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 20 of 1031 for “"LLM"”.

  1. Understanding LLM Communictaion

    The training of modern Large Language Models (LLMs) requires distributed computing across Graphics Processing Unit (GPU) clusters, where network communication efficiency critically impacts performance and cost. Existing profiling tools provide either high-level metrics or low-level timing data, but …

    heid-thes Repository record for Understanding LLM Communictaion (opens in a new tab)

  2. Simulating LLM Runtime Latency

    Large Language Models (LLMs) are expensive to run and can incur high latencies. Each LLM application has its own cost and latency targets. For example, AI voice assistants operate under low latency objectives, while large document batch processing jobs are typically cost-sensitive. However, …

    mit Repository record for Simulating LLM Runtime Latency (opens in a new tab)

  3. ResearchBuddy AI: LLM-Powered Assistant

    This paper presents ResearchBuddy AI, an LLM-powered assistant that addresses modern research information overload problems. The project has three essential features, including finetuning of large language models for structured research paper summarization, prompt engineering for flexible …

    texas-state Repository record for ResearchBuddy AI: LLM-Powered Assistant (opens in a new tab)

  4. LEO: an LLM-Powered EDA Overview

    Computational notebooks impose a linear structure that impedes data analysts’ sensemaking process with overwritten cells, dead-end code, and fragmented logic. This challenge is especially pronounced when analysts either encounter a notebook authored by someone else or revisit a self-authored …

    mit Repository record for LEO: an LLM-Powered EDA Overview (opens in a new tab)

  5. LLM-Directed Agent Models in Cyberspace

    … the application of Large Language Models (LLMs) for automating penetration tests and Cyber Capture the Flag (CTF) challenges, bridging the gap between static tools and dynamic human intuition in cybersecurity. This work provides an evaluation framework for assessing the performance of LLMs …

    mit Repository record for LLM-Directed Agent Models in Cyberspace (opens in a new tab)

  6. Bypassing LLM watermarks with color-aware substitutions

    Submission published under a 24 month embargo labeled 'Closed Access', the embargo will last until 2026-05-01

    uiuc Repository record for Bypassing LLM watermarks with color-aware substitutions (opens in a new tab)

  7. Mitigating LLM Hallucination in the Banking Domain

    Large Language Models (LLMs) offer significant potential in the banking sector, particularly for applications such as fraud detection, credit approval, and enhancing customer experience. However, their tendency to "hallucinate"—generating plausible but inaccurate information—poses a critical …

    mit Repository record for Mitigating LLM Hallucination in the Banking Domain (opens in a new tab)

  8. LLM-Supported Natural Language to Bash Translation

    … capabilities of large language models (LLMs) for command composition alleviates these issues. However, the NL2SH performance of LLMs is difficult to assess due to inaccurate test data and unreliable heuristics for determining the functional equivalence of Bash commands. We present a …

    mit Repository record for LLM-Supported Natural Language to Bash Translation (opens in a new tab)

  9. Addressing data challenges in LLM-enhanced software engineering

    The rapid adoption of large language models (LLMs) is reshaping software engineering practice, yet it reveals a critical dichotomy: while resource-intensive tasks like code generation benefit from large datasets and standardized benchmarks, they also face significant risks from data contamination …

    uoit Repository record for Addressing data challenges in LLM-enhanced software engineering (opens in a new tab)

  10. Efficient LLM training and inference with contextual sparsity

    Submission published under a 24 month embargo labeled 'U of I Access', the embargo will last until 2027-05-01

    uiuc Repository record for Efficient LLM training and inference with contextual sparsity (opens in a new tab)

  11. Initiation and Growth of Reaction in LLM-105

    … this thesis was to understand the behaviour of LLM-105, a new explosive material, when subjected to impact. Explosive reactivity under impact can be thought of in terms of safety (sensitiveness) and response to shock loading (sensitivity). The experimental work presented addresses both regimes, …

    cambridge Repository record for Initiation and Growth of Reaction in LLM-105 (opens in a new tab)

  12. Impacts of LLM-Based Text Normalization on Price Prediction

    This study investigates the effect of LLM-based text normalization on price prediction from user-generated product descriptions. Using the Mercari Price Suggestion Challenge dataset, we normalize 120,000 item descriptions with GPT-4o-mini and evaluate the impact across three modeling pipelines: a …

    reykjavik Repository record for Impacts of LLM-Based Text Normalization on Price Prediction (opens in a new tab)

  13. Automatically Improving The Code Quality Of Rust Via LLM

    … define and resolve the challenges of leveraging LLM to automatically improve Rust’s code quality. The application of LLMs to Rust code quality improvement requires addressing fundamental challenges in three key areas: generating compilable code that satisfies Rust’s strict type system, detecting …

    gatech Repository record for Automatically Improving The Code Quality Of Rust Via LLM (opens in a new tab)

  14. LLM-powered active learning for cost-effective text classification

    This thesis presents an LLM-powered active learning framework for cost-effective text classification, addressing the challenge of potential LLM annotation errors while balancing annotation quality and model accuracy. Our methodology combines human and large language model (LLM) annotations using …

    uoit Repository record for LLM-powered active learning for cost-effective text classification (opens in a new tab)

  15. Taxonomie pro LLM v komponentě Kafka projektu Apache Camel

    Tato práce se zaměřuje na koncept umělé inteligence, konkrétně na velké jazykové modely (Large Language Models). Popisuje základní principy neuronových sítí a fáze trénování v oblasti umělé inteligence, strojového učení a jazykových modelů, přičemž se zabývá i výzvami efektivního trénování …

    brno-tech Repository record for Taxonomie pro LLM v komponentě Kafka projektu Apache Camel (opens in a new tab)

  16. SLO-aware optimization and stateful orchestration for LLM systems

    The rapid evolution of Large Language Models (LLMs) has shifted the focus of AI infrastructure from simple text generation to complex, multi-turn agentic workflows. As these applications become increasingly sensitive to latency and dependencies, existing serving systems—which primarily optimize for …

    uiuc Repository record for SLO-aware optimization and stateful orchestration for LLM systems (opens in a new tab)

  17. Improving Accuracy Predictions of Companion Classifiers for LLM Routing

    … increasing versatility of Large Language Models (LLMs) calls for developing effective routing systems to match tasks with the most suitable models, balancing accuracy and computational cost. This research introduces a novel meta-cascade routing framework that combines meta-routing, where a …

    mit Repository record for Improving Accuracy Predictions of Companion Classifiers for LLM Routing (opens in a new tab)

  18. Can an LLM find its way around a Spreadsheet?

    … highly specialized pipelines. We ask whether an LLM can find its way around a spreadsheet and how to support end-users in taking their free-form data processing requests to fruition. Just like RAG retrieves context to answer users' queries, we demonstrate how we can retrieve elements from a code …

    vt Repository record for Can an LLM find its way around a Spreadsheet? (opens in a new tab)

  19. CLOSED-LOOP SCALING: AUTONOMOUS IMPROVEMENT OF LLM AND LVLM REASONING

    … the improvement of large language models (LLMs) and large vision--language models (LVLMs) demands a paradigm shift. This thesis proposes automatic scaling: a closed-loop framework in which models autonomously improve through their own computation via three layers. Inference-time scaling …

    nus Repository record for CLOSED-LOOP SCALING: AUTONOMOUS IMPROVEMENT OF LLM AND LVLM REASONING (opens in a new tab)

  20. Consistency-aware and LLM-assisted methods for named entity recognition

    … thesis investigates how large language models (LLMs) can be leveraged to enhance NER and relation extraction in data-scarce clinical settings. Although LLMs are capable of generating diverse and contextually rich text, their direct application to clinical information extraction poses challenges …

    iastate Repository record for Consistency-aware and LLM-assisted methods for named entity recognition (opens in a new tab)

Page 1 of 52