ChLogic: Evaluating Robustness of Logical Reasoning in Chinese Expressions

Hugging Face Daily Papers Papers

Summary

Introduces ChLogic, an English-Chinese aligned benchmark that tests whether large language models preserve logical reasoning performance across languages, revealing persistent gaps influenced by surface realization and translation artifacts.

Large language models perform increasingly well on standardized logical reasoning benchmarks, but whether this ability remains robust beyond English is unclear. We introduce ChLogic, an English--Chinese aligned benchmark that tests whether models preserve logical reasoning performance when the same latent logical structure is expressed in English and diverse Chinese surface realizations. Built from formal logical templates, the benchmark contains three data sets: (i) the General aligned set, derived from 60 General Propositions across nine template families; (ii) the Difficult aligned set, derived from 40 Difficult Problems; and (iii) the Chinese-only set, covering 15 language-specific phenomenon types. Each aligned item pairs one English reference expression with five Chinese realizations. Experiments on Qwen3, Ministral, and GLM models reveal a persistent English--Chinese performance gap. Back-translation from standard Chinese into English often improves performance on the General aligned set, but produces mixed effects on the Difficult aligned set, where Qwen3-32B and GLM-5.1 perform worse after translation. These results indicate that Chinese surface realization, translation artifacts, and model-specific behavior jointly affect multilingual logical reasoning. Overall, ChLogic provides a useful stress test for the robustness of multilingual reasoning.
Original Article
View Cached Full Text

Cached at: 06/17/26, 03:35 AM

Paper page - ChLogic: Evaluating Robustness of Logical Reasoning in Chinese Expressions

Source: https://huggingface.co/papers/2606.17905

Abstract

ChLogic benchmark reveals persistent performance gaps between English and Chinese logical reasoning in large language models, influenced by surface realization differences and translation artifacts.

Large language modelsperform increasingly well on standardizedlogical reasoning benchmarks, but whether this ability remains robust beyond English is unclear. We introduce ChLogic, an English--Chinese aligned benchmark that tests whether models preserve logical reasoning performance when the same latent logical structure is expressed in English and diverse Chinesesurface realizations. Built from formal logical templates, the benchmark contains three data sets: (i) the General aligned set, derived from 60 General Propositions across nine template families; (ii) the Difficult aligned set, derived from 40 Difficult Problems; and (iii) the Chinese-only set, covering 15 language-specific phenomenon types. Each aligned item pairs one English reference expression with five Chinese realizations. Experiments on Qwen3, Ministral, and GLM models reveal a persistent English--Chinese performance gap.Back-translationfrom standard Chinese into English often improves performance on the General aligned set, but produces mixed effects on the Difficult aligned set, where Qwen3-32B and GLM-5.1 perform worse after translation. These results indicate that Chinesesurface realization, translation artifacts, and model-specific behavior jointly affect multilingual logical reasoning. Overall, ChLogic provides a useful stress test for the robustness ofmultilingual reasoning.

View arXiv pageView PDFGitHubAdd to collection

Get this paper in your agent:

hf papers read 2606\.17905

Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash

Models citing this paper0

No model linking this paper

Cite arxiv.org/abs/2606.17905 in a model README.md to link it from this page.

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2606.17905 in a dataset README.md to link it from this page.

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2606.17905 in a Space README.md to link it from this page.

Collections including this paper0

No Collection including this paper

Add this paper to acollectionto link it from this page.

Similar Articles

Hidden Language Consistency Phenomena in Reasoning LLMs

arXiv cs.CL

This paper studies multilingual reasoning models and reveals that language consistency in outputs can degrade or collapse with task difficulty, especially for less represented languages. It argues that evaluating multilingual capability requires jointly considering accuracy, language consistency, and task difficulty.

Evaluating Chinese Ambiguity Understanding in Large Language Models

arXiv cs.CL

This paper introduces CHA-Gen, a Chinese ambiguity dataset grounded in Potential Ambiguity theory, and evaluates several LLMs on ambiguity detection, finding that models struggle but benefit from chain-of-thought prompting, and that instruction tuning induces overconfidence.