{"id":{"repo_id":"cambridge","oai_identifier":"oai:www.repository.cam.ac.uk:1810/384090"},"canonical_url":"https://search.dev.ndltd.org/etd/cambridge/oai:www.repository.cam.ac.uk:1810/384090","repository":{"repo_id":"cambridge","name":"Cambridge University","base_url":"https://api.repository.cam.ac.uk/server/oai/request"},"display":{"title":"Neuro-symbolic fact verification","abstract":"Fact-checking, the process of assessing the veracity of claims, is a time-consuming task that can potentially take hours or days for a single claim, incentivising the development of computational methods to automate (parts of) the fact-checking process. This challenge has been instantiated in the field of natural language processing as fact verification, and is typically modelled by systems which extract textual evidence from a knowledge source and reason about a claim’s veracity via neural entailment systems. However, the reasoning processes of these systems are inherently opaque, suffer from robustness issues, and fail at capturing well-formalised semantic concepts like monotonicity. To address these issues, this thesis explores neuro-symbolic methods for fact verification, which integrate symbolic systems with neural representations. We focus in particular on natural logic, a framework of compositional entailment which operates directly on natural language by capturing the set-theoretic relation between parts of a claim and textual evidence. As a logical system designed to identify valid inferences via deterministic proofs, it is particularly suited for fact verification, where a claim needs to be entailed by evidence, while guaranteeing explainability properties like faithfulness and actionability. The first contribution of this thesis is the development of FEVEROUS, a large-scale dataset which requires complex reasoning over retrieved textual and tabular evidence, such as arithmetic or multi-hop reasoning, to incentivise the development of neuro-symbolic methods. We then explore means of combining natural logic as a symbolic reasoning framework with advances in autoregressive language modelling to improve the explainability, robustness, and generalisability of fact verification systems. We propose systems that (i) integrate natural logic as a dynamic and transparent stopping criterion for autoregressive multi-hop document retrieval; (ii) obviate the need for large-scale annotated data for training natural logic proof systems; and (iii) extend natural logic to tabular evidence and arithmetic computations, thus addressing key challenges encountered in the verification of complex claims. Finally, we unify these three contributions into a single natural logic-based fact verification system towards reasoning over textual and tabular evidence while satisfying important explainability desiderata.","abstract_html":"Fact-checking, the process of assessing the veracity of claims, is a time-consuming task that can potentially take hours or days for a single claim, incentivising the development of computational methods to automate (parts of) the fact-checking process. This challenge has been instantiated in the field of natural language processing as fact verification, and is typically modelled by systems which extract textual evidence from a knowledge source and reason about a claim’s veracity via neural entailment systems. However, the reasoning processes of these systems are inherently opaque, suffer from robustness issues, and fail at capturing well-formalised semantic concepts like monotonicity. To address these issues, this thesis explores neuro-symbolic methods for fact verification, which integrate symbolic systems with neural representations. We focus in particular on natural logic, a framework of compositional entailment which operates directly on natural language by capturing the set-theoretic relation between parts of a claim and textual evidence. As a logical system designed to identify valid inferences via deterministic proofs, it is particularly suited for fact verification, where a claim needs to be entailed by evidence, while guaranteeing explainability properties like faithfulness and actionability. The first contribution of this thesis is the development of FEVEROUS, a large-scale dataset which requires complex reasoning over retrieved textual and tabular evidence, such as arithmetic or multi-hop reasoning, to incentivise the development of neuro-symbolic methods. We then explore means of combining natural logic as a symbolic reasoning framework with advances in autoregressive language modelling to improve the explainability, robustness, and generalisability of fact verification systems. We propose systems that (i) integrate natural logic as a dynamic and transparent stopping criterion for autoregressive multi-hop document retrieval; (ii) obviate the need for large-scale annotated data for training natural logic proof systems; and (iii) extend natural logic to tabular evidence and arithmetic computations, thus addressing key challenges encountered in the verification of complex claims. Finally, we unify these three contributions into a single natural logic-based fact verification system towards reasoning over textual and tabular evidence while satisfying important explainability desiderata.","abstract_has_math":false,"creators":["Aly, Rami"],"institution":"University of Cambridge","degree_name":"Doctor of Philosophy (PhD)","degree_level":"Doctoral","degree_discipline":null,"degree_department":null,"school":null,"contributors":[],"advisors":["Vlachos, Andreas"],"committee_chairs":[],"committee_members":[],"year":2024,"date_issued":"2024-11-23","date_published":"2024-11-23","updated_at":"2026-07-22T22:24:28Z","subjects":["natural language processing","fact-checking","fact verification","explainable AI","information retrieval","neuro-symbolic AI","natural logic","compositional entailment"],"languages":["eng"],"rights":[],"rights_urls":["https://apollo8-f-pro.lib.cam.ac.uk/bitstreams/12901f69-c896-437e-a026-26d960b0a02e/download","http://purl.org/NET/rdflicense/allrightsreserved"],"identifier_entries":[]},"links":{"outbound_url":"https://doi.org/10.17863/CAM.118214","outbound_label":"DOI","outbound_source":"dc:identifier.doi"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.advisor","label":"Advisor","values":["Vlachos, Andreas"]},{"key":"dc:contributor.sponsor","label":"Sponsor","values":["The research was supported by an EPSRC studentship. The curation of the FEVEROUS dataset was funded by Amazon."]},{"key":"dc:creator","label":"Author","values":["Aly, Rami"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.issued","label":"Date","values":["2024-11-23"]},{"key":"dc:publisher.institution","label":"Dc Publisher Institution","values":["University of Cambridge"]},{"key":"dc:relation.isreferencedby.uri","label":"Dc Relation Isreferencedby URI","values":["https://www.repository.cam.ac.uk/handle/1810/384090"]},{"key":"dc:type","label":"Dc Type","values":["Thesis"]},{"key":"dc:type.qualificationlevel","label":"Dc Type Qualificationlevel","values":["Doctoral"]},{"key":"dc:type.qualificationname","label":"Dc Type Qualificationname","values":["Doctor of Philosophy (PhD)"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["natural language processing","fact-checking","fact verification","explainable AI","information retrieval","neuro-symbolic AI","natural logic","compositional entailment"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language","label":"Dc Language","values":["eng"]},{"key":"dc:rights","label":"Dc Rights","values":["https://apollo8-f-pro.lib.cam.ac.uk/bitstreams/12901f69-c896-437e-a026-26d960b0a02e/download","http://purl.org/NET/rdflicense/allrightsreserved"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.doi","label":"DOI","values":["https://doi.org/10.17863/CAM.118214"]},{"key":"dc:identifier.uri","label":"Identifier URI","values":["https://apollo8-f-pro.lib.cam.ac.uk/bitstreams/c977a7b7-af8d-497e-9de2-3867ab812a54/download"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["Fact-checking, the process of assessing the veracity of claims, is a time-consuming task that can potentially take hours or days for a single claim, incentivising the development of computational methods to automate (parts of) the fact-checking process. This challenge has been instantiated in the field of natural language processing as fact verification, and is typically modelled by systems which extract textual evidence from a knowledge source and reason about a claim’s veracity via neural entailment systems. However, the reasoning processes of these systems are inherently opaque, suffer from robustness issues, and fail at capturing well-formalised semantic concepts like monotonicity. To address these issues, this thesis explores neuro-symbolic methods for fact verification, which integrate symbolic systems with neural representations. We focus in particular on natural logic, a framework of compositional entailment which operates directly on natural language by capturing the set-theoretic relation between parts of a claim and textual evidence. As a logical system designed to identify valid inferences via deterministic proofs, it is particularly suited for fact verification, where a claim needs to be entailed by evidence, while guaranteeing explainability properties like faithfulness and actionability. The first contribution of this thesis is the development of FEVEROUS, a large-scale dataset which requires complex reasoning over retrieved textual and tabular evidence, such as arithmetic or multi-hop reasoning, to incentivise the development of neuro-symbolic methods. We then explore means of combining natural logic as a symbolic reasoning framework with advances in autoregressive language modelling to improve the explainability, robustness, and generalisability of fact verification systems. We propose systems that (i) integrate natural logic as a dynamic and transparent stopping criterion for autoregressive multi-hop document retrieval; (ii) obviate the need for large-scale annotated data for training natural logic proof systems; and (iii) extend natural logic to tabular evidence and arithmetic computations, thus addressing key challenges encountered in the verification of complex claims. Finally, we unify these three contributions into a single natural logic-based fact verification system towards reasoning over textual and tabular evidence while satisfying important explainability desiderata."]},{"key":"dc:format.checksum.md5","label":"Dc Format Checksum Md5","values":["c656eae60901ad69c4f643a917edda73","87eda9de84448d1f82354d60eee3eb5f"]},{"key":"dc:title","label":"Title","values":["Neuro-symbolic fact verification"]}]}],"canonical_facts":{"dc:contributor.advisor":["Vlachos, Andreas"],"dc:contributor.sponsor":["The research was supported by an EPSRC studentship. The curation of the FEVEROUS dataset was funded by Amazon."],"dc:creator":["Aly, Rami"],"dc:date.issued":["2024-11-23"],"dc:description.abstract":["Fact-checking, the process of assessing the veracity of claims, is a time-consuming task that can potentially take hours or days for a single claim, incentivising the development of computational methods to automate (parts of) the fact-checking process. This challenge has been instantiated in the field of natural language processing as fact verification, and is typically modelled by systems which extract textual evidence from a knowledge source and reason about a claim’s veracity via neural entailment systems. However, the reasoning processes of these systems are inherently opaque, suffer from robustness issues, and fail at capturing well-formalised semantic concepts like monotonicity. To address these issues, this thesis explores neuro-symbolic methods for fact verification, which integrate symbolic systems with neural representations. We focus in particular on natural logic, a framework of compositional entailment which operates directly on natural language by capturing the set-theoretic relation between parts of a claim and textual evidence. As a logical system designed to identify valid inferences via deterministic proofs, it is particularly suited for fact verification, where a claim needs to be entailed by evidence, while guaranteeing explainability properties like faithfulness and actionability. The first contribution of this thesis is the development of FEVEROUS, a large-scale dataset which requires complex reasoning over retrieved textual and tabular evidence, such as arithmetic or multi-hop reasoning, to incentivise the development of neuro-symbolic methods. We then explore means of combining natural logic as a symbolic reasoning framework with advances in autoregressive language modelling to improve the explainability, robustness, and generalisability of fact verification systems. We propose systems that (i) integrate natural logic as a dynamic and transparent stopping criterion for autoregressive multi-hop document retrieval; (ii) obviate the need for large-scale annotated data for training natural logic proof systems; and (iii) extend natural logic to tabular evidence and arithmetic computations, thus addressing key challenges encountered in the verification of complex claims. Finally, we unify these three contributions into a single natural logic-based fact verification system towards reasoning over textual and tabular evidence while satisfying important explainability desiderata."],"dc:format.checksum.md5":["c656eae60901ad69c4f643a917edda73","87eda9de84448d1f82354d60eee3eb5f"],"dc:identifier.doi":["https://doi.org/10.17863/CAM.118214"],"dc:identifier.uri":["https://apollo8-f-pro.lib.cam.ac.uk/bitstreams/c977a7b7-af8d-497e-9de2-3867ab812a54/download"],"dc:language":["eng"],"dc:publisher.institution":["University of Cambridge"],"dc:relation.isreferencedby.uri":["https://www.repository.cam.ac.uk/handle/1810/384090"],"dc:rights":["https://apollo8-f-pro.lib.cam.ac.uk/bitstreams/12901f69-c896-437e-a026-26d960b0a02e/download","http://purl.org/NET/rdflicense/allrightsreserved"],"dc:subject":["natural language processing","fact-checking","fact verification","explainable AI","information retrieval","neuro-symbolic AI","natural logic","compositional entailment"],"dc:title":["Neuro-symbolic fact verification"],"dc:type":["Thesis"],"dc:type.qualificationlevel":["Doctoral"],"dc:type.qualificationname":["Doctor of Philosophy (PhD)"]},"updated_at":"2026-07-22T22:24:28Z"}