Showing 1–20 of 134 results
/ Date/ Name
Mar 26, 2021Leveraging pre-trained representations to improve access to untranscribed speech from endangered languagesApr 21, 2021Sensitivity as a Complexity Measure for Sequence Classification TasksMay 10, 2022Richer Countries and Richer RepresentationsMay 24, 2022The Authenticity Gap in Human EvaluationSep 7, 2018Textual Analogy Parsing: What's Shared and What's Compared among Analogous FactsNov 14, 2022Follow the Wisdom of the Crowd: Effective Text Generation via Minimum Bayes Risk DecodingJul 14, 2023Othering and low status framing of immigrant cuisines in US restaurant reviews and large language modelsOct 4, 2022When and why vision-language models behave like bags-of-words, and what to do about it?Oct 28, 2024Belief in the Machine: Investigating Epistemological Blind Spots of Language ModelsApr 10, 2025Dynamic Cheatsheet: Test-Time Learning with Adaptive MemoryAug 27, 2024Can Unconfident LLM Annotations Be Used for Confident Conclusions?Feb 28, 2015When Are Tree Structures Necessary for Deep Learning of Representations?Jun 5, 2016Deep Reinforcement Learning for Dialogue GenerationMar 9, 2018Community Interaction and Conflict on the WebJan 16, 2026Beyond Tokens: Concept-Level Training Objectives for LLMsJan 7, 2026Accommodation and Epistemic Vigilance: A Pragmatic Account of Why LLMs Fail to Challenge Harmful BeliefsOct 2, 2025Transcribe, Translate, or Transliterate: An Investigation of Intermediate Representations in Spoken Language ModelsMay 21, 2019Sample Efficient Text Summarization Using a Single Pre-Trained TransformerOct 24, 2020Causal Effects of Linguistic PropertiesSep 4, 2019The Diversity-Innovation Paradox in Science