LOREN: Logic-Regularized Reasoning for Interpretable Fact Verification

Chen, Jiangjie; Bao, Qiaoben; Sun, Changchun; Zhang, Xinbo; Chen, Jiaze; Zhou, Hao; Li, Lei

doi:10.1609/aaai.v36i10.21291

Cited by 18 publications

(15 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To enhance fact-checking capabilities, various techniques have been developed over the past decade. These include employing multi-layer perceptron models (Vlachos and Riedel 2014), incorporating attention mechanisms (Parikh et al 2016), utilizing Graph Neural Networks (Liu et al 2020), employing semantic role labeling and logical reasoning tools (Chen et al 2020). Transformer-based language models, particularly BERT models, have gained significant attention in claim verification (Soleimani, Monz, and Worring 2019;Portelli et al 2020;Chernyavskiy and Ilvovsky 2019;Nie, Chen, and Bansal 2019;Tokala et al 2019;Tan et al 2023b).…”

Section: Related Workmentioning

confidence: 99%

Faithful Reasoning over Scientific Claims

Tan,

Tandon,

Wadden

et al. 2024

AAAI-SS

View full text Add to dashboard Cite

Claim verification in scientific domains requires models that faithfully incorporate relevant knowledge from the ever-growing, vast existing literature. Unfaithful claim verifications can lead to misinformation such as those observed during the COVID-19 pandemic. Fact-checking systems often fail to capture the complex relationship between claims and evidence, especially with ambiguous claims and implicit assumptions. Relying only on current LLMs poses challenges due to hallucinations and information traceability issues. To address these challenges, our approach considers multiple viewpoints onto the scientific literature, enabling the assessment of contradictory arguments and implicit assumptions. Our proposed inference method adds faithful reasoning to large language models by distilling information from diverse, relevant scientific abstracts. This method provides a verdict label that can be weighted by the reputation of the scientific articles and an explanation that can be traced back to sources. Our findings demonstrate that humans not only perceive our explanation to be significantly superior to the off-the-shelf model, but they also evaluate it as faithfully enabling the tracing of evidence back to its original sources.

show abstract

Section: Related Workmentioning

confidence: 99%

Faithful Reasoning over Scientific Claims

Tan,

Tandon,

Wadden

et al. 2024

AAAI-SS

View full text Add to dashboard Cite

show abstract

“…We adopt the knowledge distillation strategy with a teacher model and a student model to integrate logic rules into latent variables, providing weak supervision inspired by (Chen et al 2022a). The teacher model projects the variational distribution q ω (z | x, y) into a subspace q ⋆ ω (y z | x, y) adhering to the logic rules, with y z ∈ {Real, Fake} representing the logical aggregation of z.…”

Section: Logical Rule Constraintsmentioning

confidence: 99%

“…Fortunately, from the perspective of human cognition, there is at least one deceptive pattern if the news is fake, while no deceptive pattern if the news is real. Inspired by the powerful expressive capabilities of first-order logic language in capturing complex relationships (Enderton 2001), our mind starts by formalizing these rules using first-order logic as a form of weak supervision inspired by (Chen et al 2022a). By doing so, we establish a correlation between the available labels for news authenticity and the presence of unsupervised deceptive patterns, enabling the underlying deceptive patterns to be automatically learned.…”

Section: Introductionmentioning

confidence: 99%

Unveiling Implicit Deceptive Patterns in Multi-Modal Fake News via Neuro-Symbolic Reasoning

Dong,

He,

Wang

et al. 2024

AAAI

View full text Add to dashboard Cite

In the current Internet landscape, the rampant spread of fake news, particularly in the form of multi-modal content, poses a great social threat. While automatic multi-modal fake news detection methods have shown promising results, the lack of explainability remains a significant challenge. Existing approaches provide superficial explainability by displaying learned important components or views from well-trained networks, but they often fail to uncover the implicit deceptive patterns that reveal how fake news is fabricated. To address this limitation, we begin by predefining three typical deceptive patterns, namely image manipulation, cross-modal inconsistency, and image repurposing, which shed light on the mechanisms underlying fake news fabrication. Then, we propose a novel Neuro-Symbolic Latent Model called NSLM, that not only derives accurate judgments on the veracity of news but also uncovers the implicit deceptive patterns as explanations. Specifically, the existence of each deceptive pattern is expressed as a two-valued learnable latent variable, which is acquired through amortized variational inference and weak supervision based on symbolic logic rules. Additionally, we devise pseudo-siamese networks to capture distinct deceptive patterns effectively. Experimental results on two real-world datasets demonstrate that our NSLM achieves the best performance in fake news detection while providing insightful explanations of deceptive patterns.

show abstract

“…e.g. GopherCite supports answers with verified quotes [183], logicregularized reasoning for interpretable fact verification [194], survey on automated fact-checking [195], hallucinated content detection [196], RL approach for explainability using entailment trees [197].…”

Section: Strengthsmentioning

confidence: 99%

“…• Provide references, traceability, faithful explanation logic [194] or the emerging field of entailment tree explanation [197,329]. • Automated fact-checking [195].…”

Section: Hallucination and Credibilitymentioning

confidence: 99%

Complex QA and language models hybrid architectures, Survey

Daull¹,

Bellot²,

Bruno³

et al. 2023

Preprint

View full text Add to dashboard Cite

This paper provides a survey of the state of the art of hybrid language models architectures and strategies for "complex" question-answering (QA, CQA, CPS). Very large language models are good at leveraging public data on standard problems but once you want to tackle more specific complex questions or problems you may need specific architecture, knowledge, skills, tasks, methods, sensitive data, performance, human approval and versatile feedback... This survey extends findings from the robust community edited research papers BIG, BLOOM and HELM which open source, benchmark and analyze limits and challenges of large language models in terms of tasks complexity and strict evaluation on accuracy (e.g. fairness, robustness, toxicity, ...). It identifies the key elements used with Large Language Models (LLM) to solve complex questions or problems. Recent projects like ChatGPT and GALACTICA have allowed non-specialists to grasp the great potential as well as the equally strong limitations of language models in complex QA. Hybridizing these models with different components could allow to overcome these different limits and go much further. We discuss some challenges associated with complex QA, including domain adaptation, decomposition and efficient multi-step QA, long form QA, non-factoid QA, safety and multi-sensitivity data protection, multimodal search, hallucinations, QA explainability and truthfulness, time dimension. Therefore we review current solutions and promising strategies, using elements such as hybrid LLM architectures, human-in-the-loop reinforcement learning, prompting adaptation, neuro-symbolic and structured knowledge grounding, program synthesis, and others. We analyze existing solutions and provide an overview of the current research and trends in the area of complex QA.

show abstract

LOREN: Logic-Regularized Reasoning for Interpretable Fact Verification

Cited by 18 publications

References 24 publications

Faithful Reasoning over Scientific Claims

Faithful Reasoning over Scientific Claims

Unveiling Implicit Deceptive Patterns in Multi-Modal Fake News via Neuro-Symbolic Reasoning

Complex QA and language models hybrid architectures, Survey

Contact Info

Product

Resources

About