New dataset evaluates language models' ability to handle time-aware information.
David Herel, Vojtech Bartek, Tomas Mikolov
― 5 min read
Computer Science - Computation and Language
RSSSLaVA-CXR improves chest X-ray report generation for better clinical efficiency.
Jinge Wu, Yunsoo Kim, Daqian Shi
― 4 min read
GAProtoNet enhances text classification by improving interpretability while maintaining high accuracy.
Ximing Wen, Wenjuan Tan, Rosina O. Weber
― 5 min read
A novel approach for creating labeled data in keyphrase generation using citation contexts.
Florian Boudin, Akiko Aizawa
― 7 min read
A system that learns and adapts through continuous interaction with its environment.
Yu Wang, Chi Han, Tongtong Wu
― 7 min read
A new approach to training language models improves efficiency and performance.
Yinmin Zhong, Zili Zhang, Bingyang Wu
― 7 min read
A new framework assesses medical knowledge in large language models.
Yuxuan Zhou, Xien Liu, Chen Ning
― 5 min read
New framework enhances AI planning by improving visual understanding and reasoning.
Yew Ken Chia, Qi Sun, Lidong Bing
― 6 min read
New dataset enhances AI's ability to handle conversation misunderstandings.
Javier Chiyah-Garcia, Alessandro Suglia, Arash Eshghi
― 6 min read
Maintaining meaning while transforming data is key for privacy and accuracy.
Muhan Zhang
― 5 min read
A new method boosts small models for telecom question answering.
Blessed Guda, Gabrial Zencha A., Lawrence Francis
― 6 min read
New insights into how context and similarity affect language model performance.
Stefan Arnold, Marian Fietta, Dilara Yesilbas
― 5 min read
Examining how BERT interprets words with multiple meanings.
Soniya Vijayakumar, Josef van Genabith, Simon Ostermann
― 5 min read
This study addresses challenges in audio language models for low-resource languages.
Potsawee Manakul, Guangzhi Sun, Warit Sirichotedumrong
― 5 min read
Examining how language models learn factual knowledge and their limitations.
Xiao Zhang, Miao Li, Ji Wu
― 7 min read
GroupDebate method reduces costs while improving accuracy in agent discussions.
Tongxuan Liu, Xingyu Wang, Weizhe Huang
― 5 min read
This study enhances emotion recognition systems for less common languages using high-resource data.
Hsi-Che Lin, Yi-Cheng Lin, Huang-Cheng Chou
― 6 min read
This paper evaluates how well language models explain scientific concepts.
Prasoon Bajpai, Niladri Chatterjee, Subhabrata Dutta
― 4 min read
Token pooling improves data storage while maintaining retrieval accuracy.
Benjamin Clavié, Antoine Chaffin, Griffin Adams
― 6 min read
A model improves speech tasks in multilingual settings, addressing code-switching challenges.
Jing Xu, Daxin Tan, Jiaqi Wang
― 5 min read
A new approach enhances robot learning by combining rich language instructions with data.
Yinpei Dai, Jayjun Lee, Nima Fazeli
― 5 min read
A study on LLM performance using instruction tuning and in-context learning.
Taihang Wang, Xiaoman Xu, Yimin Wang
― 5 min read
A new model enhances efficiency in collecting language data during fieldwork.
Aso Mahmudi, Borja Herce, Demian Inostroza Amestica
― 6 min read
This study examines how language models create effective research paper titles from abstracts.
Tohida Rehman, Debarshi Kumar Sanyal, Samiran Chattopadhyay
― 5 min read
This study examines the effectiveness of Sparse Autoencoders in understanding language model features.
David Chanin, James Wilken-Smith, Tomáš Dulka
― 6 min read
PODA enhances AI's ability to understand texts and reason logically.
Chenxu Wang, Ping Jian, Zhen Yang
― 6 min read
A new framework streamlines microstructure design using natural language commands.
Nikita Kartashov, Nikolaos N. Vlassis
― 7 min read
This research explores LLM effectiveness in various languages beyond English.
Daoyang Li, Mingyu Jin, Qingcheng Zeng
― 6 min read
Research shows AI can predict user stances from indirect social media posts.
Siyuan Brandon Loh, Liang Ze Wong, Prasanta Bhattacharya
― 6 min read
This article examines how different layers affect LLM performance.
Yang Zhang, Yanfei Dong, Kenji Kawaguchi
― 5 min read
A study on how AI agents follow user-defined rules using the ACS dataset.
Lior Madmoni, Amir Zait, Ilia Labzovsky
― 9 min read
CADA-GAN enhances ASR systems' performance across various recording environments.
Chien-Chun Wang, Li-Wei Chen, Cheng-Kang Chou
― 6 min read
New methods boost LLM performance by compressing token input.
Runsong Zhao, Pengcheng Huang, Xinyu Liu
― 5 min read
MQM-APE enhances the quality of machine translation evaluations through advanced error analysis.
Qingyu Lu, Liang Ding, Kanjian Zhang
― 7 min read
This study evaluates how well LLMs understand narrative tropes in movie summaries.
Hung-Ting Su, Ya-Ching Hsu, Xudong Lin
― 4 min read
FLEX method offers a new approach for evaluating text-to-SQL systems accurately.
Heegyu Kim, Taeyang Jeon, Seunghwan Choi
― 6 min read
New features enhance user experience in screen understanding and multilingual interactions.
Naman Goyal
― 6 min read
Using technology to gather plant trait information efficiently from the web.
Diego Marcos, Robert van de Vlasakker, Ioannis N. Athanasiadis
― 4 min read
EVA combines audio and visual signals for better speech recognition accuracy.
Yihan Wu, Yifan Peng, Yichen Lu
― 4 min read
A novel model enhances text embeddings through in-context learning strategies.
Chaofan Li, MingHao Qin, Shitao Xiao
― 5 min read