Hongfu Liu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Hongfu Liu has a total of 10 co-authors. Here are the top co-authors by number of shared publications:
- Ye Wang
School of Computing, National University of Singapore, Singapore
6 shared publications - Hengguan Huang
National University of Singapore
1 shared publication - Hengguan Huang
School of Computing National University of Singapore
1 shared publication - Michael Shieh
National University of Singapore
1 shared publication - Min-Yen Kan
School of Computing, National University of Singapore, Singapore, Singapore
1 shared publication - Mingqian Shi
School of Computing National University of Singapore Singapore
1 shared publication
Latest Publications
- Open Access
- 1 January 2024
- Published by Association for Computational Linguistics (ACL)
- p. 7213-7224
Advancing Adversarial Suffix Transfer Learning on Aligned Large Language Models
Hongfu Liu, Yuxi Xie, Ye Wang, Michael Shieh. Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing. 2024.
- 1 January 2024
- Published by Association for Computational Linguistics (ACL)
- p. 7213-7224
Open AccessAdvancing Adversarial Suffix Transfer Learning on Aligned Large Language Models
Hongfu Liu, Yuxi Xie, Ye Wang, Michael Shieh. Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing. 2024.
- Open Access
- 1 January 2024
- Published by Association for Computational Linguistics (ACL)
- p. 7138-7155
Advancing Test-Time Adaptation in Wild Acoustic Test Settings
Hongfu Liu, Hengguan Huang, Ye Wang. Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing. 2024.
- 1 January 2024
- Published by Association for Computational Linguistics (ACL)
- p. 7138-7155
Open AccessAdvancing Test-Time Adaptation in Wild Acoustic Test Settings
Hongfu Liu, Hengguan Huang, Ye Wang. Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing. 2024.
- Open Access
- 1 January 2024
- Published by Association for Computational Linguistics (ACL)
- p. 6277-6295
Discursive Socratic Questioning: Evaluating the Faithfulness of Language Models’ Understanding of Discourse Relations
Yisong Miao, Hongfu Liu, Wenqiang Lei, Nancy Chen, Min-Yen Kan. Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2024.
- 1 January 2024
- Published by Association for Computational Linguistics (ACL)
- p. 6277-6295
Open AccessDiscursive Socratic Questioning: Evaluating the Faithfulness of Language Models’ Understanding of Discourse Relations
Yisong Miao, Hongfu Liu, Wenqiang Lei, Nancy Chen, Min-Yen Kan. Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2024.
- Open Access
Advancing Test-Time Adaptation for Acoustic Foundation Models in Open-World Shifts
Test-Time Adaptation (TTA) is a critical paradigm for tackling distribution shifts during inference, especially in visual recognition tasks. However, while acoustic models face similar challenges due to distribution shifts in test-time speech, TTA techniques specifically designed for acoustic modeling in the context of open-world data shifts remain scarce. This gap is further exacerbated when considering the unique characteristics of acoustic foundation models: 1) they are primarily built on transformer architectures with layer normalization and 2) they deal with test-time speech data of varying lengths in a non-stationary manner. These aspects make the direct application of vision-focused TTA methods, which are mostly reliant on batch normalization and assume independent samples, infeasible. In this paper, we delve into TTA for pre-trained acoustic models facing open-world data shifts. We find that noisy, high-entropy speech frames, often non-silent, carry key semantic content. Traditional TTA methods might inadvertently filter out this information using potentially flawed heuristics. In response, we introduce a heuristic-free, learning-based adaptation enriched by confidence enhancement. Noting that speech signals' short-term consistency, we also apply consistency regularization during test-time optimization. Our experiments on synthetic and real-world datasets affirm our method's superiority over existing baselines.
Open AccessAdvancing Test-Time Adaptation for Acoustic Foundation Models in Open-World Shifts
Test-Time Adaptation (TTA) is a critical paradigm for tackling distribution shifts during inference, especially in visual recognition tasks. However, while acoustic models face similar challenges due to distribution shifts in test-time speech, TTA techniques specifically designed for acoustic modeling in the context of open-world data shifts remain scarce. This gap is further exacerbated when considering the unique characteristics of acoustic foundation models: 1) they are primarily built on transformer architectures with layer normalization and 2) they deal with test-time speech data of varying lengths in a non-stationary manner. These aspects make the direct application of vision-focused TTA methods, which are mostly reliant on batch normalization and assume independent samples, infeasible. In this paper, we delve into TTA for pre-trained acoustic models facing open-world data shifts. We find that noisy, high-entropy speech frames, often non-silent, carry key semantic content. Traditional TTA methods might inadvertently filter out this information using potentially flawed heuristics. In response, we introduce a heuristic-free, learning-based adaptation enriched by confidence enhancement. Noting that speech signals' short-term consistency, we also apply consistency regularization during test-time optimization. Our experiments on synthetic and real-world datasets affirm our method's superiority over existing baselines.
- Open Access
Towards Informative Few-Shot Prompt with Maximum Information Gain for In-Context Learning
Large Language models (LLMs) possess the capability to engage In-context Learning (ICL) by leveraging a few demonstrations pertaining to a new downstream task as conditions. However, this particular learning paradigm suffers from high instability stemming from substantial variances induced by factors such as the input distribution of selected examples, their ordering, and prompt formats. In this work, we demonstrate that even when all these factors are held constant, the random selection of examples still results in high variance. Consequently, we aim to explore the informative ability of data examples by quantifying the Information Gain (IG) obtained in prediction after observing a given example candidate. Then we propose to sample those with maximum IG. Additionally, we identify the presence of template bias, which can lead to unfair evaluations of IG during the sampling process. To mitigate this bias, we introduce Calibration Before Sampling strategy. The experimental results illustrate that our proposed method can yield an average relative improvement of 14.3% across six classification tasks using three LLMs.
Open AccessTowards Informative Few-Shot Prompt with Maximum Information Gain for In-Context Learning
Large Language models (LLMs) possess the capability to engage In-context Learning (ICL) by leveraging a few demonstrations pertaining to a new downstream task as conditions. However, this particular learning paradigm suffers from high instability stemming from substantial variances induced by factors such as the input distribution of selected examples, their ordering, and prompt formats. In this work, we demonstrate that even when all these factors are held constant, the random selection of examples still results in high variance. Consequently, we aim to explore the informative ability of data examples by quantifying the Information Gain (IG) obtained in prediction after observing a given example candidate. Then we propose to sample those with maximum IG. Additionally, we identify the presence of template bias, which can lead to unfair evaluations of IG during the sampling process. To mitigate this bias, we introduce Calibration Before Sampling strategy. The experimental results illustrate that our proposed method can yield an average relative improvement of 14.3% across six classification tasks using three LLMs.
- Open Access
Zero-Shot Automatic Pronunciation Assessment
Automatic Pronunciation Assessment (APA) is vital for computer-assisted language learning. Prior methods rely on annotated speech-text data to train Automatic Speech Recognition (ASR) models or speech-score data to train regression models. In this work, we propose a novel zero-shot APA method based on the pre-trained acoustic model, HuBERT. Our method involves encoding speech input and corrupting them via a masking module. We then employ the Transformer encoder and apply k-means clustering to obtain token sequences. Finally, a scoring module is designed to measure the number of wrongly recovered tokens. Experimental results on speechocean762 demonstrate that the proposed method achieves comparable performance to supervised regression baselines and outperforms non-regression baselines in terms of Pearson Correlation Coefficient (PCC). Additionally, we analyze how masking strategies affect the performance of APA.
Open AccessZero-Shot Automatic Pronunciation Assessment
Automatic Pronunciation Assessment (APA) is vital for computer-assisted language learning. Prior methods rely on annotated speech-text data to train Automatic Speech Recognition (ASR) models or speech-score data to train regression models. In this work, we propose a novel zero-shot APA method based on the pre-trained acoustic model, HuBERT. Our method involves encoding speech input and corrupting them via a masking module. We then employ the Transformer encoder and apply k-means clustering to obtain token sequences. Finally, a scoring module is designed to measure the number of wrongly recovered tokens. Experimental results on speechocean762 demonstrate that the proposed method achieves comparable performance to supervised regression baselines and outperforms non-regression baselines in terms of Pearson Correlation Coefficient (PCC). Additionally, we analyze how masking strategies affect the performance of APA.
- Open Access
- 1 January 2023
- Published by Association for Computational Linguistics (ACL)
- p. 15825-15838
Towards Informative Few-Shot Prompt with Maximum Information Gain for In-Context Learning
Hongfu Liu, Ye Wang. Findings of the Association for Computational Linguistics: EMNLP 2023. 2023.
- 1 January 2023
- Published by Association for Computational Linguistics (ACL)
- p. 15825-15838
Open AccessTowards Informative Few-Shot Prompt with Maximum Information Gain for In-Context Learning
Hongfu Liu, Ye Wang. Findings of the Association for Computational Linguistics: EMNLP 2023. 2023.