Khayyam Challenge (PersianMMLU): Is Your LLM Truly Wise to The Persian Language?
Research Area: Data, Evaluation
Keywords: LLM, Evaluation, Multitask, Persian Language Understanding
TL;DR: The Khayyam Challenge offers an evaluation framework for Persian-supporting LLMs, featuring 20,805 original, diverse questions accompanied by rich metadata.
Abstract: Evaluating Large Language Models (LLMs) is challenging due to their generative nature, necessitating precise evaluation methodologies. Additionally, non-English LLM evaluation lags behind English, resulting in the absence or weakness of LLMs for many languages.
In response to this necessity, we introduce Khayyam Challenge (also known as PersianMMLU), a meticulously curated collection comprising 20,805 four-choice questions sourced from 38 diverse tasks extracted from Persian examinations, spanning a wide spectrum of subjects, complexities, and ages. The primary objective of the Khayyam Challenge is to facilitate the rigorous evaluation of LLMs that support the Persian language. Distinctive features of the Khayyam Challenge are (i) its comprehensive coverage of various topics, including literary comprehension, mathematics, sciences, logic, intelligence testing, etc aimed at assessing different facets of LLMs such as language comprehension, reasoning, and information retrieval across various educational stages, from lower primary school to upper secondary school (ii) its inclusion of rich metadata such as human response rates, difficulty levels, and descriptive answers (iii) its utilization of new data to avoid data contamination issues prevalent in existing frameworks (iv) its use of original, non-translated data tailored for Persian speakers, ensuring the framework is free from translation challenges and errors while encompassing cultural nuances (v) its inherent scalability for future data updates and evaluations without requiring special human effort. Previous works lacked an evaluation framework that combined all of these features into a single comprehensive benchmark. Furthermore, we evaluate a wide range of existing LLMs that support the Persian language, with statistical analyses and interpretations of their outputs. We believe that the Khayyam Challenge will improve advancements in LLMs for the Persian language by highlighting the existing limitations of current models, while also enhancing the precision and depth of evaluations on LLMs, even within the English language context.
Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the COLM Code of Ethics on https://colmweb.org/CoE.html
Author Guide: I certify that this submission complies with the submission instructions as described on https://colmweb.org/AuthorGuide.html
Submission Number: 1499
Loading