1 code implementation • 21 May 2025 • Zehong Wang, Zheyuan Liu, Tianyi Ma, Jiazheng Li, Zheyuan Zhang, Xingbo Fu, Yiyang Li, Zhengqing Yuan, Wei Song, Yijun Ma, Qingkai Zeng, Xiusi Chen, Jianan Zhao, Jundong Li, Meng Jiang, Pietro Lio, Nitesh Chawla, Chuxu Zhang, Yanfang Ye
Positioned at the intersection of graph learning and general-purpose AI, GFMs are poised to become foundational infrastructure for open-ended reasoning over structured data.
1 code implementation • 8 Feb 2025 • Bo Ni, Zheyuan Liu, Leyao Wang, Yongjia Lei, Yuying Zhao, Xueqi Cheng, Qingkai Zeng, Luna Dong, Yinglong Xia, Krishnaram Kenthapadi, Ryan Rossi, Franck Dernoncourt, Md Mehrab Tanjim, Nesreen Ahmed, Xiaorui Liu, Wenqi Fan, Erik Blasch, Yu Wang, Meng Jiang, Tyler Derr
Although various methods have been developed to improve the trustworthiness of RAG methods, there is a lack of a unified perspective and framework for research in this topic.
1 code implementation • 23 Jan 2025 • Zhaoxuan Tan, Zinan Zeng, Qingkai Zeng, Zhenyu Wu, Zheyuan Liu, Fengran Mo, Meng Jiang
To address this, we introduce PerRecBench, disassociating the evaluation from these two factors and assessing recommendation techniques on capturing the personal preferences in a grouped ranking manner.
1 code implementation • 29 Oct 2024 • Zheyuan Liu, Guangyao Dou, Mengzhao Jia, Zhaoxuan Tan, Qingkai Zeng, Yongle Yuan, Meng Jiang
Generative models such as Large Language Models (LLM) and Multimodal Large Language models (MLLMs) trained on massive web corpora can memorize and disclose individuals' confidential and private data, raising legal and ethical concerns.
no code implementations • 16 Oct 2024 • Zhenyu Wu, Qingkai Zeng, Zhihan Zhang, Zhaoxuan Tan, Chao Shen, Meng Jiang
Best-of-N decoding methods instruct large language models (LLMs) to generate multiple solutions, score each using a scoring function, and select the highest scored as the final answer to mathematical reasoning problems.
1 code implementation • 17 Aug 2024 • Qingkai Zeng, Yuyang Bai, Zhaoxuan Tan, Zhenyu Wu, Shangbin Feng, Meng Jiang
Taxonomies play a crucial role in various applications by providing a structural representation of knowledge.
1 code implementation • 9 Aug 2024 • Guangyu Meng, Qingkai Zeng, John P. Lalor, Hong Yu
Leveraging IRT, we propose a Dynamic Data Selection via Model Ability Estimation (DDS-MAE) strategy to schedule the appropriate amount of data during model training.
no code implementations • 23 May 2024 • Zhenyu Wu, Qingkai Zeng, Zhihan Zhang, Zhaoxuan Tan, Chao Shen, Meng Jiang
The condition can be an entity in an open-domain question or a numeric value in a math question, which requires minimal effort (via prompting) to identify.
1 code implementation • 20 Feb 2024 • Yifan Ding, Qingkai Zeng, Tim Weninger
Fortunately, Large Language Models (LLMs) like GPT provide a highly-advanced solution to the problems inherent in EL models, but simply naive prompts to LLMs do not work well.
1 code implementation • 12 Feb 2024 • Qingkai Zeng, Yuyang Bai, Zhaoxuan Tan, Shangbin Feng, Zhenwen Liang, Zhihan Zhang, Meng Jiang
Automatic taxonomy induction is crucial for web search, recommendation systems, and question answering.
1 code implementation • 9 Feb 2024 • Yifan Ding, Amrit Poudel, Qingkai Zeng, Tim Weninger, Balaji Veeramani, Sanmitra Bhattacharya
Additionally, our instruction tuning method (EntGPT-I) improves micro-F_1 scores by 2. 1% on average in supervised EL tasks and outperforms several baseline models in six Question Answering tasks.
2 code implementations • 6 Feb 2024 • Zhaoxuan Tan, Qingkai Zeng, Yijun Tian, Zheyuan Liu, Bing Yin, Meng Jiang
OPPU integrates parametric user knowledge in the personal PEFT parameters with non-parametric knowledge from retrieval and profiles, adapting LLMs to user behavior shifts.
no code implementations • 11 Jan 2024 • Zicheng Wang, Tiejin Chen, Qinrun Dai, Yueqi Chen, Hua Wei, Qingkai Zeng
Compartmentalization effectively prevents initial corruption from turning into a successful attack.
no code implementations • 19 Oct 2023 • Zhihan Zhang, Shuohang Wang, Wenhao Yu, Yichong Xu, Dan Iter, Qingkai Zeng, Yang Liu, Chenguang Zhu, Meng Jiang
Large language models (LLMs) can perform a wide range of tasks by following natural language instructions, without the necessity of task-specific fine-tuning.
no code implementations • 16 Jul 2023 • Zhenwen Liang, Dian Yu, Xiaoman Pan, Wenlin Yao, Qingkai Zeng, Xiangliang Zhang, Dong Yu
Our approach uniquely considers the various annotation formats as different "views" and leverages them in training the model.
1 code implementation • 21 Jun 2022 • Xiaojie Guo, Qingkai Zeng, Meng Jiang, Yun Xiao, Bo Long, Lingfei Wu
Automatic product description generation for e-commerce has witnessed significant advancement in the past decade.
2 code implementations • 5 Jun 2021 • Qingkai Zeng, Jinfeng Lin, Wenhao Yu, Jane Cleland-Huang, Meng Jiang
Automatic construction of a taxonomy supports many applications in e-commerce, web search, and question answering.
1 code implementation • 8 Feb 2021 • Jinfeng Lin, Yalin Liu, Qingkai Zeng, Meng Jiang, Jane Cleland-Huang
In this study, we propose a novel framework called Trace BERT (T-BERT) to generate trace links between source code and natural language artifacts.
Transfer Learning
Software Engineering
no code implementations • EMNLP (Eval4NLP) 2021 • Qingkai Zeng, Mengxia Yu, Wenhao Yu, Tianwen Jiang, Meng Jiang
It can be used to validate the label consistency (or catches the inconsistency) in multiple sets of NER data annotation.
no code implementations • Findings of the Association for Computational Linguistics 2020 • Qingkai Zeng, Wenhao Yu, Mengxia Yu, Tianwen Jiang, Tim Weninger, Meng Jiang
The training process of scientific NER models is commonly performed in two steps: i) Pre-training a language model by self-supervised tasks on huge data and ii) fine-tune training with small labelled data.
1 code implementation • NAACL 2021 • Wenhao Yu, Lingfei Wu, Yu Deng, Qingkai Zeng, Ruchi Mahindru, Sinem Guven, Meng Jiang
In this paper, we propose a novel framework of deep transfer learning to effectively address technical QA across tasks and domains.
1 code implementation • EMNLP 2020 • Wenhao Yu, Lingfei Wu, Yu Deng, Ruchi Mahindru, Qingkai Zeng, Sinem Guven, Meng Jiang
In recent years, the need for community technical question-answering sites has increased significantly.
no code implementations • ACL 2020 • Wenhao Yu, Lingfei Wu, Qingkai Zeng, Shu Tao, Yu Deng, Meng Jiang
Existing methods learned semantic representations with dual encoders or dual variational auto-encoders.
no code implementations • NAACL 2021 • Chenguang Zhu, William Hinthorn, Ruochen Xu, Qingkai Zeng, Michael Zeng, Xuedong Huang, Meng Jiang
Automatic abstractive summaries are found to often distort or fabricate facts in the article.
no code implementations • WS 2019 • Qingkai Zeng, Mengxia Yu, Wenhao Yu, JinJun Xiong, Yiyu Shi, Meng Jiang
On a scientific concept hierarchy, a parent concept may have a few attributes, each of which has multiple values being a group of child concepts.