5 papers
Inference-Time Target Speaker Unlearning in LLM-Based Automatic Speech Recognition
Bo Su, Yueru Yan, Thai Le
We introduce target-speaker unlearning ASR (TSU-ASR) task in a fully end-to-end framework for multi-speaker ASR and diarization. Given a multi-speaker utterance and a set of opt-ou…
PreUnlearn: Auditing Collateral Knowledge Damage Before Large Language Model Unlearning
Bo Su, Ankit Shah, Thai Le
Machine unlearning for large language models (LLMs) aims to remove specified knowledge while preserving the rest of the model's capabilities. However, the boundary between knowledg…
ShareChat: A Dataset of Chatbot Conversations in the Wild
Yueru Yan, Tuc Nguyen, Bo Su +2
By evaluating Large Language Models (LLMs) through uniform, text-only interfaces, current academic benchmarks obscure how the unique designs and affordances of distinct commercial…
Instructional Prompt Optimization for Few-Shot LLM-Based Recommendations on Cold-Start Users
Haowei Yang, Yushang Zhao, Sitao Min +3
The cold-start user issue further compromises the effectiveness of recommender systems in limiting access to the historical behavioral information. It is an effective pipeline to o…
Context-Dependent Semantic Parsing for Temporal Relation Extraction
Bo-Ying Su, Shang-Ling Hsu, Kuan-Yin Lai +1
Extracting temporal relations among events from unstructured text has extensive applications, such as temporal reasoning and question answering. While it is difficult, recent devel…