Results 81 to 90 of about 283,708 (114)

Test-Time Preference Optimization: On-the-Fly Alignment via Iterative Textual Feedback

International Conference on Machine Learning
Large language models (LLMs) demonstrate impressive performance but lack the flexibility to adapt to human preferences quickly without retraining. In this work, we introduce Test-time Preference Optimization (TPO), a framework that aligns LLM outputs ...
Yafu Li, Xuyang Hu, Xiaoye Qu, Linjie Li, Yu Cheng   +4 more
semanticscholar   +1 more source

Análise textual discursiva

Tópicos Educacionais
A presente pesquisa tem como objetivo exemplificar a aplicação da Análise Textual Discursiva (ATD) como metodologia de investigação qualitativa, buscando apresentar de forma detalhada o percurso de sua realização prática.
Elaine Cristina Nascimento da Silva, Janaína Farias de Ornellas   +1 more
semanticscholar   +1 more source

ChatGPT for Textual Analysis? How to Use Generative LLMs in Accounting Research

Management Sciences
Generative large language models (GLLMs), such as ChatGPT and GPT-4 by OpenAI, are emerging as powerful tools for textual analysis tasks in accounting research.
T. D. Kok
semanticscholar   +1 more source

FG-CLIP: Fine-Grained Visual and Textual Alignment

International Conference on Machine Learning
Contrastive Language-Image Pre-training (CLIP) excels in multimodal tasks such as image-text retrieval and zero-shot classification but struggles with fine-grained understanding due to its focus on coarse-grained short captions.
Chunyu Xie, Bin Wang, Fanjing Kong, Jincheng Li, Dawei Liang, Ge Zhang, Dawei Leng, Yuhui Yin   +7 more
semanticscholar   +1 more source

ChatTime: A Unified Multimodal Time Series Foundation Model Bridging Numerical and Textual Data

AAAI Conference on Artificial Intelligence
Human experts typically integrate numerical and textual multimodal information to analyze time series. However, most traditional deep learning predictors rely solely on unimodal numerical data, using a fixed-length window for training and prediction on a
Chengsen Wang, Qi Qi, Jingyu Wang, Haifeng Sun, Zirui Zhuang, Jinming Wu, Lei Zhang, Jianxin Liao   +7 more
semanticscholar   +1 more source

IDGenRec: LLM-RecSys Alignment with Textual ID Learning

Annual International ACM SIGIR Conference on Research and Development in Information Retrieval
LLM-based Generative recommendation has attracted significant attention. However, in contrast to standard NLP tasks that inherently operate on human vocabulary, current generative recommendation approaches struggle to effectively encode items within the ...
Juntao Tan, Shuyuan Xu, Wenyue Hua, Yingqiang Ge, Zelong Li, Yongfeng Zhang   +5 more
semanticscholar   +1 more source

Efficient Tuning and Inference for Large Language Models on Textual Graphs

International Joint Conference on Artificial Intelligence
Rich textual and topological information of textual graphs need to be modeled in real-world applications such as webpages, e-commerce, and academic articles.
Yun Zhu, Yaoke Wang, Haizhou Shi, Siliang Tang   +3 more
semanticscholar   +1 more source

STaRK: Benchmarking LLM Retrieval on Textual and Relational Knowledge Bases

Neural Information Processing Systems
Answering real-world complex queries, such as complex product search, often requires accurate retrieval from semi-structured knowledge bases that involve blend of unstructured (e.g., textual descriptions of products) and structured (e.g., entity ...
Shirley Wu, Shiyu Zhao, Michihiro Yasunaga, Kexin Huang, Kaidi Cao, Qian Huang, V. Ioannidis, Karthik Subbian, James Zou, J. Leskovec   +9 more
semanticscholar   +1 more source

Context is Key: A Benchmark for Forecasting with Essential Textual Information

arXiv.org
Forecasting is a critical task in decision-making across numerous domains. While historical numerical data provide a start, they fail to convey the complete context for reliable and accurate predictions.
A. Williams, Arjun Ashok, 'Etienne Marcotte, V. Zantedeschi, Jithendaraa Subramanian, Roland Riachi, James Requeima, Alexandre Lacoste, Irina Rish, Nicolas Chapados, Alexandre Drouin   +10 more
semanticscholar   +1 more source

AoE: Angle-optimized Embeddings for Semantic Textual Similarity

Annual Meeting of the Association for Computational Linguistics
,
Xianming Li, Jing Li
semanticscholar   +1 more source