Study explores AI's effectiveness in predicting suicide risk through hotline conversations.
Yining Chen, Jianqiang Li, Changwei Song
― 6 min read
Computer Science - Computation and Language
RSSDoppelgänger aids language models in ensuring accurate and unbiased responses.
Shervin Ghasemlou, Ashish Katiyar, Aparajita Saraf
― 6 min read
This study assesses LLMs' abilities to tackle fraud and abusive language.
Joymallya Chakraborty, Wei Xia, Anirban Majumder
― 7 min read
A new framework combines federated learning and multimodal models to improve privacy and performance.
Jianyi Zhang, Hao Frank Yang, Ang Li
― 6 min read
New methods improve understanding of spoken language through innovative dataset.
Lennart Keller, Goran Glavaš
― 5 min read
MessIRve offers a unique dataset for Spanish information retrieval research.
Francisco Valentini, Viviana Cotik, Damián Furman
― 6 min read
This study evaluates how LLMs handle SPARQL queries and Knowledge Graphs.
Lars-Peter Meyer, Johannes Frey, Felix Brei
― 5 min read
New framework improves training data for language models using images and text.
Run Luo, Haonan Zhang, Longze Chen
― 4 min read
A new framework enhances voice identity confirmation accuracy.
Massa Baali, Abdulhamid Aldoobi, Hira Dhamyal
― 5 min read
Research reveals links between language models and human brain processing.
Emily Cheng, Richard J. Antonello
― 5 min read
New methods improve access to spoken news by segmenting topics more effectively.
Sakshi Deo Shukla, Pavel Denisov, Tugtekin Turan
― 6 min read
A new method enhances clarity in dialogue through effective referring expressions.
Bram Willemsen, Gabriel Skantze
― 7 min read
RegNLP aims to make understanding regulatory documents easier and more efficient.
Tuba Gokhan, Kexin Wang, Iryna Gurevych
― 5 min read
A new dataset aims to improve the understanding of gender bias in AI.
Vagrant Gautam, Julius Steuer, Eileen Bingert
― 5 min read
New approach improves robot understanding of navigation instructions using spatial awareness.
Muraleekrishna Gopinathan, Martin Masek, Jumana Abu-Khalaf
― 7 min read
A study on LLMs' capabilities in understanding musical intervals, chords, and scales.
Anna Kruspe
― 8 min read
This article reviews dropout methods for boosting small language models' performance.
Dylan Hillier, Leon Guertler, Bobby Cheng
― 5 min read
Introducing NLLB-E5, a model enhancing multilingual information access for low-resource languages.
Arkadeep Acharya, Rudra Murthy, Vishwajeet Kumar
― 5 min read
This article explores the NL-DAR framework for improving diagnostic reasoning with AI.
Nils Dycke, Matej Zečević, Ilia Kuznetsov
― 6 min read
A new method enhances accuracy in medical term normalization using language models.
Daniel B. Hier, Thanh Son Do, Tayo Obafemi-Ajayi
― 5 min read
Research showcases diffusion models for improved table-to-text conversion.
Aleksei S. Krylov, Oleg D. Somov
― 5 min read
Review of recent methods in automating process extraction using NLP techniques.
William Van Woensel, Soroor Motie
― 8 min read
A new method enhances how language models follow complex instructions.
Kuan Wang, Alexander Bukharin, Haoming Jiang
― 5 min read
AdaPPA enhances jailbreak attacks on language models by combining safe and harmful responses.
Lijia Lv, Weigang Zhang, Xuehai Tang
― 5 min read
A new method to enhance AI game masters using function calling in tabletop games.
Jaewoo Song, Andrew Zhu, Chris Callison-Burch
― 6 min read
Researchers fine-tune LLMs to enhance honesty and reliability in outputs.
Christopher M. Ackerman
― 5 min read
Small models offer unique advantages in AI, complementing larger models efficiently.
Lihu Chen, Gaël Varoquaux
― 6 min read
Introducing an innovative framework for testing language model interactions in role-playing scenarios.
Ilya Gusev
― 8 min read
This article discusses a step-by-step method for improving translation accuracy.
Eleftheria Briakou, Jiaming Luo, Colin Cherry
― 6 min read
Soft preference labels enhance the alignment of models with human choices.
Hiroki Furuta, Kuang-Huei Lee, Shixiang Shane Gu
― 5 min read
New model enhances speech generation in diverse dialects of pitch-accent languages.
Kazuki Yamauchi, Yuki Saito, Hiroshi Saruwatari
― 5 min read
TeXBLEU provides a reliable way to evaluate LaTeX expressions from spoken math.
Kyudan Jung, Nam-Joon Kim, Hyongon Ryu
― 5 min read
Enhancing Llama-3's capabilities with improved language mixture and training methods.
Ningyuan Xi, Yetao Wu, Kun Fan
― 6 min read
Study investigates how language models process Italian through multi-task learning.
Vivi Nastase, Giuseppe Samo, Chunyang Jiang
― 5 min read
A new approach to reduce inaccuracies in language models using skepticism.
Yetao Wu, Yihong Wang, Teng Chen
― 5 min read
This article discusses the challenges and solutions in evaluating grounded question answering models.
Sacha Muller, António Loison, Bilel Omrani
― 9 min read
Investigating how language models handle subject-verb agreement across different languages.
Vivi Nastase, Chunyang Jiang, Giuseppe Samo
― 5 min read
This study evaluates how LLMs process information using Olympic medal data.
Juhwan Choi, YoungBin Kim
― 5 min read
A new approach enhances research clarity using cognitive knowledge graphs and language models.
Gollam Rabby, Sören Auer, Jennifer D'Souza
― 5 min read
A new approach to make language models concise and effective.
Wei Liu, Yang Bai, Chengcheng Han
― 4 min read