ZEBRA: Zero-Shot Example-Based Retrieval Augmentation for Commonsense Question Answering Paper • 2410.05077 • Published Oct 7, 2024 • 5
Right Answer, Wrong Score: Uncovering the Inconsistencies of LLM Evaluation in Multiple-Choice Question Answering Paper • 2503.14996 • Published Mar 19, 2025 • 3
Optimizing LLMs for Italian: Reducing Token Fertility and Enhancing Efficiency Through Vocabulary Adaptation Paper • 2504.17025 • Published Apr 23, 2025 • 17
Maverick: Efficient and Accurate Coreference Resolution Defying Recent Trends Paper • 2407.21489 • Published Jul 31, 2024 • 3
LLMs Lost in Translation: M-ALERT uncovers Cross-Linguistic Safety Gaps Paper • 2412.15035 • Published Dec 19, 2024 • 4
Word Sense Linking: Disambiguating Outside the Sandbox Paper • 2412.09370 • Published Dec 12, 2024 • 10
Word Sense Linking Collection Word Sense Linking is the task designed to identify and disambiguate spans of text to their most suitable senses from a reference inventory. • 6 items • Updated Jan 13, 2025 • 6
FENICE Collection FENICE is a metric for summarization factuality, with a focus on interpretability. FENICE leverages NLI and claim extraction to assess factuality • 4 items • Updated Dec 5, 2024 • 4
Babelscape/mdeberta-v3-base-triplet-critic-xnli Text Classification • 0.3B • Updated Dec 3, 2024 • 4 • 10