Saved in:
Bibliographic Details
Main Authors: Yu, Jifan, Wang, Xiaozhi, Tu, Shangqing, Cao, Shulin, Zhang-Li, Daniel, Lv, Xin, Peng, Hao, Yao, Zijun, Zhang, Xiaohan, Li, Hanming, Li, Chunyang, Zhang, Zheyuan, Bai, Yushi, Liu, Yantao, Xin, Amy, Lin, Nianyi, Yun, Kaifeng, Gong, Linlu, Chen, Jianhui, Wu, Zhili, Qi, Yunjia, Li, Weikai, Guan, Yong, Zeng, Kaisheng, Qi, Ji, Jin, Hailong, Liu, Jinxin, Gu, Yu, Yao, Yuan, Ding, Ning, Hou, Lei, Liu, Zhiyuan, Xu, Bin, Tang, Jie, Li, Juanzi
Format: Preprint
Published: 2023
Subjects:
Online Access:https://arxiv.org/abs/2306.09296
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916306151800832
author Yu, Jifan
Wang, Xiaozhi
Tu, Shangqing
Cao, Shulin
Zhang-Li, Daniel
Lv, Xin
Peng, Hao
Yao, Zijun
Zhang, Xiaohan
Li, Hanming
Li, Chunyang
Zhang, Zheyuan
Bai, Yushi
Liu, Yantao
Xin, Amy
Lin, Nianyi
Yun, Kaifeng
Gong, Linlu
Chen, Jianhui
Wu, Zhili
Qi, Yunjia
Li, Weikai
Guan, Yong
Zeng, Kaisheng
Qi, Ji
Jin, Hailong
Liu, Jinxin
Gu, Yu
Yao, Yuan
Ding, Ning
Hou, Lei
Liu, Zhiyuan
Xu, Bin
Tang, Jie
Li, Juanzi
author_facet Yu, Jifan
Wang, Xiaozhi
Tu, Shangqing
Cao, Shulin
Zhang-Li, Daniel
Lv, Xin
Peng, Hao
Yao, Zijun
Zhang, Xiaohan
Li, Hanming
Li, Chunyang
Zhang, Zheyuan
Bai, Yushi
Liu, Yantao
Xin, Amy
Lin, Nianyi
Yun, Kaifeng
Gong, Linlu
Chen, Jianhui
Wu, Zhili
Qi, Yunjia
Li, Weikai
Guan, Yong
Zeng, Kaisheng
Qi, Ji
Jin, Hailong
Liu, Jinxin
Gu, Yu
Yao, Yuan
Ding, Ning
Hou, Lei
Liu, Zhiyuan
Xu, Bin
Tang, Jie
Li, Juanzi
contents The unprecedented performance of large language models (LLMs) necessitates improvements in evaluations. Rather than merely exploring the breadth of LLM abilities, we believe meticulous and thoughtful designs are essential to thorough, unbiased, and applicable evaluations. Given the importance of world knowledge to LLMs, we construct a Knowledge-oriented LLM Assessment benchmark (KoLA), in which we carefully design three crucial factors: (1) For \textbf{ability modeling}, we mimic human cognition to form a four-level taxonomy of knowledge-related abilities, covering $19$ tasks. (2) For \textbf{data}, to ensure fair comparisons, we use both Wikipedia, a corpus prevalently pre-trained by LLMs, along with continuously collected emerging corpora, aiming to evaluate the capacity to handle unseen data and evolving knowledge. (3) For \textbf{evaluation criteria}, we adopt a contrastive system, including overall standard scores for better numerical comparability across tasks and models and a unique self-contrast metric for automatically evaluating knowledge-creating ability. We evaluate $28$ open-source and commercial LLMs and obtain some intriguing findings. The KoLA dataset and open-participation leaderboard are publicly released at https://kola.xlore.cn and will be continuously updated to provide references for developing LLMs and knowledge-related systems.
format Preprint
id arxiv_https___arxiv_org_abs_2306_09296
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle KoLA: Carefully Benchmarking World Knowledge of Large Language Models
Yu, Jifan
Wang, Xiaozhi
Tu, Shangqing
Cao, Shulin
Zhang-Li, Daniel
Lv, Xin
Peng, Hao
Yao, Zijun
Zhang, Xiaohan
Li, Hanming
Li, Chunyang
Zhang, Zheyuan
Bai, Yushi
Liu, Yantao
Xin, Amy
Lin, Nianyi
Yun, Kaifeng
Gong, Linlu
Chen, Jianhui
Wu, Zhili
Qi, Yunjia
Li, Weikai
Guan, Yong
Zeng, Kaisheng
Qi, Ji
Jin, Hailong
Liu, Jinxin
Gu, Yu
Yao, Yuan
Ding, Ning
Hou, Lei
Liu, Zhiyuan
Xu, Bin
Tang, Jie
Li, Juanzi
Computation and Language
The unprecedented performance of large language models (LLMs) necessitates improvements in evaluations. Rather than merely exploring the breadth of LLM abilities, we believe meticulous and thoughtful designs are essential to thorough, unbiased, and applicable evaluations. Given the importance of world knowledge to LLMs, we construct a Knowledge-oriented LLM Assessment benchmark (KoLA), in which we carefully design three crucial factors: (1) For \textbf{ability modeling}, we mimic human cognition to form a four-level taxonomy of knowledge-related abilities, covering $19$ tasks. (2) For \textbf{data}, to ensure fair comparisons, we use both Wikipedia, a corpus prevalently pre-trained by LLMs, along with continuously collected emerging corpora, aiming to evaluate the capacity to handle unseen data and evolving knowledge. (3) For \textbf{evaluation criteria}, we adopt a contrastive system, including overall standard scores for better numerical comparability across tasks and models and a unique self-contrast metric for automatically evaluating knowledge-creating ability. We evaluate $28$ open-source and commercial LLMs and obtain some intriguing findings. The KoLA dataset and open-participation leaderboard are publicly released at https://kola.xlore.cn and will be continuously updated to provide references for developing LLMs and knowledge-related systems.
title KoLA: Carefully Benchmarking World Knowledge of Large Language Models
topic Computation and Language
url https://arxiv.org/abs/2306.09296