Global ETD Search
Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.
Results
Showing 1 to 15 of 15 for “"Claim verification"”.
-
Explainable Neural Claim Verification Using Rationalization
… which is a significant challenge. Although claim verification techniques exist, they lack proper explainability. Numerical scores such as Attention and Lime and visualization techniques such as saliency heat maps are insufficient because they require specialized knowledge. It is inaccessible …
-
SciCheck: Reasoning Distillation for Biomedical Claim Verification
False claims about medical information can have damaging consequences. Although LLMs have been used to verify such claims, their success depends on access to accurate content and robust reasoning capabilities. Prior research assumes access to gold evidence during inference or relies on expensive, …
-
On explainable stance detection, distribution, and claim verification
… detection, stance distribution analysis, and claim verification. Yet many high-performing models remain opaque, producing accurate predictions without revealing how decisions were reached. Building systems that provide predictions with clear, faithful explanations is essential for trust, …
-
EVIDENCE-BASED CLAIM VERIFICATION WITH COMMONSENSE KNOWLEDGE AND TEMPORAL INFORMATION
… the current challenge of evidence-based claim verification by incorporating commonsense knowledge and leveraging temporal information. First, it proposes the CGAT, a framework that enriches contextual representations with commonsense knowledge from ConceptNet, improving the performance on …
-
Secure Motion Claim Verification and Decision-Making for Vehicular Cyber-Physical Systems
… For example, if one malicious vehicle claims accelerating but in fact slowing down, and meanwhile its following vehicle believes this claim, a severe collision may occur. However, traditional crypto-primitives can only guarantee the authenticity and integrity of these messages, but not …
-
Enhancing fact-checking in large language models: Cost-effective claim verification through first-order logic reformulation
… (FC) tasks, which involves verifying complex claims against challenging evidence from multiple sources, remains a crucial yet under-explored area. Our study presents a comprehensive benchmarking of various LLMs, including GPT-4, on this critical task. We utilize a modern, challenging dataset …
-
Evaluating LLM Robustness Under Adversarial and Conflicting Evidence
… including health question answering, scientific claim verification, and retrieval-augmented generation (RAG). A fundamental question underlies these systems: do LLMs genuinely reason over the evidence they receive, or do they primarily follow the stance expressed in the provided documents? This …
-
Fact-checking as a multi-step process: from ambiguity resolution to claim validation
… people. Fact-checking—the process of verifying claims against credible evidence—has emerged as a critical safeguard against misinformation. Yet, the task is fraught with challenges: claims are often ambiguous, context-dependent, or composed of multiple intertwined assertions, while automated …
-
Knowledge-Intensive NLP for Real-World Information Needs
… into a structured knowledge graph. Scientific claim verification aims to assess the veracity of scientific claims against a corpus of research literature. Finally, entity-oriented query refinement aims to help users navigate an open-ended space of entities to quickly understand a new domain or …
-
Interpretation and Robustness of Black-Box ML Models for Secure Cyber Space
… analyzes the resilience of Automatic Scientific Claim Verification (ASCV) tools against sophisticated adversarial rephrasing, underscoring the imperative for robust model design and introducing an innovative attack model that crafts precise adversarial examples. Secondly, it assesses the impact …
-
DP-CP-RAG: DUAL-PROJECTION CONSTRAINT-PROVIDER RETRIEVAL-AUGMENTED GENERATION FOR EVIDENCE-GROUNDED PORT-DOMAIN QUESTION ANSWERING
… SQL synthesis and execution, constraint gating, claim verification, and fusion-based answer generation within a unified end-to-end pipeline. It supports three processing depths for non-domain, knowledge-only, and data-dependent queries, thereby improving both efficiency and answer reliability. …
-
False Textual Information Detection - Towards Building a Truth Machine
… false information, such as questionable claims and fake news, diffuses fast. Detecting false information is one of the most elusive and long-standing challenges. With social media growing dominant, falsehood can diffuse faster and broader than truth. This calls for building a ``truth …
-
Toward complex data structure aggregation and truth discovery
… or a reliable single source (e.g., fact verification). The conflict among different sources might be because of errors, out-of-date data, typos, missing records, etc. However, the misinformation from a single reliable source might be generated by a public figure like a politician or an …
-
Modeling and predicting trustworthiness of online textual information
… new dynamics, it is important to validate online claims and distinguish fact from fiction. My research tries to address the challenges in modeling trustworthiness of free-text claims. In this dissertation, I present the need for research on trustworthiness of online information and argue for going …
-
Reasoning beyond scale: Structured inference for small language models
Submission published under a 24 month embargo labeled 'U of I Access', the embargo will last until 2027-05-01