no code implementations • 27 Mar 2024 • Yan Fang, Jingtao Zhan, Qingyao Ai, Jiaxin Mao, Weihang Su, Jia Chen, Yiqun Liu
In this study, we investigate whether the performance of dense retrieval models follows the scaling law as other neural models.
1 code implementation • 15 Mar 2024 • Weihang Su, Yichen Tang, Qingyao Ai, Zhijing Wu, Yiqun Liu
Our framework is specifically designed to make decisions on when and what to retrieve based on the LLM's real-time information needs during the text generation process.
no code implementations • 11 Mar 2024 • Weihang Su, Changyue Wang, Qingyao Ai, Yiran Hu, Zhijing Wu, Yujia Zhou, Yiqun Liu
Hallucinations in large language models (LLMs) refer to the phenomenon of LLMs producing responses that are coherent yet factually inaccurate.
1 code implementation • 17 Dec 2023 • Weihang Su, Qingyao Ai, Xiangsheng Li, Jia Chen, Yiqun Liu, Xiaolong Wu, Shengluan Hou
With the development of deep learning and natural language processing techniques, pre-trained language models have been widely used to solve information retrieval (IR) problems.
1 code implementation • 9 Dec 2023 • Ziyi Ye, Xiaohui Xie, Qingyao Ai, Yiqun Liu, Zhihong Wang, Weihang Su, Min Zhang
To explore the effectiveness of brain signals in the context of RF, we propose a novel RF framework that combines BCI-based relevance feedback with pseudo-relevance signals and implicit signals to improve the performance of document re-ranking.
1 code implementation • 1 Nov 2023 • Weihang Su, Qingyao Ai, Yueyue Wu, Yixiao Ma, Haitao Li, Yiqun Liu, Zhijing Wu, Min Zhang
Legal case retrieval aims to help legal workers find relevant cases related to their cases at hand, which is important for the guarantee of fairness and justice in legal judgments.
no code implementations • 1 Jul 2023 • Weihang Su, Xiangsheng Li, Yiqun Liu, Min Zhang, Shaoping Ma
Our team(THUIR2) participated in both FOSS and POSS subtasks of the NTCIR-161 Session Search (SS) Task.
2 code implementations • 11 May 2023 • Haitao Li, Changyue Wang, Weihang Su, Yueyue Wu, Qingyao Ai, Yiqun Liu
This paper describes the approach of the THUIR team at the COLIEE 2023 Legal Case Entailment task.
2 code implementations • 11 May 2023 • Haitao Li, Weihang Su, Changyue Wang, Yueyue Wu, Qingyao Ai, Yiqun Liu
Legal case retrieval techniques play an essential role in modern intelligent legal systems.
no code implementations • 9 May 2023 • Yixiao Ma, Yueyue Wu, Weihang Su, Qingyao Ai, Yiqun Liu
In the data sampling phase, we enhance the quality of the training data by utilizing fine-grained law article information to guide the selection of positive and negative examples.
1 code implementation • 25 Apr 2023 • Jia Chen, Haitao Li, Weihang Su, Qingyao Ai, Yiqun Liu
This paper introduces the approaches we have used to participate in the WSDM Cup 2023 Task 1: Unbiased Learning to Rank.
no code implementations • 28 Feb 2023 • Haitao Li, Jia Chen, Weihang Su, Qingyao Ai, Yiqun Liu
This paper describes the approach of the THUIR team at the WSDM Cup 2023 Pre-training for Web Search task.
no code implementations • 14 Oct 2021 • Xuesong Chen, Ziyi Ye, Xiaohui Xie, Yiqun Liu, Weihang Su, Shuqi Zhu, Min Zhang, Shaoping Ma
While search technologies have evolved to be robust and ubiquitous, the fundamental interaction paradigm has remained relatively stable for decades.