Explore the privacy concerns surrounding membership inference attacks in machine learning.
Hongyan Chang, Ali Shahin Shamsabadi, Kleomenis Katevas
― 5 min read
Computer Science - Computation and Language
RSSImproving assessments through Item Response Theory for better language learning.
Jue Hou, Anisia Katinskaia, Anh-Duc Vu
― 7 min read
A study of datasets and metrics in question answering research.
Jamshid Mozafari, Abdelrahman Abdallah, Bhawna Piryani
― 4 min read
Connecting markets to improve product-related question answering.
Yifei Yuan, Yang Deng, Anders Søgaard
― 6 min read
Examining cognitive biases' effects on language model assessments and decision-making.
Nuo Chen, Jiqun Liu, Xiaoyu Dong
― 6 min read
A new auction-based method enhances the efficiency of collecting preference data for AI models.
Guoxi Zhang, Jiuding Duan
― 5 min read
A new method enhances text evaluation by using soft probabilities for better accuracy.
Vatsal Raina, Adian Liusie, Mark Gales
― 6 min read
Analyzing how music reflects and shapes gender perceptions through lyrics.
Danqing Chen, Adithi Satish, Rasul Khanbayov
― 5 min read
A new method for assessing AI agents in customer support via test generation.
Samuel Arcadinho, David Aparicio, Mariana Almeida
― 5 min read
This paper presents a framework for improving NER in the Italian language using advanced models.
Andrew Zamai, Leonardo Rigutini, Marco Maggini
― 5 min read
A new method enhances prediction of research significance using word embeddings.
Lucie Dvorackova, Marcin P. Joachimiak, Michal Cerny
― 6 min read
A new method using knowledge graphs for accurate answers to simple questions.
Maria Lysyuk, Mikhail Salnikov, Pavel Braslavski
― 5 min read
A new benchmark assesses how well AI models mimic human language.
Xufeng Duan, Bei Xiao, Xuemei Tang
― 5 min read
This benchmark evaluates privacy threats and defense mechanisms in NLP models.
Wei Huang, Yinggui Wang, Cen Chen
― 8 min read
Introducing an adaptable method for tracking user needs in dialogue systems.
Abdulfattah Safa, Gözde Gül Şahin
― 6 min read
This study reveals how neurons relate to specific language tasks in GPT-2-XL.
Xufeng Duan, Xinyu Zhou, Bei Xiao
― 6 min read
This study uncovers how LLMs adapt their learning through attention patterns.
Yang Zhao, Li Du, Xiao Ding
― 6 min read
Small language models are changing how technology works in everyday devices.
Zhenyan Lu, Xiang Li, Dongqi Cai
― 7 min read
A look at how AI detects and analyzes online fraud.
Antonis Papasavva, Shane Johnson, Ed Lowther
― 8 min read
DiaSynth creates high-quality dialogues for effective training of conversational systems.
Sathya Krishnan Suresh, Wu Mengjun, Tushar Pranav
― 6 min read
A new framework improves detection of false outputs in language models using unlabeled data.
Xuefeng Du, Chaowei Xiao, Yixuan Li
― 5 min read
A new method enhances LLM performance while reducing complexity.
Gongfan Fang, Hongxu Yin, Saurav Muralidharan
― 7 min read
This framework enhances model performance by addressing low-quality augmented data.
Guanyi Mou, Yichuan Li, Kyumin Lee
― 6 min read
Exploring the importance of ethics in hate speech detection research.
Sidney Gig-Jan Wong
― 6 min read
Exploring the pitfalls of language models in data interpretation.
Yuqing Zhou, Ruixiang Tang, Ziyu Yao
― 5 min read
We enhance Direct Preference Optimization to better handle ties in decision-making.
Jinghong Chen, Guangyu Yang, Weizhe Lin
― 6 min read
A method to enhance efficiency of language models with long text inputs.
Zhenmei Shi, Yifei Ming, Xuan-Phi Nguyen
― 5 min read
New method improves language models' knowledge from limited data.
Zitong Yang, Neil Band, Shuangping Li
― 7 min read
Research on LLMs in multilingual mental health settings highlights successes and challenges.
Konstantinos Skianis, John Pavlopoulos, A. Seza Doğruöz
― 5 min read
A new method enhances predictions of language features using textual data.
Hamidreza Amirzadeh, Sadegh Jafari, Anika Harju
― 6 min read
A new method improves speech interactions by integrating recognition and response processes.
Robin Shing-Hei Yuen, Timothy Tin-Long Tse, Jian Zhu
― 5 min read
A new framework aims to enhance reliability and clarity in AI reasoning.
Debargha Ganguly, Srinivasan Iyengar, Vipin Chaudhary
― 7 min read
A new system encourages diverse perspectives in artificial intelligence discussions.
Joshua Ashkinaze, Emily Fry, Narendra Edara
― 3 min read
A new framework enhances hate speech detection and promotes fairness online.
Guanyi Mou, Kyumin Lee
― 6 min read
This study investigates toxic comments targeting marginalized groups in Bengali on social media.
Mukaffi Bin Moin, Pronay Debnath, Usafa Akther Rifa
― 6 min read
AI and machine learning are reshaping industries and daily life.
Benji Peng, Xuanhe Pan, Yizhu Wen
― 7 min read
Evaluating VLMs on spatial tasks using visual and unclear text.
Bowen Zhao, Leo Parker Dirac, Paulina Varshavskaya
― 6 min read
A new dataset aims to improve understanding of time-related question ambiguities.
Bhawna Piryani, Abdelrahman Abdallah, Jamshid Mozafari
― 5 min read
Research evaluates connections between speech and language models for improved recognition and translation.
Francesco Verdini, Pierfrancesco Melucci, Stefano Perna
― 5 min read
This method allows language models to consider alternative outcomes in text generation.
Ivi Chatzi, Nina Corvelo Benz, Eleni Straitouri
― 5 min read