This study examines gender bias in teacher evaluations generated by AI models.
Yuanning Huang
― 9 min read
Computer Science - Computation and Language
RSSThis study focuses on improving dialogue systems' reliability by assessing confidence in responses.
Yi-Jyun Sun, Suvodip Dey, Dilek Hakkani-Tur
― 6 min read
Automating text annotation improves accuracy and efficiency in machine learning.
Jianfei Wu, Xubin Wang, Weijia Jia
― 5 min read
A new approach combines two KenLM models for better data filtering.
Yungi Kim, Hyunsoo Ha, Sukyung Lee
― 5 min read
A new technique reveals weaknesses in AI safety measures for language models.
Emet Bethany, Mazal Bethany, Juan Arturo Nolazco Flores
― 6 min read
Transforming text into lifelike digital movements using innovative models.
S. Rohollah Hosseyni, Ali Ahmad Rahmani, S. Jamal Seyedmohammadi
― 4 min read
Visualize how keywords and topics evolve over time with TimeLink.
Daniel Palamarchuk, Lemara Williams, Brian Mayer
― 6 min read
This study investigates generative models for effective keyphrase creation in scientific papers.
Anna Glazkova, Dmitry Morozov
― 6 min read
A new technique cuts memory needs for large language models while keeping performance.
Luning Wang, Shiyao Li, Xuefei Ning
― 5 min read
A new method enhances efficiency in processing long inputs for language models.
Di Liu, Meng Chen, Baotong Lu
― 5 min read
Causal language models show promise in solving Sudoku and Zebra puzzles.
Kulin Shah, Nishanth Dikkala, Xin Wang
― 4 min read
Exploring how memory functions in LLMs and its comparison to human memory.
Wei Wang, Qing Li
― 7 min read
A framework to enhance cooperative behavior using advanced AI technology.
Qiliang Chen, Sepehr Ilami, Nunzio Lore
― 7 min read
ReflectDiffu improves chatbot interactions by better understanding emotions.
Jiahao Yuan, Zixiang Di, Zhiqing Cui
― 5 min read
Research highlights working memory constraints in Transformer models during complex tasks.
Dongyu Gong, Hantao Zhang
― 5 min read
A new method enhances language model communication by adjusting personality traits.
Navya Jain, Zekun Wu, Cristian Munoz
― 7 min read
A study evaluates GPT-4 and clinalytix Medical AI for predicting delirium risk.
Mohamed Rezk, Patricia Cabanillas Silva, Fried-Michael Dahlweid
― 7 min read
A new method enhances speech recognition systems by detecting interruptions in speech.
Robin Amann, Zhaolin Li, Barbara Bruno
― 6 min read
A new text embedding model shows promise in multilingual tasks and performance.
Saba Sturua, Isabelle Mohr, Mohammad Kalim Akram
― 7 min read
A look into how IRL enhances language model performance and diversity.
Markus Wulfmeier, Michael Bloesch, Nino Vieillard
― 8 min read
Researchers assess large language models' role in organizing knowledge.
Hamed Babaei Giglou, Jennifer D'Souza, Sören Auer
― 5 min read
Improving dialogue summaries by focusing on conversation context and intent.
Eunice Akani, Benoit Favre, Frederic Bechet
― 6 min read
Householder Pseudo-Rotation enhances language models' performance and consistency in responses.
Van-Cuong Pham, Thien Huu Nguyen
― 7 min read
A new benchmark aims to improve uncertainty assessment in language models.
Pei-Fu Guo, Yun-Da Tsai, Shou-De Lin
― 5 min read
A new dataset and model improve parsing of complex academic texts.
Huawei Ji, Cheng Deng, Bo Xue
― 4 min read
A new framework enhances accuracy and reduces errors in medical text generation.
Sumera Anjum, Hanzhi Zhang, Wenjun Zhou
― 5 min read
SelECT-SQL boosts accuracy in converting natural language to SQL queries.
Ke Shen, Mayank Kejriwal
― 7 min read
SC-Phi2 is a small language model designed for efficient gameplay in StarCraft II.
Muhammad Junaid Khan, Gita Sukthankar
― 5 min read
A new approach enhances reliability in training language models through robust feedback systems.
Yuzi Yan, Xingzhou Lou, Jialian Li
― 5 min read
A new method improves model reasoning through structured programming traces.
Cassandra A. Cohen, William W. Cohen
― 8 min read
A new method uses audio to enhance machine pronunciation accuracy.
Siqi Sun, Korin Richmond
― 5 min read
A new system combines LLMs and symbolic AI for better accuracy and transparency.
Priyesh Vakharia, Abigail Kufeldt, Max Meyers
― 5 min read
HEARTS aims to improve stereotype detection in text while ensuring explainability and sustainability.
Theo King, Zekun Wu, Adriano Koshiyama
― 6 min read
A new method enhances conversation flow using multiple documents as sources.
Young-Suk Lee, Chulaka Gunasekara, Danish Contractor
― 6 min read
Enhancing language models for better Arabic dialect generation and cultural awareness.
Basel Mousi, Nadir Durrani, Fatema Ahmad
― 5 min read
Exploring the GenSEC challenge to improve speech transcription accuracy.
Chao-Han Huck Yang, Taejin Park, Yuan Gong
― 4 min read
NVLM enhances AI's grasp of language and visuals for diverse tasks.
Wenliang Dai, Nayeon Lee, Boxin Wang
― 5 min read
A new method improves data selection for training language models.
Simon Yu, Liangyu Chen, Sara Ahmadian
― 9 min read
Investigating how AI agents reproduce scientific results through a new benchmark.
Zachary S. Siegel, Sayash Kapoor, Nitya Nagdir
― 6 min read
THaMES offers a framework to reduce hallucinations in language models.
Mengfei Liang, Archish Arun, Zekun Wu
― 5 min read