paper-with-me

홈 › Papers

LLMEval-Logic: A Solver-Verified Chinese Benchmark for Logical Reasoning of LLMs with Adversarial Hardening

2026-05-19 · Ming Zhang, Qiyuan Peng, Yinxi Wei, Yujiong Shen, Kexin Tan, Yuhui Wang, Zhenghao Xiang, Junjie Ye, Zhangyue Yin, Zhiheng Xi, Shihan Dou, Tao Gui, Maxm Pan, Ruizhi Yang, Qi Zhang, Xuanjing Huang arxiv

Evaluating large language models (LLMs) on natural-language logical reasoning is essential because rule-governed tasks require conclusions to follow strictly from stated premises. Many existing logical-reasoning benchmarks are generated by templating natural-language items from sampled formulas, provide only coarse or unaudited formal annotations, and are now quickly saturated by frontier reasoning models. We present LLMEval-Logic, a Chinese logical reasoning benchmark built from realistic situational scenarios. Its pipeline forward-authors and expert-audits natural-language items together with their reference formalizations, verifies annotated answers with Z3, constructs expert rubrics for natural-to-formal grading, and hardens selected items through a closed-loop adversarial workflow. The benchmark is released in two paired subsets: a 246-item Base subset shipped with 1,400 expert-developed rubric atoms, and a 190-item Hard subset with 938 multi-step sub-questions over closed model spaces. Evaluating 14 frontier LLMs on LLMEval-Logic reveals substantial gaps in current models: the best model reaches only 37.5% Hard Item Accuracy, and even with reference symbols the highest joint Z3+Rubric formalization score among evaluated models reaches only 60.16%. Our benchmark is publicly available at https://github.com/llmeval/LLMEval-Logic.

📄 PDF Abstract BibTeX arXiv:2605.19597

Code (0)

등록된 구현이 없습니다.

Tasks

Logical Reasoning

Similar Papers 제목 키워드 기반

LLMEval-Fair: A Large-Scale Longitudinal Study on Robust and Fair Evaluation of Large Language Models

2025-08-07 · Ming Zhang, Yujiong Shen, Jingyi Deng, Yuhui Wang 외 arxiv

Existing evaluation of Large Language Models (LLMs) on static benchmarks is vulnerable to data contamination and leaderboard overfitting, critical issues that obscure true model capabilities. To address this, we introduc…

LLMEval-Med: A Real-world Clinical Benchmark for Medical LLMs with Physician Validation

2025-06-04 · Ming Zhang, Yujiong Shen, Zelin Li, Huayu Sha 외

Evaluating large language models (LLMs) in medicine is crucial because medical applications require high accuracy with little room for error. Current medical benchmarks have three main types: medical exam-based, comprehe…

Multiple-choice

TencentLLMEval: A Hierarchical Evaluation of Real-World Capabilities for Human-Aligned LLMs

2023-11-09 · Shuyi Xie, Wenlin Yao, Yong Dai, Shaobo Wang 외

Large language models (LLMs) have shown impressive capabilities across various natural language tasks. However, evaluating their alignment with human preferences remains a challenge. To this end, we propose a comprehensi…

BenchmarkingQuestion AnsweringText Generation

Instantiation-based Formalization of Logical Reasoning Tasks using Language Models and Logical Solvers

2025-01-28 · Mohammad Raza, Natasa Milic-Frayling

Robustness of reasoning remains a significant challenge for large language models, and addressing it is essential for the practical applicability of AI-driven reasoning systems. We introduce Semantic Self-Verification (S…

Logical Reasoning

Learning Algorithms via Neural Logic Networks

2019-04-02 · Ali Payani, Faramarz Fekri

We propose a novel learning paradigm for Deep Neural Networks (DNN) by using Boolean logic algebra. We first present the basic differentiable operators of a Boolean system such as conjunction, disjunction and exclusive-O…

Inductive logic programming