Publications

Papers and preprints.

2023

  1. Self-Specialization: Uncovering Latent Expertise within Large Language Models
    Junmo Kang, Hongyin Luo, Yada Zhu, and 5 more authors
    arXiv preprint arXiv:2310.00160 2023
    PDF
  2. Joint Audio and Speech Understanding
    Yuan Gong, Alexander H Liu, Hongyin Luo, and 2 more authors
    ASRU 2023
    PDF Code
  3. Natural Language Embedded Programs for Hybrid Language Symbolic Reasoning
    Tianhua Zhang*, Jiaxin Ge*, Hongyin Luo*, and 7 more authors
    arXiv preprint arXiv:2309.10814 2023
    PDF Code
  4. Dola: Decoding by contrasting layers improves factuality in large language models
    Yung-Sung Chuang, Yujia Xie, Hongyin Luo, and 3 more authors
    arXiv preprint arXiv:2309.03883 2023
    PDF Code
  5. ConvRGX: Recognition, Generation, and Extraction for Self-trained Conversational Question Answering
    Tianhua Zhang, Liping Tang, Wei Fang, and 4 more authors
    In Proceedings of the Third DialDoc Workshop on Document-grounded Dialogue and Conversational Question Answering 2023
    PDF
  6. SAIL: Search-Augmented Instruction Learning
    Hongyin Luo*, Tianhua Zhang*, Yung-Sung Chuang, and 6 more authors
    EMNLP 2023
    PDF Code
  7. Entailment as Robust Self-Learner
    Jiaxin Ge*, Hongyin Luo*, Yoon Kim, and 1 more author
    ACL 2023
    PDF Code
  8. Listen, Think, and Understand
    Yuan Gong, Hongyin Luo, Alexander H Liu, and 2 more authors
    arXiv preprint arXiv:2305.10790 2023
    PDF Code
  9. Chain of Thought Prompt Tuning for Vision-Language Models
    Jiaxin Ge, Hongyin Luo, Siyuan Qian, and 3 more authors
    CoRR 2023
    PDF
  10. interpretable Unified Language Checking
    Tianhua Zhang*, Hongyin Luo*, Yung-Sung Chuang, and 7 more authors
    ASRU 2023
    PDF Code
  11. Logic Against Bias: Textual Entailment Mitigates Stereotypical Sentence Reasoning
    Hongyin Luo, and James Glass
    EACL 2023
    PDF Code

2022

  1. Cooperative Self-training of Machine Reading Comprehension
    Hongyin Luo, Shang-Wen Li, Mingye Gao, and 2 more authors
    In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies 2022
    PDF Code
  2. DiffCSE: Difference-based Contrastive Learning for Sentence Embeddings
    Yung-Sung Chuang, Rumen Dangovski, Hongyin Luo, and 7 more authors
    arXiv preprint arXiv:2204.10298 2022
    PDF Code
  3. Self-Training for Natural Language Processing
    Hongyin Luo
    2022
    PDF

2021

  1. Mitigating biases in toxic language detection through invariant rationalization
    Yung-Sung Chuang, Mingye Gao, Hongyin Luo, and 4 more authors
    arXiv preprint arXiv:2106.07240 2021
    PDF Code
  2. Meta-learning for downstream aware and agnostic pretraining
    Hongyin Luo, Shuyan Dong, Yung-Sung Chuang, and 1 more author
    arXiv preprint arXiv:2106.03270 2021
    PDF
  3. Knowledge grounded conversational symptom detection with graph memory networks
    Hongyin Luo, Shang-Wen Li, and James Glass
    arXiv preprint arXiv:2101.09773 2021
    PDF
  4. Joint Retrieval-Extraction Training for Evidence-Aware Dialog Response Selection.
    Hongyin Luo, James R Glass, Garima Lalwani, and 2 more authors
    In Interspeech 2021
    PDF

2020

  1. Prototypical q networks for automatic conversational diagnosis and few-shot new disease adaption
    Hongyin Luo, Shang-Wen Li, and James Glass
    arXiv preprint arXiv:2005.11153 2020
    PDF

2019

  1. Improving neural language models by segmenting, attending, and predicting the future
    Hongyin Luo, Lan Jiang, Yonatan Belinkov, and 1 more author
    arXiv preprint arXiv:1906.01702 2019
    PDF Code
  2. Integrating Video Retrieval and Moment Detection in a Unified Corpus for Video Question Answering.
    Hongyin Luo, Mitra Mohtarami, James R Glass, and 2 more authors
    In INTERSPEECH 2019
    PDF
  3. Neural attentions for natural language understanding and modeling
    Hongyin Luo
    2019
    PDF

2018

  1. Learning word representations with cross-sentence dependency for end-to-end co-reference resolution
    Hongyin Luo, and Jim Glass
    In Proceedings of the 2018 conference on empirical methods in natural language processing 2018
    PDF

2016

  1. DrMAD: distilling reverse-mode automatic differentiation for optimizing hyperparameters of deep neural networks
    Jie Fu, Hongyin Luo, Jiashi Feng, and 2 more authors
    arXiv preprint arXiv:1601.00917 2016
    PDF Code

2015

  1. Online learning of interpretable word embeddings
    Hongyin Luo, Zhiyuan Liu, Huanbo Luan, and 1 more author
    In Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing 2015
    PDF Code