Evaluation

Anything Goes? A Crosslinguistic Study of (Im)possible Language Learning in LMs ACL 2025 A Pipeline to Assess Merging Methods via Behavior and Internals EMNLP 2025 A Proactive Reliability Metric for Detecting Failures in Language Model Training EMNLP 2025 ArabicSense: A Benchmark for Evaluating Commonsense Reasoning in Arabic with Large Language Models COLING 2025 AraEval: An Arabic Multi-Task Evaluation Suite for Large Language Models EMNLP 2025 A Rapid Test for Accuracy and Bias of Face Recognition Technology WACV 2025 AraSafe: Benchmarking Safety in Arabic LLMs EMNLP 2025 ARC ‘Challenge’ Is Not That Challenging ACL 2025 A Reality Check on Context Utilisation for Retrieval-Augmented Generation ACL 2025 Are Bias Evaluation Methods Biased ? ACL 2025 Are Checklists Really Useful for Automatic Evaluation of Generative Tasks? EMNLP 2025 Are Images Indistinguishable to Humans Also Indistinguishable to Classifiers? CVPR 2025 Are Language Models Agnostic to Linguistically Grounded Perturbations? A Case Study of Indic Languages NAACL 2025 Are Language Models Consequentialist or Deontological Moral Reasoners? EMNLP 2025 Are Large Language Models Chronically Online Surfers? A Dataset for Chinese Internet Meme Explanation EMNLP 2025 Are Large Language Models for Education Reliable Across Languages? ACL 2025 Are LLMs Better than Reported? Detecting Label Errors and Mitigating Their Effect on Model Performance EMNLP 2025 Are LLMs (Really) Ideological? An IRT-based Analysis and Alignment Tool for Perceived Socio-Economic Bias in LLMs ACL 2025 Are LLMs reliable? An exploration of the reliability of large language models in clinical note generation ACL 2025 Arena-lite: Efficient and Reliable Large Language Model Evaluation via Tournament-Based Direct Comparisons EMNLP 2025 Are Small Language Models Ready to Compete with Large Language Models for Practical Applications? NAACL 2025 Are We Done with MMLU? NAACL 2025 Are You Doing Better Than Random Guessing? A Call for Using Negative Controls When Evaluating Causal Discovery Algorithms UAI 2025 ARGENT: Automatic Reference-free Evaluation for Open-Ended Text Generation without Source Inputs ACL 2025 ArithmAttack: Evaluating Robustness of LLMs to Noisy Context in Math Problem Solving ACL 2025