PMC-LLaMA: toward building open-source language models for medicine. [PDF]
J Am Med Inform AssocWu C +5 more
europepmc +2 more sources
OpenChat: Advancing Open-source Language Models with Mixed-Quality Data [PDF]
International Conference on Learning Representations, 2023 Nowadays, open-source large language models like LLaMA have emerged. Recent developments have incorporated supervised fine-tuning (SFT) and reinforcement learning fine-tuning (RLFT) to align these models with human goals.
Guan Wang +5 more
semanticscholar +1 more source
mmT5: Modular Multilingual Pre-Training Solves Source Language Hallucinations [PDF]
Conference on Empirical Methods in Natural Language Processing, 2023 Multilingual sequence-to-sequence models perform poorly with increased language coverage and fail to consistently generate text in the correct target language in few-shot settings.
Jonas Pfeiffer +5 more
semanticscholar +1 more source
Agent Lumos: Unified and Modular Training for Open-Source Language Agents [PDF]
Annual Meeting of the Association for Computational Linguistics, 2023 Closed-source agents suffer from several issues such as a lack of affordability, transparency, and reproducibility, particularly on complex interactive tasks. This motivates the development of open-source alternatives.
Da Yin +6 more
semanticscholar +1 more source
NLNDE at SemEval-2023 Task 12: Adaptive Pretraining and Source Language Selection for Low-Resource Multilingual Sentiment Analysis [PDF]
International Workshop on Semantic Evaluation, 2023 This paper describes our system developed for the SemEval-2023 Task 12 “Sentiment Analysis for Low-resource African Languages using Twitter Dataset”.
Mingyang Wang +4 more
semanticscholar +1 more source
OpenFlamingo: An Open-Source Framework for Training Large Autoregressive Vision-Language Models [PDF]
arXiv.org, 2023 We introduce OpenFlamingo, a family of autoregressive vision-language models ranging from 3B to 9B parameters. OpenFlamingo is an ongoing effort to produce an open-source replication of DeepMind's Flamingo models.
Anas Awadalla +15 more
semanticscholar +1 more source
GPT-NeoX-20B: An Open-Source Autoregressive Language Model [PDF]
BIGSCIENCE, 2022 We introduce GPT-NeoX-20B, a 20 billion parameter autoregressive language model trained on the Pile, whose weights will be made freely and openly available to the public through a permissive license. It is, to the best of our knowledge, the largest dense
Sid Black +16 more
semanticscholar +1 more source
PARAFRASE Jurnal Kajian Kebahasaan & Kesastraan, 2021 Abstrak. Artikel ini membahas perubahan struktur frasa nomina bahasa Inggris (bahasa sumber) ke dalam bahasa Indonesia (bahasa target), terutama frasa nomina dengan derivasi nomina sebagai head, dan strategi yang dipakai dalam menerjemahkan frasa nomina ...
Alfi Maulidiyah +1 more
semanticscholar +1 more source
FinGPT: Open-Source Financial Large Language Models [PDF]
Social Science Research Network, 2023 Large language models (LLMs) have shown the potential of revolutionizing natural language processing tasks in diverse domains, sparking great interest in finance.
Hongyang Yang, Xiao-Yang Liu, Chris Wang
semanticscholar +1 more source
Tracing Source Language Interference in Translation with Graph-Isomorphism Measures
Recent Advances in Natural Language Processing, 2021 Previous research has used linguistic features to show that translations exhibit traces of source language interference and that phylogenetic trees between languages can be reconstructed from the results of translations into the same language.
Koel Dutta Chowdhury +2 more
semanticscholar +1 more source