Profiles2020-2026
Hung-Yi Lee
National Taiwan University
18Papers
14Last author
17Unique co-authors
0First author
0Solo
First and last author come from byline position, which some venues assign alphabetically.
Recent papers18
- TASTE: Text-Aligned Speech Tokenization and Embedding for Spoken Language ModelingAuthor 5 of 6ICLR 2026 · 26 citations
- Pseudo2Real: Task Arithmetic for Pseudo-Label Correction in Automatic Speech RecognitionAuthor 7 of 7ACL Findings 2026
- ReMedi: Reasoner for Medical Clinical PredictionAuthor 4 of 5ACL Findings 2026
- TRACT: Regression-Aware Fine-tuning Meets Chain-of-Thought Reasoning for LLM-as-a-JudgeAuthor 2 of 3ACL 2025
- Codec-SUPERB: An In-Depth Analysis of Sound Codec ModelsAuthor 10 of 10ACL Findings 2024 · 23 citations
- Advancing Large Language Models to Capture Varied Speaking Styles and Respond Properly in Spoken ConversationsAuthor 3 of 3ACL 2024 · 15 citations
- Large Language Model as an Assignment Evaluator: Insights, Feedback, and Challenges in a 1000+ Student CourseAuthor 5 of 5EMNLP 2024 · 14 citations
- Chat Vector: A Simple Approach to Equip LLMs with Instruction Following and Model Alignment in New LanguagesAuthor 8 of 8ACL 2024 · 6 citations
- Merging Facts, Crafting Fallacies: Evaluating the Contradictory Nature of Aggregated Factual Claims in Long-Form GenerationsAuthor 2 of 2ACL Findings 2024 · 5 citations
- Can LLMs Understand the Implication of Emphasized Sentences in Dialogue?Author 2 of 2EMNLP Findings 2024 · 3 citations
- Meta-DiffuB: A Contextualized Sequence-to-Sequence Text Diffusion Model with Meta-ExplorationAuthor 7 of 8NeurIPS 2024 · 3 citations
- A Closer Look into Using Large Language Models for Automatic EvaluationAuthor 2 of 2EMNLP Findings 2023 · 33 citations
- Are Synonym Substitution Attacks Really Synonym Substitution Attacks?Author 2 of 2ACL Findings 2023 · 10 citations
- SUPERB-SG: Enhanced Speech processing Universal PERformance Benchmark for Semantic and Generative CapabilitiesAuthor 18 of 18ACL 2022 · 130 citations
- On the Transferability of Pre-trained Language Models: A Study from Artificial DatasetsAuthor 2 of 2AAAI 2022 · 33 citations
- Investigating the Reordering Capability in CTC-based Non-Autoregressive End-to-End Speech TranslationAuthor 4 of 4ACL Findings 2021 · 19 citations
- Is BERT a Cross-Disciplinary Knowledge Learner? A Surprising Finding of Pre-trained Models' TransferabilityAuthor 2 of 2EMNLP Findings 2021 · 13 citations
- LAMOL: LAnguage MOdeling for Lifelong Language LearningAuthor 3 of 3ICLR 2020 · 247 citations
