8 citations · 21 across the 18 of their papers we have counts for
8 papers · 1 filter
MAC-SQL: A Multi-Agent Collaborative Framework for Text-to-SQL
Bing Wang, Changyu Ren, Jian Yang +8
Recent LLM-based Text-to-SQL methods usually suffer from significant performance degradation on "huge" databases and complex user questions that require multi-step reasoning. Moreo…
Multi-Stage Pre-training Enhanced by ChatGPT for Multi-Scenario Multi-Domain Dialogue Summarization
Weixiao Zhou, Gengyao Li, Xianfu Cheng +4
Dialogue summarization involves a wide range of scenarios and domains. However, existing methods generally only apply to specific scenarios or domains. In this study, we propose a…
KnowPrefix-Tuning: A Two-Stage Prefix-Tuning Framework for Knowledge-Grounded Dialogue Generation
Jiaqi Bai, Zhao Yan, Jian Yang +3
Existing knowledge-grounded conversation systems generate responses typically in a retrieve-then-generate manner. They require a large knowledge base and a strong knowledge retriev…
GripRank: Bridging the Gap between Retrieval and Generation via the Generative Knowledge Improved Passage Ranking
Jiaqi Bai, Hongcheng Guo, Jiaheng Liu +4
Retrieval-enhanced text generation has shown remarkable progress on knowledge-intensive language tasks, such as open-domain question answering and knowledge-enhanced dialogue gener…
Retrieval-Augmented Classification with Decoupled Representation
Xinnian Liang, Shuangzhi Wu, Hui Huang +3
Retrieval augmented methods have shown promising results in various classification tasks. However, existing methods focus on retrieving extra context to enrich the input, which is…
SCM: Enhancing Large Language Model with Self-Controlled Memory Framework
Bing Wang, Xinnian Liang, Jian Yang +6
Large Language Models (LLMs) are constrained by their inability to process lengthy inputs, resulting in the loss of critical historical information. To address this limitation, in…
Character, Word, or Both? Revisiting the Segmentation Granularity for Chinese Pre-trained Language Models
Xinnian Liang, Zefan Zhou, Hui Huang +5
Pretrained language models (PLMs) have shown marvelous improvements across various NLP tasks. Most Chinese PLMs simply treat an input text as a sequence of characters, and complete…
Enhancing Dialogue Summarization with Topic-Aware Global- and Local- Level Centrality
Xinnian Liang, Shuangzhi Wu, Chenhao Cui +3
Dialogue summarization aims to condense a given dialogue into a simple and focused summary text. Typically, both the roles' viewpoints and conversational topics change in the dialo…