Chenlong Deng is a third-year PhD student at the Gaoling School of Artificial Intelligence, Renmin University of China, under the supervision of Prof. Zhicheng Dou. His research primarily focuses on large language models and information retrieval. Currently, his work is centered on developing sparsity-based efficient long-context large language models.
Education
- Renmin University of China
- 2022 - Present
- Ph.D. in Artificial Intelligence
- Renmin University of China
- 2018 - 2022
- B.Eng. in Computer Science and Technology
Internship
- Tencent AI Lab
- 2024.04 - Present
- Research on Efficient Long Context LLMs
- Shenzhen, China
Publications
A Silver Bullet or a Compromise for Full Attention? A Comprehensive Study of Gist Token-based Context Compression
Preprint
Attention Entropy is a Key Factor: An Analysis of Parallel Context Encoding with Full-attention-based Pre-trained Language Models
Preprint
Learning Interpretable Legal Case Retrieval via Knowledge-Guided Case Reformulation
EMNLP 2024 (Main)
ChatRetriever: Adapting Large Language Models for Generalized and Robust Conversational Dense Retrieval
EMNLP 2024 (Main)
Enabling discriminative reasoning in LLMs for legal judgment prediction
EMNLP 2024 (Findings)
RAG-Studio: Towards In-Domain Adaptation of Retrieval Augmented Generation Through Self-Alignment
EMNLP 2024 (Findings)
An Element is Worth a Thousand Words: Enhancing Legal Case Retrieval by Incorporating Legal Elements
ACL 2024 (Findings)
