Fingpt: Open-source financial large language models

H Yang, XY Liu, CD Wang - arxiv preprint arxiv:2306.06031, 2023 - arxiv.org
Large language models (LLMs) have shown the potential of revolutionizing natural
language processing tasks in diverse domains, sparking great interest in finance. Accessing …

SemEval-2023 task 12: sentiment analysis for african languages (AfriSenti-SemEval)

SH Muhammad, I Abdulmumin, SM Yimam… - arxiv preprint arxiv …, 2023 - arxiv.org
We present the first Africentric SemEval Shared task, Sentiment Analysis for African
Languages (AfriSenti-SemEval)-The dataset is available at https://github. com/afrisenti …

Just another day on Twitter: a complete 24 hours of Twitter data

J Pfeffer, D Matter, K Jaidka, O Varol… - Proceedings of the …, 2023 - ojs.aaai.org
At the end of October 2022, Elon Musk concluded his acquisition of Twitter. In the weeks and
months before that, several questions were publicly discussed that were not only of interest …

Multilingual text categorization and sentiment analysis: a comparative analysis of the utilization of multilingual approaches for classifying twitter data

G Manias, A Mavrogiorgou, A Kiourtis… - Neural Computing and …, 2023 - Springer
Text categorization and sentiment analysis are two of the most typical natural language
processing tasks with various emerging applications implemented and utilized in different …

SOCIALITE-LLAMA: An instruction-tuned model for social scientific tasks

G Dey, AV Ganesan, YK Lal, M Shah, S Sinha… - arxiv preprint arxiv …, 2024 - arxiv.org
Social science NLP tasks, such as emotion or humor detection, are required to capture the
semantics along with the implicit pragmatics from text, often with limited amounts of training …

Biomedical language models are robust to sub-optimal tokenization

BJ Gutierrez, H Sun, Y Su - arxiv preprint arxiv:2306.17649, 2023 - arxiv.org
As opposed to general English, many concepts in biomedical terminology have been
designed in recent history by biomedical professionals with the goal of being precise and …

The skipped beat: A study of sociopragmatic understanding in llms for 64 languages

C Zhang, KD Doan, Q Liao… - arxiv preprint arxiv …, 2023 - arxiv.org
Instruction tuned large language models (LLMs), such as ChatGPT, demonstrate remarkable
performance in a wide range of tasks. Despite numerous recent studies that examine the …

SuperTweetEval: A Challenging, Unified and Heterogeneous Benchmark for Social Media NLP Research

D Antypas, A Ushio, F Barbieri, L Neves… - arxiv preprint arxiv …, 2023 - arxiv.org
Despite its relevance, the maturity of NLP for social media pales in comparison with general-
purpose models, metrics and benchmarks. This fragmented landscape makes it hard for the …

HICL: Hashtag-Driven In-Context Learning for Social Media Natural Language Understanding

H Tan, C Xu, J Li, Y Zhang, Z Fang… - IEEE Transactions on …, 2024 - ieeexplore.ieee.org
Natural language understanding (NLU) is integral to various social media applications.
However, the existing NLU models rely heavily on context for semantic learning, resulting in …

Cordyceps@ LT-EDI: Patching Language-Specific Homophobia/Transphobia Classifiers with a Multilingual Understanding

D Ninalga - arxiv preprint arxiv:2309.13561, 2023 - arxiv.org
Detecting transphobia, homophobia, and various other forms of hate speech is difficult.
Signals can vary depending on factors such as language, culture, geographical region, and …