May 27, 2024, 4:49 a.m. | Jonas Becker, Jan Philip Wahle, Bela Gipp, Terry Ruas

cs.CL updates on arXiv.org arxiv.org

arXiv:2405.15604v1 Announce Type: new
Abstract: Text generation has become more accessible than ever, and the increasing interest in these systems, especially those using large language models, has spurred an increasing number of related publications. We provide a systematic literature review comprising 244 selected papers between 2017 and 2024. This review categorizes works in text generation into five main tasks: open-ended text generation, summarization, translation, paraphrasing, and question answering. For each task, we review their relevant characteristics, sub-tasks, and specific challenges …

abstract arxiv become challenges cs.cl evaluation ever language language models large language large language models literature papers publications review systems tasks text text generation type

Senior Data Engineer

@ Displate | Warsaw

Lead Python Developer - Generative AI

@ S&P Global | US - TX - VIRTUAL

Analytics Engineer - Design Experience

@ Canva | Sydney, Australia

Data Architect

@ Unisys | Bengaluru - RGA Tech Park

Data Architect

@ HP | PSR01 - Bengaluru, Pritech Park- SEZ (PSR01)

Streetlight Analyst

@ DTE Energy | Belleville, MI, US