RAGViz reveals how AI generates answers, making its workings more transparent.
Tevin Wang, Jingyuan He, Chenyan Xiong
― 6 min read
Computer Science - Computation and Language
RSSA new framework allows AI agents to create actions dynamically for better problem-solving.
Dang Nguyen, Viet Dac Lai, Seunghyun Yoon
― 9 min read
Learn how selective training can improve robot learning efficiency and adaptability.
Junjiao Tian, Chengyue Huang, Zsolt Kira
― 4 min read
Discover how safety guardrails protect smart models from harmful prompts.
Sejoon Oh, Yiqiao Jin, Megha Sharma
― 5 min read
1-bit models show great potential in machine learning efficiency and performance.
Majid Daliri, Zhao Song, Chiwun Yang
― 5 min read
Exploring how well AI understands human communication.
Mingyue Jian, Siddharth Narayanaswamy
― 6 min read
Exploring the odd mistakes made by large language models.
William F. Bradley
― 5 min read
A new method for testing language models using randomized text.
William F. Bradley
― 6 min read
A new approach uses AI to support endangered languages like Erzya and Skolt Sami.
Mika Hämäläinen
― 5 min read
A new open-source toolkit simplifies Arabic text processing with advanced features.
Tymaa Hammouda, Mustafa Jarrar, Mohammed Khalilia
― 6 min read
Research shows new methods to better align LLMs with human feedback.
Zichen Liu, Changyu Chen, Chao Du
― 6 min read
A new method helps language models learn through guided feedback.
Liat Bezalel, Eyal Orgad, Amir Globerson
― 6 min read
New methods improve event prediction in temporal knowledge graphs.
Yukun Cao, Lisheng Wang, Luobing Huang
― 7 min read
RWKV combines strengths of Transformers and RNNs for efficient AI processing.
Akul Datta
― 8 min read
Discover how personalized search is changing the way we find information online.
Sheshera Mysore, Garima Dhanania, Kishor Patil
― 6 min read
Research shows ways to enhance context awareness in language models for better responses.
Yihan Wang, Andrew Bai, Nanyun Peng
― 5 min read
A new method aims to reduce bias in language models' predictions.
Karuna Bhaila, Minh-Hao Van, Kennedy Edemacu
― 9 min read
Introducing a new model and benchmark for evaluating multi-audio tasks.
Yiming Chen, Xianghu Yue, Xiaoxue Gao
― 5 min read
A look at how counterfactual explanations improve AI text classifiers.
Stephen McAleese, Mark Keane
― 8 min read
A look at activation steering for improving AI memory handling.
Atakan Seyitoğlu, Aleksei Kuvshinov, Leo Schwinn
― 7 min read
Vocal Sandbox allows seamless collaboration between humans and robots through interactive learning.
Jennifer Grannen, Siddharth Karamcheti, Suvir Mirchandani
― 7 min read
Examining the potential dangers of using AI in health decisions.
Jiawei Zhou, Amy Z. Chen, Darshi Shah
― 9 min read
A new dataset evaluates large language models for predicting material properties.
Andre Niyongabo Rubungo, Kangming Li, Jason Hattrick-Simpers
― 7 min read
Research aims to help people regain speech using muscle signals.
Harshavardhana T. Gowda, Zachary D. McNaughton, Lee M. Miller
― 6 min read
A look into improving search through multimodal large language models.
Sheng-Chieh Lin, Chankyu Lee, Mohammad Shoeybi
― 6 min read
Modern technology aids in preserving the endangered Skolt Sami language.
Khalid Alnajjar, Mika Hämäläinen, Jack Rueter
― 7 min read
MILU aims to improve language models for Indian languages.
Sshubam Verma, Mohammed Safi Ur Rahman Khan, Vishwajeet Kumar
― 6 min read
Computers are learning to find nature images for scientists more effectively.
Edward Vendrow, Omiros Pantazis, Alexander Shepard
― 5 min read
Examining how news shapes views on AI's negative effects.
Mowafak Allaham, Kimon Kieslich, Nicholas Diakopoulos
― 6 min read
MORCELA adjusts language model scores to better reflect human language judgment.
Lindia Tjuatja, Graham Neubig, Tal Linzen
― 6 min read
Integrating phonemic transcriptions can enhance LLM performance across different language scripts.
Hoang Nguyen, Khyati Mahajan, Vikas Yadav
― 6 min read
KG-CoI improves the accuracy of hypotheses generated by large language models.
Guangzhi Xiong, Eric Xie, Amir Hassan Shariatmadari
― 6 min read
Exploring LLMs' struggles with analogical reasoning compared to children and adults.
Claire E. Stevenson, Alexandra Pafford, Han L. J. van der Maas
― 4 min read
New techniques enhance large language models' ability in complex arithmetic reasoning.
Md Rifat Arefin, Gopeshh Subbaraj, Nicolas Gontier
― 6 min read
A study compares human and AI creativity in storytelling.
Mete Ismayilzada, Claire Stevenson, Lonneke van der Plas
― 6 min read
A new benchmark tests AI agents in realistic CRM tasks.
Kung-Hsiang Huang, Akshara Prabhakar, Sidharth Dhawan
― 6 min read
A look into how language models mimic human cognitive functions.
Badr AlKhamissi, Greta Tuckute, Antoine Bosselut
― 6 min read
Intelligent agents improve through a balance of successes and failures.
Philip Lippmann, Matthijs T. J. Spaan, Jie Yang
― 7 min read
A method to improve steering vector effectiveness in language models.
Sviatoslav Chalnev, Matthew Siu, Arthur Conmy
― 5 min read
ORMA improves molecule-text matching with innovative alignment techniques.
Zijun Min, Bingshuai Liu, Liang Zhang
― 8 min read