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 7 of 7 for “"Reasoning LLMs"”.
-
Automated Detection of Learning Pitfalls in Tabular Security Classifiers via Reasoning LLMs
… process. In this work, we investigate whether reasoning Large Language Models (LLMs) can overcome these bottlenecks to provide a fully automated identification pipeline. We focus on the uniquely challenging domain of tabular security classifiers, where rigid feature-level constraints and …
-
T-LARA: Leveraging Reasoning LLMs to Enhance the Adversarial Robustness of Tabular Security Classifiers
… families. In this thesis, we examine whether reasoning-based Large Language Models (LLMs) can circumvent these limitations to produce a classifier-agnostic method for creating realistic, low-cost adversarial examples that adhere to domain constraints. We propose T-LARA, an agentic framework …
-
Enhancing Lifelog Question-Answering with Retrieval-Augmented Generation and Reasoning Large Language Models
… recent advancements in large language models (LLMs), their capabilities in QA tasks show potential to advance lifelog understanding. In addition, with their reasoning capability, LLMs can solve the aggregation question in lifelogging that requires contextual understanding and reasoning. This …
-
Solving the ARC-AGI challenge at a human level
Reasoning LLMs such as OpenAI o1, o3 and DeepSeek R1 have made significant progress in mathematics and coding, yet struggle with advanced generalization tasks such as Abstraction and Reasoning Corpus (ARC) puzzles. To address this, we propose a diverse inference approach that aggregates multiple …
-
Semantic-Aware Fuzzing: A Reasoning-Driven Framework for LLM-Guided Input Mutation
… byte- or bit-level edits without true semantic reasoning. Even coverage-guided tools such as AFL++ rely on dictionaries, grammars, and splicing heuristics to impose only shallow structural constraints, leaving deeper protocol logic, inter-field dependencies, and domain-specific semantics …
-
Towards Reliable Machine Learning: Calibration, Label Shift Estimation, and Uncertainty Quantification
… extending reliability to large language models (LLMs), this thesis proposes Stage-Aware Uncertainty for Reasoning (SAUR) to quantify uncertainty in chain-of-thought responses produced by reasoning LLMs. By analyzing token distributions, we demonstrate that distinct stages exist within the …
-
Unifying Foundation Models with Decision Making: A Path Towards Autonomous Self-Improving Agents beyond Rewards and Human Supervision
… and scalable methods to improve base non-reasoning LLMs into better reasoners without using explicit verified data or rule-based verifiers. We analyze this counterintuitive idea: fine-tuning language models using unverified and even incorrect reasoning traces leads to reasoning …