34 citations · 92 across the 30 of their papers we have counts for
16 papers · 1 filter
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…
CORAL: Benchmarking Multi-turn Conversational Retrieval-Augmentation Generation
Yiruo Cheng, Kelong Mao, Ziliang Zhao +6
Retrieval-Augmented Generation (RAG) has become a powerful paradigm for enhancing large language models (LLMs) through external knowledge retrieval. Despite its widespread attentio…
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…
Aligning Query Representation with Rewritten Query and Relevance Judgments in Conversational Search
Fengran Mo, Chen Qu, Kelong Mao +4
Conversational search supports multi-turn user-system interactions to solve complex information needs. Different from the traditional single-turn ad-hoc search, conversational sear…
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…
Learning Interpretable Legal Case Retrieval via Knowledge-Guided Case Reformulation
Chenlong Deng, Kelong Mao, Zhicheng Dou
Legal case retrieval for sourcing similar cases is critical in upholding judicial fairness. Different from general web search, legal case retrieval involves processing lengthy, com…
CHIQ: Contextual History Enhancement for Improving Query Rewriting in Conversational Search
Fengran Mo, Abbas Ghaddar, Kelong Mao +4
In this paper, we study how open-source large language models (LLMs) can be effectively deployed for improving query rewriting in conversational search, especially for ambiguous qu…
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…
ChatRetriever: Adapting Large Language Models for Generalized and Robust Conversational Dense Retrieval
Kelong Mao, Chenlong Deng, Haonan Chen +4
Conversational search requires accurate interpretation of user intent from complex multi-turn contexts. This paper presents ChatRetriever, which inherits the strong generalization…
ConvSDG: Session Data Generation for Conversational Search
Fengran Mo, Bole Yi, Kelong Mao +3
Conversational search provides a more convenient interface for users to search by allowing multi-turn interaction with the search engine. However, the effectiveness of the conversa…
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…
Interpreting Conversational Dense Retrieval by Rewriting-Enhanced Inversion of Session Embedding
Yiruo Cheng, Kelong Mao, Zhicheng Dou
Conversational dense retrieval has shown to be effective in conversational search. However, a major limitation of conversational dense retrieval is their lack of interpretability,…
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…
History-Aware Conversational Dense Retrieval
Fengran Mo, Chen Qu, Kelong Mao +4
Conversational search facilitates complex information retrieval by enabling multi-turn interactions between users and the system. Supporting such interactions requires a comprehens…