no code implementations • EMNLP (FEVER) 2021 • Rami Aly, Zhijiang Guo, Michael Sejr Schlichtkrull, James Thorne, Andreas Vlachos, Christos Christodoulopoulos, Oana Cocarascu, Arpit Mittal
The Fact Extraction and VERification Over Unstructured and Structured information (FEVEROUS) shared task, asks participating systems to determine whether human-authored claims are Supported or Refuted based on evidence retrieved from Wikipedia (or NotEnoughInfo if the claim cannot be verified).
1 code implementation • 29 May 2024 • Huanshuo Liu, Hao Zhang, Zhijiang Guo, Kuicai Dong, Xiangyang Li, Yi Quan Lee, Cong Zhang, Yong liu
Specifically, CtrlA employs an honesty probe to regulate the LLM's behavior by manipulating its representations for increased honesty, and a confidence probe to monitor the internal states of LLM and assess confidence levels, determining the retrieval necessity during generation.
1 code implementation • 27 May 2024 • Jianqiao Lu, Zhiyang Dou, Hongru Wang, Zeyu Cao, Jianbo Dai, Yingjia Wan, Yinya Huang, Zhijiang Guo
We experimentally validate that the confidence variations learned by the verification model trained on the final answer correctness can effectively identify errors in the reasoning steps.
1 code implementation • 24 May 2024 • Dong Huang, Jianbo Dai, Han Weng, Puzhen Wu, Yuhao QING, Jie M. Zhang, Heming Cui, Zhijiang Guo
These profiles are fed back to the LLM, which then revises the code to reduce overhead.
1 code implementation • 19 May 2024 • Jianbo Dai, Jianqiao Lu, Yunlong Feng, Rongju Ruan, Ming Cheng, Haochen Tan, Zhijiang Guo
Our study analyzed two common benchmarks, HumanEval and MBPP, and found that these might not thoroughly evaluate LLMs' code generation capacities due to limitations in quality, difficulty, and granularity.
1 code implementation • 30 Apr 2024 • Chunlin Tian, Zhan Shi, Zhijiang Guo, Li Li, Chengzhong Xu
Through a series of experiments, we have uncovered two critical insights that shed light on the training and parameter inefficiency of LoRA.
no code implementations • 28 Mar 2024 • Yuxuan Yao, Han Wu, Zhijiang Guo, Biyan Zhou, Jiahui Gao, Sichun Luo, Hanxu Hou, Xiaojin Fu, Linqi Song
Large language models (LLMs) have demonstrated outstanding performance across various tasks, yet they still exhibit limitations such as hallucination, unfaithful reasoning, and toxic content.
1 code implementation • 25 Mar 2024 • Yinhong Liu, Han Zhou, Zhijiang Guo, Ehsan Shareghi, Ivan Vulić, Anna Korhonen, Nigel Collier
Large Language Models (LLMs) have demonstrated promising capabilities as automatic evaluators in assessing the quality of generated natural language.
no code implementations • 25 Feb 2024 • Xuming Hu, Xiaochuan Li, Junzhe Chen, Yinghui Li, Yangning Li, Xiaoguang Li, Yasheng Wang, Qun Liu, Lijie Wen, Philip S. Yu, Zhijiang Guo
To this end, we propose evaluating the robustness of generative search engines in the realistic and high-risk setting, where adversaries have only black-box system access and seek to deceive the model into returning incorrect responses.
no code implementations • 28 Jan 2024 • Jianqiao Lu, Wanjun Zhong, YuFei Wang, Zhijiang Guo, Qi Zhu, Wenyong Huang, Yanlin Wang, Fei Mi, Baojun Wang, Yasheng Wang, Lifeng Shang, Xin Jiang, Qun Liu
With the teacher's guidance, the student learns to iteratively refine its answer with feedback, and forms a robust and comprehensive understanding of the posed questions.
no code implementations • 27 Jan 2024 • Caiqi Zhang, Zhijiang Guo, Andreas Vlachos
This paper investigates the potential benefits of language-specific fact-checking models, focusing on the case of Chinese.
1 code implementation • 26 Jan 2024 • Haochen Tan, Zhijiang Guo, Zhan Shi, Lu Xu, Zhili Liu, Yunlong Feng, Xiaoguang Li, Yasheng Wang, Lifeng Shang, Qun Liu, Linqi Song
LLMs are prompted to generate extensive content in response to these meta-questions.
no code implementations • 12 Nov 2023 • Ying Su, Xiaojin Fu, Mingwen Liu, Zhijiang Guo
Logical reasoning remains a pivotal component within the realm of artificial intelligence.
1 code implementation • 16 Oct 2023 • Jing Xiong, Jianhao Shen, Ye Yuan, Haiming Wang, Yichun Yin, Zhengying Liu, Lin Li, Zhijiang Guo, Qingxing Cao, Yinya Huang, Chuanyang Zheng, Xiaodan Liang, Ming Zhang, Qun Liu
Automated theorem proving (ATP) has become an appealing domain for exploring the reasoning ability of the recent successful generative language models.
no code implementations • 8 Oct 2023 • Xuming Hu, Junzhe Chen, Xiaochuan Li, Yufei Guo, Lijie Wen, Philip S. Yu, Zhijiang Guo
Large language models (LLMs) have recently driven striking performance improvements across a range of natural language processing tasks.
1 code implementation • 4 Oct 2023 • Jing Xiong, Zixuan Li, Chuanyang Zheng, Zhijiang Guo, Yichun Yin, Enze Xie, Zhicheng Yang, Qingxing Cao, Haiming Wang, Xiongwei Han, Jing Tang, Chengming Li, Xiaodan Liang
Dual Queries first query LLM to obtain LLM-generated knowledge such as CoT, then query the retriever to obtain the final exemplars via both question and the knowledge.
no code implementations • 25 May 2023 • Xuming Hu, Zhijiang Guo, Zhiyang Teng, Irwin King, Philip S. Yu
Multimodal relation extraction (MRE) is the task of identifying the semantic relationships between two entities based on the context of the sentence image pair.
no code implementations • 25 May 2023 • Xuming Hu, Junzhe Chen, Zhijiang Guo, Philip S. Yu
Evidence plays a crucial role in automated fact-checking.
1 code implementation • 22 May 2023 • Mubashara Akhtar, Michael Schlichtkrull, Zhijiang Guo, Oana Cocarascu, Elena Simperl, Andreas Vlachos
In this survey, we conceptualise a framework for AFC including subtasks unique to multimodal misinformation.
1 code implementation • NeurIPS 2023 • Michael Schlichtkrull, Zhijiang Guo, Andreas Vlachos
Existing datasets for automated fact-checking have substantial limitations, such as relying on artificial claims, lacking annotations for evidence and intermediate reasoning, or including evidence published after the claim.
1 code implementation • 2 May 2023 • Xuming Hu, Zhaochen Hong, Zhijiang Guo, Lijie Wen, Philip S. Yu
In light of this, we propose a fact verification model named ReRead to retrieve evidence and verify claim that: (1) Train the evidence retriever to obtain interpretable evidence (i. e., faithfulness and plausibility criteria); (2) Train the claim verifier to revisit the evidence retrieved by the optimized evidence retriever to improve the accuracy.
1 code implementation • 19 Nov 2022 • Siyang Song, Yuxin Song, Cheng Luo, Zhiyuan Song, Selim Kuzucu, Xi Jia, Zhijiang Guo, Weicheng Xie, Linlin Shen, Hatice Gunes
Our framework is effective, robust and flexible, and is a plug-and-play module that can be combined with different backbones and Graph Neural Networks (GNNs) to generate a task-specific graph representation from various graph and non-graph data.
1 code implementation • 28 Sep 2022 • Peilin Zhou, Zeqiang Wang, Dading Chong, Zhijiang Guo, Yining Hua, Zichang Su, Zhiyang Teng, Jiageng Wu, Jie Yang
To further investigate tweet users' attitudes toward specific entities, 4 types of entities (Person, Organization, Drug, and Vaccine) are selected and annotated with user sentiments, resulting in a targeted sentiment dataset with 9, 101 entities (in 5, 278 tweets).
no code implementations • COLING 2022 • Xuming Hu, Zhijiang Guo, Yu Fu, Lijie Wen, Philip S. Yu
A scene graph is a semantic representation that expresses the objects, attributes, and relationships between objects in a scene.
1 code implementation • NAACL 2022 • Xuming Hu, Zhijiang Guo, Guanyu Wu, Aiwei Liu, Lijie Wen, Philip S. Yu
The explosion of misinformation spreading in the media ecosystem urges for automated fact-checking.
1 code implementation • EMNLP 2021 • Guoshun Nan, Jiaqi Zeng, Rui Qiao, Zhijiang Guo, Wei Lu
Information Extraction (IE) aims to extract structural information from unstructured texts.
1 code implementation • 26 Aug 2021 • Zhijiang Guo, Michael Schlichtkrull, Andreas Vlachos
Fact-checking has become increasingly important due to the speed with which both information and misinformation can spread in the modern media ecosystem.
1 code implementation • 10 Jun 2021 • Rami Aly, Zhijiang Guo, Michael Schlichtkrull, James Thorne, Andreas Vlachos, Christos Christodoulopoulos, Oana Cocarascu, Arpit Mittal
Fact verification has attracted a lot of attention in the machine learning and natural language processing communities, as it is one of the key methods for detecting misinformation.
1 code implementation • EMNLP 2020 • Yan Zhang, Zhijiang Guo, Zhiyang Teng, Wei Lu, Shay B. Cohen, Zuozhu Liu, Lidong Bing
With the help of these strategies, we are able to train a model with fewer parameters while maintaining the model capacity.
2 code implementations • ACL 2020 • Guoshun Nan, Zhijiang Guo, Ivan Sekulić, Wei Lu
Document-level relation extraction requires integrating information within and across multiple sentences of a document and capturing complex interactions between inter-sentence entities.
Ranked #9 on Relation Extraction on GDA
1 code implementation • TACL 2019 • Zhijiang Guo, Yan Zhang, Zhiyang Teng, Wei Lu
We focus on graph-to-sequence learning, which can be framed as transducing graph structures to sequences for text generation.
2 code implementations • ACL 2019 • Zhijiang Guo, Yan Zhang, Wei Lu
Dependency trees convey rich structural information that is proven useful for extracting relations among entities in text.
Ranked #26 on Relation Extraction on TACRED
no code implementations • EMNLP 2018 • Zhijiang Guo, Wei Lu
This paper introduces a simple yet effective transition-based system for Abstract Meaning Representation (AMR) parsing.