1 code implementation • 28 May 2024 • Changle Qu, Sunhao Dai, Xiaochi Wei, Hengyi Cai, Shuaiqiang Wang, Dawei Yin, Jun Xu, Ji-Rong Wen
In this survey, we focus on reviewing existing literature from the two primary aspects (1) why tool learning is beneficial and (2) how tool learning is implemented, enabling a comprehensive understanding of tool learning with LLMs.
no code implementations • 25 May 2024 • Changle Qu, Sunhao Dai, Xiaochi Wei, Hengyi Cai, Shuaiqiang Wang, Dawei Yin, Jun Xu, Ji-Rong Wen
In this paper, we propose a novel modelagnostic COllaborative Learning-based Tool Retrieval approach, COLT, which captures not only the semantic similarities between user queries and tool descriptions but also takes into account the collaborative information of tools.
no code implementations • 23 May 2024 • Pengyue Jia, Yiding Liu, Xiaopeng Li, Xiangyu Zhao, Yuhao Wang, Yantong Du, Xiao Han, Xuetao Wei, Shuaiqiang Wang, Dawei Yin
Worldwide geolocalization aims to locate the precise location at the coordinate level of photos taken anywhere on the Earth.
no code implementations • 8 Apr 2024 • Xuanfan Ni, Hengyi Cai, Xiaochi Wei, Shuaiqiang Wang, Dawei Yin, Piji Li
However, prior benchmarks create datasets that ostensibly cater to long-text comprehension by expanding the input of traditional tasks, which falls short to exhibit the unique characteristics of long-text understanding, including long dependency tasks and longer text length compatible with modern LLMs' context window size.
no code implementations • 21 Mar 2024 • Yukun Zhao, Lingyong Yan, Weiwei Sun, Guoliang Xing, Shuaiqiang Wang, Chong Meng, Zhicong Cheng, Zhaochun Ren, Dawei Yin
The training process is accomplished by self-rewards inferred from the trained model at the first stage without referring to external human preference resources.
1 code implementation • 23 Feb 2024 • Shenglai Zeng, Jiankun Zhang, Pengfei He, Yue Xing, Yiding Liu, Han Xu, Jie Ren, Shuaiqiang Wang, Dawei Yin, Yi Chang, Jiliang Tang
In this work, we conduct extensive empirical studies with novel attack methods, which demonstrate the vulnerability of RAG systems on leaking the private retrieval database.
1 code implementation • 17 Feb 2024 • Yougang Lyu, Lingyong Yan, Shuaiqiang Wang, Haibo Shi, Dawei Yin, Pengjie Ren, Zhumin Chen, Maarten de Rijke, Zhaochun Ren
To address these problems, we propose a knowledge-aware fine-tuning (KnowTuning) method to improve fine-grained and coarse-grained knowledge awareness of LLMs.
no code implementations • 14 Dec 2023 • Hao Sun, Hengyi Cai, Bo wang, Yingyan Hou, Xiaochi Wei, Shuaiqiang Wang, Yan Zhang, Dawei Yin
Despite the remarkable ability of large language models (LLMs) in language comprehension and generation, they often suffer from producing factually incorrect information, also known as hallucination.
no code implementations • 14 Nov 2023 • Yige Zhao, Jianxiang Yu, Yao Cheng, Chengcheng Yu, Yiding Liu, Xiang Li, Shuaiqiang Wang
Instead of directly reconstructing raw features for attributed nodes, SHAVA generates the initial low-dimensional representation matrix for all the nodes, based on which raw features of attributed nodes are further reconstructed to leverage accurate attributes.
1 code implementation • 6 Nov 2023 • Zeyuan Zhao, Qingqing Ge, Anfeng Cheng, Yiding Liu, Xiang Li, Shuaiqiang Wang
However, different types of nodes in heterogeneous graphs have diverse features, it is also necessary to capture interactions among node features, namely the high-order information from feature-level aspect.
1 code implementation • 2 Nov 2023 • Weiwei Sun, Zheng Chen, Xinyu Ma, Lingyong Yan, Shuaiqiang Wang, Pengjie Ren, Zhumin Chen, Dawei Yin, Zhaochun Ren
Furthermore, our approach surpasses the performance of existing supervised methods like monoT5 and is on par with the state-of-the-art zero-shot methods.
1 code implementation • 29 Oct 2023 • Pengyue Jia, Yiding Liu, Xiangyu Zhao, Xiaopeng Li, Changying Hao, Shuaiqiang Wang, Dawei Yin
While existing methods expand queries using retrieved or generated contextual documents, each approach has notable limitations.
no code implementations • 27 Oct 2023 • Yukun Zhao, Lingyong Yan, Weiwei Sun, Guoliang Xing, Chong Meng, Shuaiqiang Wang, Zhicong Cheng, Zhaochun Ren, Dawei Yin
In this paper, we propose a novel self-detection method to detect which questions that a LLM does not know that are prone to generate nonfactual results.
1 code implementation • 26 Oct 2023 • Qingqing Ge, Zeyuan Zhao, Yiding Liu, Anfeng Cheng, Xiang Li, Shuaiqiang Wang, Dawei Yin
In particular, PSP 1) employs a dual-view contrastive learning to align the latent semantic spaces of node attributes and graph structure, and 2) incorporates structure information in prompted graph to construct more accurate prototype vectors and elicit more pre-trained knowledge in prompt tuning.
no code implementations • 25 Oct 2023 • Yukun Zhao, Lingyong Yan, Weiwei Sun, Chong Meng, Shuaiqiang Wang, Zhicong Cheng, Zhaochun Ren, Dawei Yin
Dialogue assessment plays a critical role in the development of open-domain dialogue systems.
no code implementations • 10 Oct 2023 • Shenglai Zeng, Yaxin Li, Jie Ren, Yiding Liu, Han Xu, Pengfei He, Yue Xing, Shuaiqiang Wang, Jiliang Tang, Dawei Yin
In this work, we conduct the first comprehensive analysis to explore language models' (LMs) memorization during fine-tuning across tasks.
no code implementations • 29 Sep 2023 • Qian Dong, Yiding Liu, Qingyao Ai, Zhijing Wu, Haitao Li, Yiqun Liu, Shuaiqiang Wang, Dawei Yin, Shaoping Ma
Large language models (LLMs) have demonstrated remarkable capabilities across various research domains, including the field of Information Retrieval (IR).
no code implementations • 2 Sep 2023 • Haiyan Zhao, Hanjie Chen, Fan Yang, Ninghao Liu, Huiqi Deng, Hengyi Cai, Shuaiqiang Wang, Dawei Yin, Mengnan Du
For each paradigm, we summarize the goals and dominant approaches for generating local explanations of individual predictions and global explanations of overall model knowledge.
2 code implementations • 7 Jul 2023 • Zhikai Chen, Haitao Mao, Hang Li, Wei Jin, Hongzhi Wen, Xiaochi Wei, Shuaiqiang Wang, Dawei Yin, Wenqi Fan, Hui Liu, Jiliang Tang
The most popular pipeline for learning on graphs with textual node attributes primarily relies on Graph Neural Networks (GNNs), and utilizes shallow text embedding as initial node representations, which has limitations in general knowledge and profound semantic understanding.
1 code implementation • 4 Jun 2023 • Qian Dong, Yiding Liu, Qingyao Ai, Haitao Li, Shuaiqiang Wang, Yiqun Liu, Dawei Yin, Shaoping Ma
Moreover, the proposed implicit interaction is compatible with special pre-training and knowledge distillation for passage retrieval, which brings a new state-of-the-art performance.
no code implementations • 2 Jun 2023 • Canjia Li, Xiaoyang Wang, Dongdong Li, Yiding Liu, Yu Lu, Shuaiqiang Wang, Zhicong Cheng, Simiu Gu, Dawei Yin
In this work, we focus on ranking user satisfaction rather than relevance in web search, and propose a PLM-based framework, namely SAT-Ranker, which comprehensively models different dimensions of user satisfaction in a unified manner.
no code implementations • 24 May 2023 • Yubao Tang, Ruqing Zhang, Jiafeng Guo, Jiangui Chen, Zuowei Zhu, Shuaiqiang Wang, Dawei Yin, Xueqi Cheng
Specifically, we assign each document an Elaborative Description based on the query generation technique, which is more meaningful than a string of integers in the original DSI; and (2) For the associations between a document and its identifier, we take inspiration from Rehearsal Strategies in human learning.
no code implementations • 16 May 2023 • Bo wang, Heyan Huang, Xiaochi Wei, Ge Shi, Xiao Liu, Chong Feng, Tong Zhou, Shuaiqiang Wang, Dawei Yin
Event extraction aims to recognize pre-defined event triggers and arguments from texts, which suffer from the lack of high-quality annotations.
1 code implementation • 19 Apr 2023 • Weiwei Sun, Lingyong Yan, Xinyu Ma, Shuaiqiang Wang, Pengjie Ren, Zhumin Chen, Dawei Yin, Zhaochun Ren
In this paper, we first investigate generative LLMs such as ChatGPT and GPT-4 for relevance ranking in IR.
no code implementations • 28 Jan 2023 • Anfeng Cheng, Yiding Liu, Weibin Li, Qian Dong, Shuaiqiang Wang, Zhengjie Huang, Shikun Feng, Zhicong Cheng, Dawei Yin
To assess webpage quality from complex DOM tree data, we propose a graph neural network (GNN) based method that extracts rich layout-aware information that implies webpage quality in an end-to-end manner.
no code implementations • 16 Aug 2022 • Lixin Zou, Changying Hao, Hengyi Cai, Suqi Cheng, Shuaiqiang Wang, Wenwen Ye, Zhicong Cheng, Simiu Gu, Dawei Yin
We further instantiate the proposed unbiased relevance estimation framework in Baidu search, with comprehensive practical solutions designed regarding the data pipeline for click behavior tracking and online relevance estimation with an approximated deep neural network.
1 code implementation • 7 Jul 2022 • Lixin Zou, Haitao Mao, Xiaokai Chu, Jiliang Tang, Wenwen Ye, Shuaiqiang Wang, Dawei Yin
The unbiased learning to rank (ULTR) problem has been greatly advanced by recent deep learning techniques and well-designed debias algorithms.
1 code implementation • 25 Jun 2022 • Shichao Zhu, Chuan Zhou, Anfeng Cheng, Shirui Pan, Shuaiqiang Wang, Dawei Yin, Bin Wang
Self-supervised learning (especially contrastive learning) methods on heterogeneous graphs can effectively get rid of the dependence on supervisory data.
no code implementations • 20 May 2022 • Qingzhong Wang, Haifang Li, Haoyi Xiong, Wen Wang, Jiang Bian, Yu Lu, Shuaiqiang Wang, Zhicong Cheng, Dejing Dou, Dawei Yin
To handle the diverse query requests from users at web-scale, Baidu has done tremendous efforts in understanding users' queries, retrieve relevant contents from a pool of trillions of webpages, and rank the most relevant webpages on the top of results.
no code implementations • 18 May 2022 • Yuxiang Lu, Yiding Liu, Jiaxiang Liu, Yunsheng Shi, Zhengjie Huang, Shikun Feng Yu Sun, Hao Tian, Hua Wu, Shuaiqiang Wang, Dawei Yin, Haifeng Wang
Our method 1) introduces a self on-the-fly distillation method that can effectively distill late interaction (i. e., ColBERT) to vanilla dual-encoder, and 2) incorporates a cascade distillation process to further improve the performance with a cross-encoder teacher.
no code implementations • 25 Apr 2022 • Qian Dong, Yiding Liu, Suqi Cheng, Shuaiqiang Wang, Zhicong Cheng, Shuzi Niu, Dawei Yin
To leverage a reliable knowledge, we propose a novel knowledge graph distillation method and obtain a knowledge meta graph as the bridge between query and passage.
no code implementations • 3 Apr 2022 • Juanhui Li, Yao Ma, Wei Zeng, Suqi Cheng, Jiliang Tang, Shuaiqiang Wang, Dawei Yin
In other words, GE-BERT can capture both the semantic information and the users' search behavioral information of queries.
no code implementations • 7 Jun 2021 • Yiding Liu, Guan Huang, Jiaxiang Liu, Weixue Lu, Suqi Cheng, Yukun Li, Daiting Shi, Shuaiqiang Wang, Zhicong Cheng, Dawei Yin
More importantly, we present a practical system workflow for deploying the model in web-scale retrieval.
1 code implementation • 28 May 2021 • Siyuan Guo, Lixin Zou, Yiding Liu, Wenwen Ye, Suqi Cheng, Shuaiqiang Wang, Hechang Chen, Dawei Yin, Yi Chang
Based on it, a more robust doubly robust (MRDR) estimator has been proposed to further reduce its variance while retaining its double robustness.
no code implementations • 24 May 2021 • Lixin Zou, Shengqiang Zhang, Hengyi Cai, Dehong Ma, Suqi Cheng, Daiting Shi, Zhifan Zhu, Weiyue Su, Shuaiqiang Wang, Zhicong Cheng, Dawei Yin
However, it is nontrivial to directly apply these PLM-based rankers to the large-scale web search system due to the following challenging issues:(1) the prohibitively expensive computations of massive neural PLMs, especially for long texts in the web-document, prohibit their deployments in an online ranking system that demands extremely low latency;(2) the discrepancy between existing ranking-agnostic pre-training objectives and the ad-hoc retrieval scenarios that demand comprehensive relevance modeling is another main barrier for improving the online ranking system;(3) a real-world search engine typically involves a committee of ranking components, and thus the compatibility of the individually fine-tuned ranking model is critical for a cooperative ranking system.
no code implementations • 25 Jan 2018 • Weijian Zhang, Jonathan Deakin, Nicholas J. Higham, Shuaiqiang Wang
We present Etymo (https://etymo. io), a discovery engine to facilitate artificial intelligence (AI) research and development.