Scar enhances language models by reducing toxic language in text generation.
Ruben Härle, Felix Friedrich, Manuel Brack
― 5 min read
Computer Science - Computation and Language
RSSAn overview of how language models learn and retain information.
Kristijan Armeni, Marko Pranjić, Senja Pollak
― 5 min read
Researchers investigate how large language models predict sequences using induction.
Niclas Luick
― 6 min read
A new way to make language models lighter without losing performance.
Elia Cunegatti, Leonardo Lucio Custode, Giovanni Iacca
― 8 min read
UniHR improves prediction and connections in diverse knowledge graphs.
Zhiqiang Liu, Mingyang Chen, Yin Hua
― 6 min read
A study on AI's ability to understand human scents.
Shu Zhong, Zetao Zhou, Christopher Dawes
― 5 min read
EVQAScore improves video QA evaluation efficiently and effectively.
Hao Liang, Zirong Chen, Wentao Zhang
― 6 min read
Examining how Language Models influence communication and ethical challenges.
Alexander Rogiers, Sander Noels, Maarten Buyl
― 7 min read
This study examines how large language models can misbehave and be manipulated.
Yannis Belkhiter, Giulio Zizzo, Sergio Maffeis
― 5 min read
Explore how Align-SLM is changing computer speech generation.
Guan-Ting Lin, Prashanth Gurunath Shivakumar, Aditya Gourav
― 6 min read
Examining how AI models handle ethical decisions for autonomous vehicles.
Muhammad Shahrul Zaim bin Ahmad, Kazuhiro Takemoto
― 6 min read
Innovative methods enhance SQL code bug fixing using large language models.
Yiwen Duan, Yonghong Yu, Xiaoming Zhao
― 5 min read
Combining Large Language Models and knowledge bases enhances news understanding.
Yihe Zhang, Nabin Pakka, Nian-Feng Tzeng
― 7 min read
Symile combines different data types for deeper insights and understanding.
Adriel Saporta, Aahlad Puli, Mark Goldstein
― 6 min read
Study explores how language models convey emotions and meanings implicitly.
Joshua Tint, Som Sagar, Aditya Taparia
― 7 min read
Attributing harmful outputs from language models poses significant challenges and risks.
Manuel Cebrian, Jan Arne Telle
― 6 min read
A deep look into podcast transcripts and their impact.
Benjamin Litterer, David Jurgens, Dallas Card
― 6 min read
A look into verbosity compensation and its impact on language models.
Yusen Zhang, Sarkar Snigdha Sarathi Das, Rui Zhang
― 4 min read
Exploring how irony confuses machine learning systems.
Xiaoyin Yi, Jiacheng Huang
― 5 min read
A look at the ethical challenges in Natural Language Processing technology.
Antonia Karamolegkou, Sandrine Schiller Hansen, Ariadni Christopoulou
― 6 min read
How tricky word associations confuse language processing in computers.
Jiacheng Huang, Long Chen
― 5 min read
Learn how the sequence of information affects AI answer quality.
Tianyu Liu, Jirui Qi, Paul He
― 6 min read
A new method enhances how AI handles pronouns for better representation.
Tianyi Huang, Arya Somasundaram
― 5 min read
Explore the role of constructions in mastering language skills.
Ludovica Pannitto, Beatrice Bernasconi, Lucia Busso
― 5 min read
Learn how FPO improves AI response quality and efficiency.
Qingyu Yin, Chak Tou Leong, Hongbo Zhang
― 5 min read
Exploring the capabilities and challenges of Transformer technology in understanding language.
Bo Chen, Xiaoyu Li, Yingyu Liang
― 6 min read
Researchers develop DROJ to enhance the safety of language models against harmful prompts.
Leyang Hu, Boran Wang
― 6 min read
Exploring how AI enhances gameplay in the board game Diplomacy.
Feng Gu, Wichayaporn Wongkamjan, Jordan Lee Boyd-Graber
― 6 min read
Understanding how mixed languages shape communication and technology.
Wenbo Zhang, Aditya Majumdar, Amulya Yadav
― 5 min read
Research shows how smart captions help models describe images accurately.
Moran Yanuka, Assaf Ben Kish, Yonatan Bitton
― 5 min read
Learn how Affine Concept Editing improves AI's ability to refuse prompts wisely.
Thomas Marshall, Adam Scherlis, Nora Belrose
― 6 min read
A new method enhances text classification using code-like prompts.
Mohammad Mahdi Mohajeri, Mohammad Javad Dousti, Majid Nili Ahmadabadi
― 5 min read
Examining how bias affects language models and their interpretation of offensive language.
Shayan Alipour, Indira Sen, Mattia Samory
― 7 min read
New models CamemBERTav2 and CamemBERTv2 improve French language processing.
Wissam Antoun, Francis Kulumba, Rian Touchent
― 5 min read
This article discusses the relationship between steering vectors and sparse autoencoders in AI.
Harry Mayne, Yushi Yang, Adam Mahdi
― 6 min read
We examine how language relationships impact information extraction across various languages.
Nghia Trung Ngo, Thien Huu Nguyen
― 6 min read
Researchers explore how multiple perspectives improve AI understanding of human opinions.
Benedetta Muscato, Praveen Bushipaka, Gizem Gezici
― 5 min read
Discover how Dynamic Subset Tuning enhances AI model training efficiency.
Felix Stahlberg, Jared Lichtarge, Shankar Kumar
― 7 min read
Voice assistants help identify early signs of memory issues in older adults.
Nana Lin, Youxiang Zhu, Xiaohui Liang
― 7 min read
This article discusses protecting our personal data from language models.
Abhinav Java, Simra Shahid, Chirag Agarwal
― 5 min read