Papers by Wailing Ng
Dial-In LLM: Human-Aligned LLM-in-the-loop Intent Clustering for Customer Service Dialogues (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing intent clustering methods rely on embedding distance metrics and neglect of underlying semantic structures. |
| Approach: | They propose an LLM-in-the-loop framework that integrates language understanding capabilities into conventional clustering algorithms. |
| Outcome: | The proposed framework outperforms baselines in Chinese and improves quality, cost efficiency and downstream applications. |
QualBench: Benchmarking Chinese LLMs with Localized Professional Qualifications for Vertical Domain Evaluation (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing benchmarks often lack domain coverage and provide limited insights into the working context of Chinese LLMs. |
| Approach: | They propose a multi-domain Chinese QA benchmark dedicated to localized assessment of Chinese LLMs. |
| Outcome: | The Qwen2.5 model outperforms the more advanced GPT-4o model in the Chinese market . the dataset includes over 17,000 questions across six vertical domains . |