Showing 1–17 of 17 results
/ Date/ Name
Sep 13, 2025Harmful Prompt Laundering: Jailbreaking LLMs with Abductive Styles and Symbolic EncodingSep 26, 2025Black-Box Hallucination Detection via Consistency Under the Uncertain ExpressionOct 23, 2023DPP-TTS: Diversifying prosodic features of speech via determinantal point processesSep 13, 2025Public Data Assisted Differentially Private In-Context LearningSep 1, 2022Enhancing Semantic Understanding with Self-supervised Methods for Abstractive Dialogue SummarizationAug 16, 2021BiHPF: Bilateral High-Pass Filters for Robust Deepfake DetectionFeb 23, 2024Entity-level Factual Adaptiveness of Fine-tuning based Abstractive Summarization ModelsJul 31, 2024Correcting Negative Bias in Large Language Models through Negative Attention Score AlignmentJan 27, 2021KoreALBERT: Pretraining a Lite BERT Model for Korean Language UnderstandingFeb 20, 2025Drift: Decoding-time Personalized Alignments with Implicit User PreferencesMay 19, 2025MultiActor-Audiobook: Zero-Shot Audiobook Generation with Faces and Voices of Multiple SpeakersJan 26, 2021Analyzing Zero-shot Cross-lingual Transfer in Supervised NLP TasksJan 26, 2021Evaluation of BERT and ALBERT Sentence Embedding Performance on Downstream NLP TasksApr 20, 2023Is Cross-modal Information Retrieval Possible without Training?Apr 19, 2023ContraCluster: Learning to Classify without Labels by Contrastive Self-Supervision and Prototype-Based Semi-SupervisionApr 19, 2023Shuffle & Divide: Contrastive Learning for Long TextJan 16, 2021SelfMatch: Combining Contrastive Self-Supervision and Consistency for Semi-Supervised Learning