PerCoR: Evaluating Commonsense Reasoning in Persian via Multiple-Choice Sentence Completion

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Alikhani, Morteza, Bagherifard, Mohammadtaha, Zinvandi, Erfan, Sarmadi, Mehran
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912827025915904
author Alikhani, Morteza
Bagherifard, Mohammadtaha
Zinvandi, Erfan
Sarmadi, Mehran
author_facet Alikhani, Morteza
Bagherifard, Mohammadtaha
Zinvandi, Erfan
Sarmadi, Mehran
contents We introduced PerCoR (Persian Commonsense Reasoning), the first large-scale Persian benchmark for commonsense reasoning. PerCoR contains 106K multiple-choice sentence-completion problems drawn from more than forty news, cultural, and other web sources. We introduce a novel conjunction-based segmentation strategy to generate coherent sentence-completion pairs, enabling broad topical and structural diversity. To create challenging distractors, we propose DRESS-AF (Distractor Ranking via Embedding Similarity Scoring and Adversarial Filtering), a generation-free adversarial filtering method that selects distractors from the pool of gold continuations while maximising model confusion. Human annotators score 89% on PerCoR, while OpenAI-o3 achieves the highest performance at 92.18%, followed closely by Claude-Sonnet-3.7 (91.17%). The strongest open-source model, DeepSeek-R1, reaches 82.51%, underscoring both the dataset's difficulty and the remaining performance gap in Persian commonsense reasoning. We further show that DRESS-AF transfers to the English HellaSwag benchmark, increasing its difficulty without hurting human solvability. The dataset is available at https://huggingface.co/datasets/MCINext/PerCoR.
format Preprint
id arxiv_https___arxiv_org_abs_2510_22616
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle PerCoR: Evaluating Commonsense Reasoning in Persian via Multiple-Choice Sentence Completion
Alikhani, Morteza
Bagherifard, Mohammadtaha
Zinvandi, Erfan
Sarmadi, Mehran
Computation and Language
Artificial Intelligence
I.2.7
We introduced PerCoR (Persian Commonsense Reasoning), the first large-scale Persian benchmark for commonsense reasoning. PerCoR contains 106K multiple-choice sentence-completion problems drawn from more than forty news, cultural, and other web sources. We introduce a novel conjunction-based segmentation strategy to generate coherent sentence-completion pairs, enabling broad topical and structural diversity. To create challenging distractors, we propose DRESS-AF (Distractor Ranking via Embedding Similarity Scoring and Adversarial Filtering), a generation-free adversarial filtering method that selects distractors from the pool of gold continuations while maximising model confusion. Human annotators score 89% on PerCoR, while OpenAI-o3 achieves the highest performance at 92.18%, followed closely by Claude-Sonnet-3.7 (91.17%). The strongest open-source model, DeepSeek-R1, reaches 82.51%, underscoring both the dataset's difficulty and the remaining performance gap in Persian commonsense reasoning. We further show that DRESS-AF transfers to the English HellaSwag benchmark, increasing its difficulty without hurting human solvability. The dataset is available at https://huggingface.co/datasets/MCINext/PerCoR.
title PerCoR: Evaluating Commonsense Reasoning in Persian via Multiple-Choice Sentence Completion
topic Computation and Language
Artificial Intelligence
I.2.7
url https://arxiv.org/abs/2510.22616