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 13 of 13 for “"Structured Prompting"”.
-
The reasoning bottleneck in Graph-RAG: Structured prompting and context compression for multi-hop QA
… graphs from document collections and retrieving structured context that preserves entities, relations, and community summaries. Yet strong retrieval does not guarantee strong answers. This thesis studies the reasoning bottleneck in Graph-RAG and asks whether inference-time augmentations, …
-
Private Messages, Public Health: Detecting Emotional Support with Long-Context LLMs
… models, and show how newer LLMs, coupled with structured prompting and clinically informed evaluations, can drastically improve classification performance on modern chat platforms like Instagram. We describe the processing of participant-donated Instagram data, detail the methodology for …
-
Leveraging Large Language Models for Mastery Tutor Construction
… all mastery-learning behaviors are defined by a structured system prompt. Across 45 sessions with 25 novice programmers, the tutor correctly followed the mastery rule in 94.5% of progression decisions, generated structurally valid practice problems in 96% of instances, and graded responses …
-
Backward Reasoning in LLMs: A Strategy for Identifying Irrelevant Context in Mathematical Word Problems
… drops. To mitigate this gap we propose five structured prompting methods: semantic-role abstraction, timeline reasoning, tree representations, contrastive prompting, and a unified process-supervision prompt. The unified scheme yields the most reliable gains, boosting backward-reasoning …
-
Designing Answer-Aware LLM Hints to Scaffold Deeper Learning in K–12 Programming Education
… approach balances guidance and autonomy through structured prompting that preserves productive struggle. The system was tested with real students and evaluated through automated analysis and surveys, which showed that the hints were clear, helpful, and easy to use. Students who used the hints …
-
Automated Medical Coding Using Supervised Deep Learning and Large Language Models
… and limitations of LLMs. We develop a prompting pipeline without fine-tuning that decomposes coding into two subtasks: disease/procedure identification and ICD mapping. We compare zero-shot, few-shot, zero-shot Chain-of-Thought (CoT), few-shot CoT, and Retrieval-Augmented Generation …
-
Object-centric perception and description of video
… and film grammar are incorporated through structured prompting, enabling more accurate and narratively grounded descriptions. Finally, we address the problem of streaming character naming, developing a framework that infers character identities progressively from audiovisual cues and …
-
Designing Human- and AI-Assisted Health Coaching for Preventive Behaviour Change
… and an experimental study demonstrated that structured prompting improved the quality and fidelity of AI-generated responses (83% vs. 6% acceptable). Conclusions: These studies advance understanding of health coaching for preventive behaviour change across human- and AI-assisted contexts. …
-
Digital Twin Based Surgical Video Analysis
… Surgical Phase Recognition (DT-SPR) showed that structured depth and segmentation cues can improve robustness, but the original framework used a relatively limited modality design and only partially automated representation construction. This essay extends DT-SPR into a broader digital twin based …
-
Enhancing consumer health question answering systems through rhetorical structure theory-guided large language model
… network (LLM) via supervised fine-tuning and structured prompting. To support system training and evaluation, this study constructs CHQA-MedEmo, the first large-scale, multi-layer corpus of Chinese health consultation records. The corpus is annotated for both medical informational needs and …
-
Understanding 3D Dynamics of Hands, Objects and Bodies in Long Egocentric Videos
… parallel execution. Lastly, we intro- duce a structured prompting strategy that guides a vision-language model to reason about the constraints in this problem. Understanding unconstrained long egocentric videos is challenging, and many methods in this thesis are first steps, rather than final …
-
Anthrogames
… using retrieval-augmented generation, structured prompting and hybrid human–AI authoring. These pipelines address the challenge of modeling cultural systems without simplifying or distorting source materials and of constraining generative models to remain faithful to documented …
-
The Impact of Computing Environment on Test Flakiness
… with generic prompts, improving to 50–77% with structured prompting. Based on these findings, this work introduces tools to support the detection, diagnosis, and mitigation of computing environment assumptions in testing. These tools assist practitioners and researchers in identifying …