Challenge: Recent studies find 25-50% of evaluation datasets appear in training corpora . contamination hinders the possibility to differentiate memorization and reasoning skills.
Approach: They propose a two-player trading card game that is contaminated by a public engine and hidden card implementations to prevent benchmark saturation.
Outcome: The proposed benchmark is based on a new two-player trading card game similar to Magic: The Gathering.

Similar Papers

Investigating Data Contamination in Modern Benchmarks for Large Language Models (2024.naacl-long)

Copied to clipboard

Challenge: Existing evaluation benchmarks for large language models are inflated and inconsistent with actual performance.
Approach: They propose a retrieval-based system to explore potential overlaps between benchmarks and pretraining corpora and a protocol to investigate testset slot guessing.
Outcome: The proposed method exploits overlaps between evaluation benchmarks and pretraining corpora and masks a wrong answer in a multiple choice question and prompts the model to fill in the gap.
BenchMAX: A Comprehensive Multilingual Evaluation Suite for Large Language Models (2025.findings-emnlp)

Copied to clipboard

Challenge: Existing multilingual benchmarks focus primarily on language understanding tasks.
Approach: They develop a multi-way multilingual benchmark that measures critical capabilities of large language models across languages.
Outcome: Extensive experiments on BenchMAX reveal uneven utilization of core capabilities across languages, emphasizing the performance gaps that scaling model size alone does not resolve.
MathMist: A Parallel Multilingual Benchmark Dataset for Mathematical Problem Solving and Reasoning (2026.findings-eacl)

Copied to clipboard

Challenge: Existing benchmarks primarily focus on English or a narrow subset of high-resource languages, leaving significant gaps in assessing multilingual and cross-lingual mathematical reasoning.
Approach: They propose a parallel multilingual benchmark for mathematical problem solving and reasoning that encompasses 2,890 parallel Bangla-English gold standard artifacts.
Outcome: The proposed model encompasses 2,890 parallel Bangla-English gold standard artifacts, totaling 30K aligned question–answer pairs across thirteen languages, representing high-, medium-, and low-resource linguistic settings.
MuBench: Assessment of Multilingual Capabilities of Large Language Models Across 61 Languages (2026.findings-acl)

Copied to clipboard

Challenge: Existing evaluation datasets lack cross-lingual alignment, leaving assessments of multilingual capabilities fragmented in both language and skill coverage.
Approach: They propose to use multilingual consistency as a complementary metric to assess performance bottlenecks and guide model improvement.
Outcome: The proposed model lacks cross-lingual alignment and language coverage gaps between state-of-the-art models.
MMLU-ProX: A Multilingual Benchmark for Advanced Large Language Model Evaluation (2025.emnlp-main)

Copied to clipboard

Challenge: Existing large language model evaluation benchmarks focus on English, while current multilingual tasks lack parallel questions that specifically assess cross-lingual reasoning abilities.
Approach: They propose a comprehensive benchmark covering 29 languages, built on an English benchmark.
Outcome: The MMLU-ProX is a comprehensive benchmark covering 29 languages, built on an English benchmark.
MMLU-CF: A Contamination-free Multi-task Language Understanding Benchmark (2025.acl-long)

Copied to clipboard

Challenge: Multiple-choice question datasets like Massive Multitask Language Understanding (MMLU) have inevitably led to benchmark contamination, resulting in unreliable evaluation.
Approach: They propose a contamination-free MCQ benchmark called MMLU-CF which reassesses LLMs’ understanding of world knowledge by averting both unintentional and malicious data contamination.
Outcome: The proposed MMLU-CF reassesses LLMs’ understanding of world knowledge by averting both unintentional and malicious data contamination.
SALAD-Bench: A Hierarchical and Comprehensive Safety Benchmark for Large Language Models (2024.findings-acl)

Copied to clipboard

Challenge: SALAD-Bench is a safety benchmark specifically designed for LLMs . it provides a robust source for evaluating both attack and defense algorithms .
Approach: They propose a hierarchical safety benchmark specifically designed for LLMs . it uses a taxonomy of questions spanning three levels and a robust taxonomies based on a QA pair .
Outcome: The proposed safety benchmark shows that LLMs are resilient against emerging threats and the effectiveness of contemporary defense methods.
CRUXEVAL-X: A Benchmark for Multilingual Code Reasoning, Understanding and Execution (2025.acl-long)

Copied to clipboard

Challenge: Existing code benchmarks focus on code generation, while those for code reasoning are insufficient.
Approach: They propose a multi-lingual code reasoning benchmark that contains 19 programming languages and at least 600 subjects for each language.
Outcome: The proposed model trains on Python and achieves 34.4% Pass@1 in other languages, revealing the cross-language generalization of LLMs.
Data Contamination Can Cross Language Barriers (2024.emnlp-main)

Copied to clipboard

Challenge: Existing methods to detect contamination of public benchmarks are too superficial to reflect deeper forms of contamination.
Approach: They propose generalization-based approaches to unmask a cross-lingual form of contamination that inflates LLMs’ performance while evading current detection methods.
Outcome: The proposed model outperforms existing detection methods while avoiding contamination of public benchmarks in the pre-training data.
MEGAVERSE: Benchmarking Large Language Models Across Languages, Modalities, Models and Tasks (2024.naacl-long)

Copied to clipboard

Challenge: Several new LLMs have been introduced necessitating their evaluation on non-English languages.
Approach: They perform a thorough evaluation of the non-English capabilities of SoTA LLMs by comparing them on the same set of multilingual datasets.
Outcome: The proposed model outperforms models on multilingual datasets on 22 languages including low-resource African languages.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations