WangchanLion and WangchanX MRC Eval

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Phatthiyaphaibun, Wannaphong, Nonesung, Surapon, Payoungkhamdee, Patomporn, Limkonchotiwat, Peerat, Udomcharoenchaikit, Can, Sawatphol, Jitkapat, Chaksangchaichot, Chompakorn, Chuangsuwanich, Ekapol, Nutanong, Sarana
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909178643087360
author Phatthiyaphaibun, Wannaphong
Nonesung, Surapon
Payoungkhamdee, Patomporn
Limkonchotiwat, Peerat
Udomcharoenchaikit, Can
Sawatphol, Jitkapat
Chaksangchaichot, Chompakorn
Chuangsuwanich, Ekapol
Nutanong, Sarana
author_facet Phatthiyaphaibun, Wannaphong
Nonesung, Surapon
Payoungkhamdee, Patomporn
Limkonchotiwat, Peerat
Udomcharoenchaikit, Can
Sawatphol, Jitkapat
Chaksangchaichot, Chompakorn
Chuangsuwanich, Ekapol
Nutanong, Sarana
contents This technical report describes the development of WangchanLion, an instruction fine-tuned model focusing on Machine Reading Comprehension (MRC) in the Thai language. Our model is based on SEA-LION and a collection of instruction following datasets. To promote open research and reproducibility, we publicly release all training data, code, and the final model weights under the Apache-2 license. To assess the contextual understanding capability, we conducted extensive experimental studies using two Thai MRC datasets, XQuAD and Iapp_wiki_qa_squad. Experimental results demonstrate the model's ability to comprehend the context and produce an answer faithful to the reference one in 0-shot and 1-shot settings. In addition, our evaluation goes beyond the traditional MRC. We propose a new evaluation scheme assessing the answer's correctness, helpfulness, conciseness, and contextuality. Our code is available publicly at https://github.com/vistec-AI/WangchanLion.
format Preprint
id arxiv_https___arxiv_org_abs_2403_16127
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle WangchanLion and WangchanX MRC Eval
Phatthiyaphaibun, Wannaphong
Nonesung, Surapon
Payoungkhamdee, Patomporn
Limkonchotiwat, Peerat
Udomcharoenchaikit, Can
Sawatphol, Jitkapat
Chaksangchaichot, Chompakorn
Chuangsuwanich, Ekapol
Nutanong, Sarana
Computation and Language
Artificial Intelligence
This technical report describes the development of WangchanLion, an instruction fine-tuned model focusing on Machine Reading Comprehension (MRC) in the Thai language. Our model is based on SEA-LION and a collection of instruction following datasets. To promote open research and reproducibility, we publicly release all training data, code, and the final model weights under the Apache-2 license. To assess the contextual understanding capability, we conducted extensive experimental studies using two Thai MRC datasets, XQuAD and Iapp_wiki_qa_squad. Experimental results demonstrate the model's ability to comprehend the context and produce an answer faithful to the reference one in 0-shot and 1-shot settings. In addition, our evaluation goes beyond the traditional MRC. We propose a new evaluation scheme assessing the answer's correctness, helpfulness, conciseness, and contextuality. Our code is available publicly at https://github.com/vistec-AI/WangchanLion.
title WangchanLion and WangchanX MRC Eval
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2403.16127