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
  • [21] Evidence Inference Networks for Interpretable Claim Verification
    Wu, Lianwei
    Rao, Yuan
    Sun, Ling
    He, Wangbo
    THIRTY-FIFTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, THIRTY-THIRD CONFERENCE ON INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE AND THE ELEVENTH SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE, 2021, 35 : 14058 - 14066
  • [22] Claim Verification under Positive Unlabeled Learning
    Yang, Fan
    Dragut, Eduard
    Mukherjee, Arjun
    2020 IEEE/ACM INTERNATIONAL CONFERENCE ON ADVANCES IN SOCIAL NETWORKS ANALYSIS AND MINING (ASONAM), 2020, : 143 - 150
  • [23] An enhanced dynamic interaction network for claim verification
    Li, Peiguang
    Sun, Xian
    Yu, Hongfeng
    Zhang, Wenkai
    Xu, Guangluan
    NEUROCOMPUTING, 2021, 439 : 34 - 43
  • [24] ClaimVerif: A Real-time Claim Verification System Using the Web and Fact Databases
    Zhi, Shi
    Sun, Yicheng
    Liu, Jiayi
    Zhang, Chao
    Han, Jiawei
    CIKM'17: PROCEEDINGS OF THE 2017 ACM CONFERENCE ON INFORMATION AND KNOWLEDGE MANAGEMENT, 2017, : 2555 - 2558
  • [25] Signature verification using DWT and neural network
    Jawarkar, N.P.
    Ahmed, V.
    Journal of the Institution of Engineers (India), Part CP: Computer Engineering Division, 2009, 90 (MAY): : 41 - 46
  • [26] Neural Network Verification Using Residual Reasoning
    Elboher, Yizhak Yisrael
    Cohen, Elazar
    Katz, Guy
    SOFTWARE ENGINEERING AND FORMAL METHODS, SEFM 2022, 2022, 13550 : 173 - 189
  • [27] Neural Network Verification using Polynomial Optimisation
    Newton, Matthew
    Papachristodoulou, Antonis
    2021 60TH IEEE CONFERENCE ON DECISION AND CONTROL (CDC), 2021, : 5092 - 5097
  • [28] Speaker verification using committee neural networks
    Reddy, NP
    Butch, OA
    COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE, 2003, 72 (02) : 109 - 115
  • [29] Automatic fingerprint verification using neural networks
    Ceguerra, A
    Koprinska, I
    ARTIFICIAL NEURAL NETWORKS - ICANN 2002, 2002, 2415 : 1281 - 1286
  • [30] Simplifying Neural Networks Using Formal Verification
    Gokulanathan, Sumathi
    Feldsher, Alexander
    Malca, Adi
    Barrett, Clark
    Katz, Guy
    NASA FORMAL METHODS (NFM 2020), 2020, 12229 : 85 - 93