34 citations · 92 across the 30 of their papers we have counts for
10 papers · 1 filter
UniGist: Towards General and Hardware-aligned Sequence-level Long Context Compression
Chenlong Deng, Zhisong Zhang, Kelong Mao +6
Large language models are increasingly capable of handling long-context inputs, but the memory overhead of key-value (KV) cache remains a major bottleneck for general-purpose deplo…
UniConv: Unifying Retrieval and Response Generation for Large Language Models in Conversations
Fengran Mo, Yifan Gao, Chuan Meng +9
The rapid advancement of conversational search systems revolutionizes how information is accessed by enabling the multi-turn interaction between the user and the system. Existing c…
A Silver Bullet or a Compromise for Full Attention? A Comprehensive Study of Gist Token-based Context Compression
Chenlong Deng, Zhisong Zhang, Kelong Mao +4
In this work, we provide a thorough investigation of gist-based context compression methods to improve long-context processing in large language models. We focus on two key questio…
A Survey of Conversational Search
Fengran Mo, Kelong Mao, Ziliang Zhao +7
As a cornerstone of modern information access, search engines have become indispensable in everyday life. With the rapid advancements in AI and natural language processing (NLP) te…
MemoRAG: Boosting Long Context Processing with Global Memory-Enhanced Retrieval Augmentation
Hongjin Qian, Zheng Liu, Peitian Zhang +4
Processing long contexts presents a significant challenge for large language models (LLMs). While recent advancements allow LLMs to handle much longer contexts than before (e.g., 3…
Enabling Discriminative Reasoning in LLMs for Legal Judgment Prediction
Chenlong Deng, Kelong Mao, Yuyao Zhang +1
Legal judgment prediction is essential for enhancing judicial efficiency. In this work, we identify that existing large language models (LLMs) underperform in this domain due to ch…
YuLan: An Open-source Large Language Model
Yutao Zhu, Kun Zhou, Kelong Mao +35
Large language models (LLMs) have become the foundation of many applications, leveraging their extensive capabilities in processing and understanding natural language. While many o…
Are Long-LLMs A Necessity For Long-Context Tasks?
Hongjin Qian, Zheng Liu, Peitian Zhang +4
The learning and deployment of long-LLMs remains a challenging problem despite recent progresses. In this work, we argue that the long-LLMs are not a necessity to solve long-contex…
Grounding Language Model with Chunking-Free In-Context Retrieval
Hongjin Qian, Zheng Liu, Kelong Mao +2
This paper presents a novel Chunking-Free In-Context (CFIC) retrieval approach, specifically tailored for Retrieval-Augmented Generation (RAG) systems. Traditional RAG systems ofte…
Generalizing Conversational Dense Retrieval via LLM-Cognition Data Augmentation
Haonan Chen, Zhicheng Dou, Kelong Mao +2
Conversational search utilizes muli-turn natural language contexts to retrieve relevant passages. Existing conversational dense retrieval models mostly view a conversation as a fix…