ExClaim: Explainable Neural Claim Verification Using Rationalization

被引:2
|
作者
Gurrapu, Sai [1 ]
Huang, Lifu [1 ]
Batarseh, Feras A. [2 ]
机构
[1] Virginia Tech, Dept Comp Sci, Blacksburg, VA 24061 USA
[2] Virginia Tech, Dept Biol Syst Engn BSE, Blacksburg, VA USA
关键词
rationalization; NLP assurance; claim verification; XAI;
D O I
10.1109/STC55697.2022.00012
中图分类号
TP31 [计算机软件];
学科分类号
081202 ; 0835 ;
摘要
With the advent of deep learning, text generation language models have improved dramatically, with text at a similar level as human-written text. This can lead to rampant misinformation because content can now be created cheaply and distributed quickly. Automated claim verification methods exist to validate claims, but they lack foundational data and often use mainstream news as evidence sources that are strongly biased towards a specific agenda. Current claim verification methods use deep neural network models and complex algorithms for a high classification accuracy but it is at the expense of model explainability. The models are black-boxes and their decision-making process and the steps it took to arrive at a final prediction are obfuscated from the user. We introduce a novel claim verification approach, namely: ExClaim, that attempts to provide an explainable claim verification system with foundational evidence. Inspired by the legal system, ExClaim leverages rationalization to provide a verdict for the claim and justifies the verdict through a natural language explanation (rationale) to describe the model's decision-making process. ExClaim treats the verdict classification task as a question-answer problem and achieves a performance of 0.93 F1 score. It provides subtasks explanations to also justify the intermediate outcomes. Statistical and Explainable AI (XAI) evaluations are conducted to ensure valid and trustworthy outcomes. Ensuring claim verification systems are assured, rational, and explainable is an essential step toward improving Human-AI trust and the accessibility of black-box systems.
引用
收藏
页码:19 / 26
页数:8
相关论文
共 50 条
  • [41] A Framework for Explainable Deep Neural Models Using External Knowledge Graphs
    Daniels, Zachary A.
    Frank, Logan D.
    Menart, Christopher J.
    Raymer, Michael
    Hitzler, Pascal
    ARTIFICIAL INTELLIGENCE AND MACHINE LEARNING FOR MULTI-DOMAIN OPERATIONS APPLICATIONS II, 2020, 11413
  • [42] MSVEC: A Multidomain Testing Dataset for Scientific Claim Verification
    Evans, Michael
    Soos, Dominik
    Landers, Ethan
    Wu, Jian
    PROCEEDINGS OF THE 2023 INTERNATIONAL SYMPOSIUM ON THEORY, ALGORITHMIC FOUNDATIONS, AND PROTOCOL DESIGN FOR MOBILE NETWORKS AND MOBILE COMPUTING, MOBIHOC 2023, 2023, : 504 - 509
  • [43] A Semantics-Aware Approach to Automated Claim Verification
    Figueras, Blanca Calvo
    Cuadros, Montse
    Agerri, Rodrigo
    PROCEEDINGS OF THE FIFTH FACT EXTRACTION AND VERIFICATION WORKSHOP (FEVER 2022), 2022, : 37 - 48
  • [44] Zero-shot Fact Verification by Claim Generation
    Pan, Liangming
    Chen, Wenhu
    Xiong, Wenhan
    Kan, Min-Yen
    Wang, William Yang
    ACL-IJCNLP 2021: THE 59TH ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS AND THE 11TH INTERNATIONAL JOINT CONFERENCE ON NATURAL LANGUAGE PROCESSING, VOL 2, 2021, : 476 - 483
  • [45] Explainable Neural Networks: Achieving Interpretability in Neural Models
    Chakraborty, Manomita
    ARCHIVES OF COMPUTATIONAL METHODS IN ENGINEERING, 2024, 31 (06) : 3535 - 3550
  • [46] Explainable Face Verification for Film and Video Archive Documentation
    Neuschmied, Helmut
    Winter, Martin
    20TH INTERNATIONAL CONFERENCE ON CONTENT-BASED MULTIMEDIA INDEXING, CBMI 2023, 2023, : 104 - 110
  • [47] xCos: An Explainable Cosine Metric for Face Verification Task
    Lin, Yu-Sheng
    Liu, Zhe-Yu
    Chen, Yu-An
    Wang, Yu-Siang
    Chang, Ya-Liang
    Hsu, Winston H.
    ACM TRANSACTIONS ON MULTIMEDIA COMPUTING COMMUNICATIONS AND APPLICATIONS, 2021, 17 (03)
  • [48] Verification of Sigmoidal Artificial Neural Networks using iSAT
    Grundt, Dominik
    Jurj, Sorin Liviu
    Hagemann, Willem
    Kroeger, Paul
    Fraenzle, Martin
    ELECTRONIC PROCEEDINGS IN THEORETICAL COMPUTER SCIENCE, 2021, (361): : 45 - 60
  • [49] Verification of approved pdf using convolutional neural network
    Tsay, Tswn-Syau
    Lin, Ying-Chen
    Journal of Taiwan Agricultural Engineering, 2021, 67 (02): : 44 - 55
  • [50] Biometric Signature Verification Using Recurrent Neural Networks
    Tolosana, Ruben
    Vera-Rodriguez, Ruben
    Fierrez, Julian
    Ortega-Garcia, Javier
    2017 14TH IAPR INTERNATIONAL CONFERENCE ON DOCUMENT ANALYSIS AND RECOGNITION (ICDAR), VOL 1, 2017, : 652 - 657