Search Results for author: Hsuan Su

Found 13 papers, 0 papers with code

CueBot: Cue-Controlled Response Generation for Assistive Interaction Usages

no code implementations SLPAT (ACL) 2022 Shachi H. Kumar, Hsuan Su, Ramesh Manuvinakurike, Max Pinaroc, Sai Prasad, Saurav Sahay, Lama Nachman

Conversational assistants are ubiquitous among the general population, however, these systems have not had an impact on people with disabilities, or speech and language disorders, for whom basic day-to-day communication and social interaction is a huge struggle.

Language Modelling Response Generation

Jailbreaking with Universal Multi-Prompts

no code implementations3 Feb 2025 Yu-Ling Hsu, Hsuan Su, Shang-Tse Chen

Large language models (LLMs) have seen rapid development in recent years, revolutionizing various applications and significantly enhancing convenience and productivity.

Safeguard Fine-Tuned LLMs Through Pre- and Post-Tuning Model Merging

no code implementations27 Dec 2024 Hua Farn, Hsuan Su, Shachi H Kumar, Saurav Sahay, Shang-Tse Chen, Hung-Yi Lee

In this paper, we address the question: How can we improve downstream task performance while preserving safety in LLMs without relying on additional safety data?

Decoding Biases: Automated Methods and LLM Judges for Gender Bias Detection in Language Models

no code implementations7 Aug 2024 Shachi H Kumar, Saurav Sahay, Sahisnu Mazumder, Eda Okur, Ramesh Manuvinakurike, Nicole Beckage, Hsuan Su, Hung-Yi Lee, Lama Nachman

However, even with supervised training and human alignment, these LLMs are susceptible to adversarial attacks where malicious users can prompt the model to generate undesirable text.

Bias Detection Gender Bias Detection +1

Task Arithmetic can Mitigate Synthetic-to-Real Gap in Automatic Speech Recognition

no code implementations5 Jun 2024 Hsuan Su, Hua Farn, Fan-Yun Sun, Shang-Tse Chen, Hung-Yi Lee

Synthetic data is widely used in speech recognition due to the availability of text-to-speech models, which facilitate adapting models to previously unseen text domains.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +4

Learning from Red Teaming: Gender Bias Provocation and Mitigation in Large Language Models

no code implementations17 Oct 2023 Hsuan Su, Cheng-Chu Cheng, Hua Farn, Shachi H Kumar, Saurav Sahay, Shang-Tse Chen, Hung-Yi Lee

Recently, researchers have made considerable improvements in dialogue systems with the progress of large language models (LLMs) such as ChatGPT and GPT-4.

In-Context Learning Red Teaming

Controllable Response Generation for Assistive Use-cases

no code implementations4 Dec 2021 Shachi H Kumar, Hsuan Su, Ramesh Manuvinakurike, Saurav Sahay, Lama Nachman

We build models that can suggest relevant cues in the dialog response context which is used to control response generation and can speed up communication.

Language Modelling Response Generation

Cannot find the paper you are looking for? You can Submit a new open access paper.