4 papers
Exploring Weaknesses in Function Call Models via Reinforcement Learning: An Adversarial Data Augmentation Approach
Weiran Guo, Bing Bo, Shaoxiang Wu +1
Function call capabilities have become crucial for Large Language Models (LLMs), enabling them to interact more effectively with external tools and APIs. Existing methods for impro…
From Events to Trending: A Multi-Stage Hotspots Detection Method Based on Generative Query Indexing
Kaichun Wang, Yanguang Chen, Ting Zhang +7
LLM-based conversational systems have become a popular gateway for information access, yet most existing chatbots struggle to handle news-related trending queries effectively. To i…
ODIA: Oriented Distillation for Inline Acceleration of LLM-based Function Calling
Hanlong Zhang, Jingsheng Yang, Hao Li +2
Function Calling is a crucial technique that enables Large Language Models (LLMs) to interact with external systems through APIs. However, the high latency associated with LLM-base…
The Volcspeech system for the ICASSP 2022 multi-channel multi-party meeting transcription challenge
Chen Shen, Yi Liu, Wenzhi Fan +6
This paper describes our submission to ICASSP 2022 Multi-channel Multi-party Meeting Transcription (M2MeT) Challenge. For Track 1, we propose several approaches to empower the clus…