Showing 1–20 of 25 results
/ Date/ Name
Oct 28, 2022Moving beyond word lists: towards abstractive topic labels for human-like topics of scientific documentsJan 29, 2022Learning to pronounce as measuring cross-lingual joint orthography-phonology complexityFeb 26, 2024Immunization against harmful fine-tuning attacksMay 23, 2024Representation Noising: A Defence Mechanism Against Harmful FinetuningFeb 21, 2026Limits of Convergence-Rate Control for Open-Weight SafetyOct 20, 2023Self-Consistency of Large Language Models under AmbiguityMar 7, 2023Discovering substantive disagreement with review articles?Apr 16, 2021Citations are not opinions: a corpus linguistics approach to understanding how citations are madeSep 7, 2022SynSciPass: detecting appropriate uses of scientific text generationSep 28, 2022Using contradictions improves question answering systemsSep 19, 2024Evaluating Defences against Unsafe Feedback in RLHFMay 3, 2023Background Knowledge Grounding for Readable, Relevant, and Factual Biomedical Lay SummariesFeb 14, 2024Long-form evaluation of model editingFeb 22, 2021How are journals cited? characterizing journal citations by type of citationAug 17, 2023Semantic Consistency for Assuring Reliability of Large Language ModelsApr 7, 2025Content-aware rankings: a new approach to rankings in scholarshipAug 19, 2024Resolving Lexical Bias in Model EditingNov 10, 2022Measuring Reliability of Large Language Models through Semantic ConsistencyOct 18, 2022Title detection: a novel approach to automatically finding retractions and other editorial notices in the scholarly literatureMay 26, 2025Dependency Parsing is More Parameter-Efficient with Normalization