![[2606.02584] IdiomX A Multilingual Benchmark for Idiom Understanding, Retrieval, and Interpretation](/static/img/curated/desks/afbytes-tech.png)
[2606.02584] IdiomX A Multilingual Benchmark for Idiom Understanding, Retrieval, and Interpretation
Abstract page for arXiv paper 2606.02584: IdiomX A Multilingual Benchmark for Idiom Understanding, Retrieval, and Interpretation
America Forever Bytes
benchmarks · AFBytes
Other
benchmarks
Recent coverage
LURE: Alignment Evaluations to Reduce Evaluation Awareness — LessWrong
TLDR: * Frontier models can detect when they're being evaluated and change their behavior, which risks compromising safety benchmarks. * We introdu…
[2606.01804] SpeechEditBench: A Bilingual Multi-Attribute Benchmark for Instruction-Guided Speech Editing
Abstract page for arXiv paper 2606.01804: SpeechEditBench: A Bilingual Multi-Attribute Benchmark for Instruction-Guided Speech Editing
[2605.31086] Beyond Static Dialogues: Benchmarking Realistic, Heterogeneous, and Evolving Long-Term Memory
Abstract page for arXiv paper 2605.31086: Beyond Static Dialogues: Benchmarking Realistic, Heterogeneous, and Evolving Long-Term Memory
[2605.30788] XLGoBench: Detecting cross-lingual skill gaps with algorithmic tasks
Abstract page for arXiv paper 2605.30788: XLGoBench: Detecting cross-lingual skill gaps with algorithmic tasks
[2605.29872] Claim against Measurement: Statistical Artefacts in Quantum Error Mitigation Benchmarks
Abstract page for arXiv paper 2605.29872: Claim against Measurement: Statistical Artefacts in Quantum Error Mitigation Benchmarks
[2605.29170] UA-Legal-Bench: A Benchmark for Evaluating Large Language Models on Ukrainian Legal Reasoning
Abstract page for arXiv paper 2605.29170: UA-Legal-Bench: A Benchmark for Evaluating Large Language Models on Ukrainian Legal Reasoning
[2605.29230] Toward Ethical Facial Age Estimation: A Generalized Zero-Shot Benchmark Without Training on Children's Data
Abstract page for arXiv paper 2605.29230: Toward Ethical Facial Age Estimation: A Generalized Zero-Shot Benchmark Without Training on Children's Data
[2605.27566] DynaSchedBench: Calibrated Dynamic Scheduling Benchmarks and Observability Paradox in LLM-based Scheduling Agents
Abstract page for arXiv paper 2605.27566: DynaSchedBench: Calibrated Dynamic Scheduling Benchmarks and Observability Paradox in LLM-based Scheduling Agents