Papers by Hsuan Su
Task Arithmetic can Mitigate Synthetic-to-Real Gap in Automatic Speech Recognition (2024.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for speech recognition suffer from the synthetic-to-real gap . existing methods suffer from this distributional shift due to acoustic mismatches . |
| Approach: | They propose to use task arithmetic to fine-tune an ASR model on synthetic data to mitigate the synthetic-to-real gap. |
| Outcome: | The proposed method shows an improvement of 10.03% over baselines on the SLURP dataset. |
Put Chatbot into Its Interlocutor’s Shoes: New Framework to Learn Chatbot Responding with Intention (2021.naacl-main)
Copied to clipboard
| Challenge: | Currently, most work on improving the fluency and coherence of chatbots is focused on making them more human-like. |
| Approach: | They propose a framework to train chatbots to possess human-like intentions by making them learn from interactive conversation. |
| Outcome: | The proposed framework includes a guiding chatbot and an interlocutor model that plays the role of humans. |
Jailbreaking with Universal Multi-Prompts (2025.findings-naacl)
Copied to clipboard
| Challenge: | Large language models (LLMs) have seen rapid development in recent years, but ethical concerns and new types of attacks have emerged. |
| Approach: | They propose a prompt-based method to jailbreak large language models using universal multi-prompts and an approach for defense that outperforms existing techniques. |
| Outcome: | The proposed method outperforms existing techniques for jailbreaking LLMs using universal multi-prompts. |
Safeguard Fine-Tuned LLMs Through Pre- and Post-Tuning Model Merging (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Fine-tuning large language models for downstream tasks often leads to catastrophic forgetting, notably degrading the safety of original alignments. |
| Approach: | They propose to merge the weights of pre- and post-fine-tuned models to improve safety while enhancing performance. |
| Outcome: | Experiments across different downstream tasks and models validate the method’s practicality and effectiveness. |
Cue-bot: A Conversational Agent for Assistive Technology (2022.acl-demo)
Copied to clipboard
Shachi H Kumar, Hsuan Su, Ramesh Manuvinakurike, Maximilian C. Pinaroc, Sai Prasad, Saurav Sahay, Lama Nachman
| Challenge: | Large-scale pre-training has achieved significant performance gains across many tasks within NLP, including intent prediction and dialogue state tracking. |
| Approach: | They propose to use eye-tracking, mouse controls and an intelligent agent Cue-bot to represent the user in a conversation. |
| Outcome: | The proposed system can be used by people with different levels of disabilities to interact with the world, supported by eye-tracking, mouse controls and an intelligent agent Cue-bot. |
Pseudo2Real: Task Arithmetic for Pseudo-Label Correction in Automatic Speech Recognition (2026.findings-acl)
Copied to clipboard
| Challenge: | ASR models can be used to correct accent-specific errors without ground truth . pseudo-labels inherit the teacher model's systematic biases, authors say . |
| Approach: | They propose a parameter-space correction technique that captures pseudo-label biases . they propose achieving up to 35% relative WER reduction on a pseudo-labeled target model . |
| Outcome: | The proposed model achieves 35% relative WER reduction on ten African accents with the Whisper tiny model. |