most citedKnowledge-Driven CoT: Exploring Faithful Reasoning in LLMs for Knowledge-intensive Question Answering

11 citations · 24 across the 12 of their papers we have counts for

collaborators

12 papers

cs.IR2024

Beyond the Sequence: Statistics-Driven Pre-training for Stabilizing Sequential Recommendation Model

Sirui Wang, Peiguang Li, Yunsen Xian +1

The sequential recommendation task aims to predict the item that user is interested in according to his/her historical action sequence. However, inevitable random action, i.e. user…

cs.CL20245 cited

Beyond the Known: Investigating LLMs Performance on Out-of-Domain Intent Detection

Pei Wang, Keqing He, Yejie Wang +6

Out-of-domain (OOD) intent detection aims to examine whether the user's query falls outside the predefined domain of the system, which is crucial for the proper functioning of task…

cs.CL2024

Exploiting Duality in Open Information Extraction with Predicate Prompt

Zhen Chen, Jingping Liu, Deqing Yang +5

Open information extraction (OpenIE) aims to extract the schema-free triplets in the form of (\emph{subject}, \emph{predicate}, \emph{object}) from a given sentence. Compared with…

cs.CL2023

Large Language Models Meet Open-World Intent Discovery and Recognition: An Evaluation of ChatGPT

Xiaoshuai Song, Keqing He, Pei Wang +6

The tasks of out-of-domain (OOD) intent discovery and generalized intent discovery (GID) aim to extend a closed intent classifier to open-world intent sets, which is crucial to tas…

cs.CV20233 cited

Towards Visual Taxonomy Expansion

Tinghui Zhu, Jingping Liu, Jiaqing Liang +5

Taxonomy expansion task is essential in organizing the ever-increasing volume of new concepts into existing taxonomies. Most existing methods focus exclusively on using textual sem…

cs.CV20231 cited

Exchanging-based Multimodal Fusion with Transformer

Renyu Zhu, Chengcheng Han, Yong Qian +5

We study the problem of multimodal fusion in this paper. Recent exchanging-based methods have been proposed for vision-vision fusion, which aim to exchange embeddings learned from…