modeling data using natural language for better interpretation.
Ruiqi Zhong, Heng Wang, Dan Klein
― 8 min read
Measuring conversation length and complexity to assess AI safety.
John Burden, Manuel Cebrian, Jose Hernandez-Orallo
― 7 min read
Study reveals how language models utilize context for accurate responses.
Yufei Tao, Adam Hiatt, Erik Haake
― 6 min read
New strategies for agent collaboration enhance trust and efficiency in AI responses.
Vladyslav Larin, Ivan Nikitin, Alexander Firsov
― 7 min read
Study examines combining spoken messages and visual icons for drone control.
Ashwini Gundappa, Emilia Ellsiepen, Lukas Schmitz
― 6 min read
Harnessing AI to improve honeypot effectiveness against cyber threats.
Hakan T. Otal, M. Abdullah Canbaz
― 6 min read
This article examines the impact of context on reading efficiency.
Andreas Opedal, Eleanor Chodroff, Ryan Cotterell
― 7 min read
A new framework analyzes candidates' debate performances using large language models.
Zhengliang Liu, Yiwei Li, Oleksandra Zolotarevych
― 9 min read
Study reveals how tones change in everyday Taiwanese Mandarin speech.
Xiaoyun Jin, Mirjam Ernestus, R. Harald Baayen
― 5 min read
A new model combines speech recognition and entity recognition for better results.
Gil Ayache, Menachem Pirchi, Aviv Navon
― 5 min read
A dataset to predict outcomes in UK Employment Tribunal cases.
Huiyuan Xie, Felix Steffek, Joana Ribeiro de Faria
― 8 min read
A study on using language models for correcting errors in speech recognition systems.
Zhiyuan Tang, Dong Wang, Shen Huang
― 5 min read
New synthetic datasets enhance machine learning in healthcare while protecting patient privacy.
Tal Baumel, Andre Manoel, Daniel Jones
― 6 min read
AI tools improve online discussions by encouraging engagement and better comment quality.
Maike Behrendt, Stefan Sylvius Wagner, Stefan Harmeling
― 6 min read
A novel approach using grid images enhances VideoQA performance on complex tasks.
Yanan Wang, Shuichiro Haruta, Donghuo Zeng
― 5 min read
A new method improves video question answering by focusing on multi-object events.
Yanan Wang, Shuichiro Haruta, Donghuo Zeng
― 5 min read
Exploring the role of logic in understanding personal pronouns and gender identity.
Rose Bohrer, Ashe Neth
― 7 min read
Block-Attention enhances language models by speeding up responses while maintaining accuracy.
East Sun, Yan Wang, Lan Tian
― 5 min read
Learn about the challenges and models in visual question-answering tasks.
Neelabh Sinha, Vinija Jain, Aman Chadha
― 5 min read