all AI news
Answer is All You Need: Instruction-following Text Embedding via Answering the Question
Feb. 16, 2024, 5:47 a.m. | Letian Peng, Yuwei Zhang, Zilong Wang, Jayanth Srinivasa, Gaowen Liu, Zihan Wang, Jingbo Shang
cs.CL updates on arXiv.org arxiv.org
Abstract: This work aims to build a text embedder that can capture characteristics of texts specified by user instructions. Despite its tremendous potential to deploy user-oriented embeddings, none of previous approaches provides a concrete solution for it. This paper offers a new viewpoint, which treats the instruction as a question about the input text and encodes the expected answers to obtain the representation accordingly. Intuitively, texts with the same (implicit) semantics would share similar answers following …
abstract arxiv build concrete cs.cl deploy embedding embeddings paper question solution text text embedding type via work
More from arxiv.org / cs.CL updates on arXiv.org
Benchmarking LLMs via Uncertainty Quantification
2 days, 3 hours ago |
arxiv.org
CARE: Extracting Experimental Findings From Clinical Literature
2 days, 3 hours ago |
arxiv.org
Jobs in AI, ML, Big Data
Data Architect
@ University of Texas at Austin | Austin, TX
Data ETL Engineer
@ University of Texas at Austin | Austin, TX
Lead GNSS Data Scientist
@ Lurra Systems | Melbourne
Senior Machine Learning Engineer (MLOps)
@ Promaton | Remote, Europe
Research Scientist
@ Meta | Menlo Park, CA
Principal Data Scientist
@ Mastercard | O'Fallon, Missouri (Main Campus)