Showing 1–20 of 49 results
/ Date/ Name
Jul 19, 2018Deconfounding age effects with fair representation learning when assessing dementiaApr 8, 2024Plug and Play with Prompts: A Prompt Tuning Approach for Controlling Text GenerationFeb 25, 2022On the data requirements of probingOct 1, 2020Examining the rhetorical capacities of neural language modelsJul 13, 2021What do writing features tell us about AI papers?Sep 15, 2020An information theoretic view on selecting linguistic probesMay 23, 2018Semi-supervised classification by reaching consensus among modalitiesOct 17, 2023A State-Vector Framework for Dataset EffectsOct 6, 2023Measuring Information in Text ExplanationsMay 16, 2021How is BERT surprised? Layerwise detection of linguistic anomaliesOct 13, 2022Predicting Fine-Tuning Performance with ProbingJan 6, 2026The Illusion of Specialization: Unveiling the Domain-Invariant "Standing Committee" in Mixture-of-Experts ModelsAug 25, 2022OOD-Probe: A Neural Interpretation of Out-of-Domain GeneralizationSep 1, 2021An unsupervised framework for tracing textual sources of moral changeFeb 5, 2025PerPO: Perceptual Preference Optimization via Discriminative RewardingMay 10, 2024LLM-Generated Black-box Explanations Can Be Adversarially HelpfulJul 3, 2025VERBA: Verbalizing Model Differences Using Large Language ModelsAug 27, 2023Situated Natural Language ExplanationsAug 20, 2018Detecting cognitive impairments by agreeing on interpretations of linguistic featuresNov 1, 2020Semantic coordinates analysis reveals language changes in the AI field