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 “"Complex Reasoning"”.
-
Multimodal Representation Learning for Textual Reasoning over Knowledge Graphs
… from KGs is generally achieved through logical reasoning, but this process can be computationally expensive and has limited performance due to the large size and complexity of relationships within the KGs. Furthermore, to extend the usage of KGs to non-expert users, retrieval over them cannot …
-
Advances in Hierarchical Probabilistic Multimodal Data Fusion
… into a shared representation suitable for complex reasoning. As a result, one can make more precise inferences about the underlying phenomenon than is possible with each data source used in isolation. In the thesis we adopt a Bayesian view of multimodal data fusion, which formulates …
-
A*-Decoding: Token-Efficient Inference Scaling
… for improving language model performance on complex reasoning tasks. While existing methods have shown strong performance gains under fixed compute budgets, there has been little focus on optimally utilizing that budget during inference. In this work, we introduce A*-decoding, a search-based …
-
Hybrid Testing: Combining Static Analysis and Directed Fuzzing
… be challenging for developers to debug large, complex codebases. In this paper, Hybrid Testing is presented as a solution. Hybrid Testing combines static and dynamic analyses, leveraging static analysis to perform complex reasoning about logic, memory management, and concurrency. It creates a …
-
Enhancing Natural Language Inference through Multi-Agent Deliberation
… strategies (from basic responses to step-by-step reasoning) against four deliberation protocols (individual baseline, self-deliberation, peer review, and judge-mediated consensus). Using the Llama-3.2 and Phi-3-Mini models on the challenging SciNLI, MSciNLI, MISMATCHED, and ConjNLI benchmarks, we …
-
Scalable Data Paradigms for Steering General-Purpose Language Models
… chatting with users, using tools, or performing complex reasoning, poses another set of challenges that require diverse, high-quality, and increasingly costly training data. This dissertation explores scalable paradigms for structuring, creating, and optimizing data to facilitate the broader …
-
Large-scale probabilistic aerial reconstruction
… Collectively, these models enable complex reasoning about urban scenes by fusing all available data across modalities, a crucial necessity for future autonomous agents and large-scale augmented-reality applications.
-
Characterizing and recognizing spoken corrections in human-computer dialog
… transcription of the recognition string nor complex reasoning based on the full conversation. We further extend the conventional analysis of speaking styles beyond a 'read' versus 'conversational' contrast to extreme clear speech, describing divergence from phonological and durational models …
-
Exploring the impact of a Project 2000 Common Foundation Programme Curriculum upon the critical thinking abilities of a group of student nurses
… be identified in the concurrent professional reasoning processes of student nurses. A longitudinal multi-method approach incorporating across-method triangulation in the collection of quantitative and qualitative data have been utilised in order to address the following questions: 1. Does the …
-
Neuro-symbolic fact verification
… 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 …
-
Reasoning one's way out of skepticism
… the past, which commits them to accepting a complex argument for skepticism about complex reasoning. But if one accepts this argument, one's position is self-undermining in the following sense: one believes a proposition P while at the same time believing that one should not believe P. This …
-
Toward Deliberative AI: Multi-Agent LLMs for Real-World Reasoning
… as a promising strategy for improving the reasoning abilities of large language models (LLMs). However, existing approaches often fall short due to inefficiencies, shallow agreement, and a lack of real-world applicability. In this thesis, we introduce two novel frameworks CONSENSAGENT and …
-
Transformative Technology: Staff Perceptions, Attitudes, And Behaviors Related To The Use Of Learning Management Transformative Technologies
… attention to processes that take into account complex reasoning, and habits of mind and work. The study also concludes that providing practitioners with deeply meaningful learning experiences, personalized supports, and restructured planning time is crucial to sustainability and must be …
-
Interpretable Multi-hop Question Answering
… can be used to quantify the understanding and reasoning ability of intelligent systems, a large number of QA datasets have been developed in recent years, and significant progress has been made in this direction. However, most existing QA systems use an end-to-end model to answer natural …
-
Language models for verifiable mathematical automation: Interaction, integration, and autoformalization
Stronger automation in formal mathematical reasoning provides scalability, trust-worthiness, and accessibility: it enables efficient verification of complex proofs, reduces the likelihood of errors in intricate calculations, allows non-experts to engage with mathematical concepts, and potentially …