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 39 for “"Factual Accuracy"”.

  1. FROM BALANCE TO ADJUDICATION: OBJECTIVITY AND THE REPORTING PRACTICES OF JOURNALISTS AND FACT-CHECKERS

    … journalistic practice that evaluates the factual accuracy of political claims. Its rise has intensified debates about how fact-checking differs from traditional journalism, even though verifying factual accuracy has long been a core professional responsibility of journalists. This question …

    maryland Repository record for FROM BALANCE TO ADJUDICATION: OBJECTIVITY AND THE REPORTING PRACTICES OF JOURNALISTS AND FACT-CHECKERS (opens in a new tab)

  2. Striving for Honesty: A Travel Writer in Brazil

    … book to her reader is that the writer aims for factual accuracy. But there are more complex promises to be found in modern travel books (and works of creative non-fiction generally), it is argued, that allow for deviations from factual accuracy or presenting characters, events and other details …

    adelaide Repository record for Striving for Honesty: A Travel Writer in Brazil (opens in a new tab)

  3. The Irish in the Caribbean as an online post historical phenomenon

    … their political or emotional utility rather than factual accuracy. The study introduces the concept of Ophelialogy—a heuristic tool that analyzes how historical claims are used and what effects they produce. Drawing on a wide array of sources including memes, fact-checkers, journalists, and …

    lmu-germany Repository record for The Irish in the Caribbean as an online post historical phenomenon (opens in a new tab)

  4. Uncovering the Reliability and Consistency of AI Language Models: A Systematic Study

    … understanding, leading to inconsistencies and factual inaccuracies in their responses. Traditional Natural Language Processing (NLP) benchmarks often overlook nuances in LLM behavior and reliability. This thesis addresses this gap by curating a dataset across six categories: Fact, Conspiracy, …

    waterloo Repository record for Uncovering the Reliability and Consistency of AI Language Models: A Systematic Study (opens in a new tab)

  5. Moral self-convictions: uncontested pleas and Canadian criminal law

    … creating new opportunities for certainty, factual accuracy, agency, and mutual advantage in otherwise highly adversarial proceedings. Although formally forbidden, defendants may still enter nolo contendere informally and surreptitiously. I conclude by arguing that these pleas be formalized …

    manitoba Repository record for Moral self-convictions: uncontested pleas and Canadian criminal law (opens in a new tab)

  6. Generation of Wikidata Descriptions with Grammatical Framework

    … achieve higher cross-linguistic consistency and factual accuracy. The workflow also supports efficient extension to additional languages, as demonstrated by the Bengali case by Mohammad Rakib Imtiaz. These results highlight the potential of GF, the GF Resource Grammar Library, and the approach …

    chalmers Repository record for Generation of Wikidata Descriptions with Grammatical Framework (opens in a new tab)

  7. RAG at scale : accelerating prompt assembly for LLM inference with CXL

    Retrieval-augmented generation (RAG) enhances the factual accuracy of large language models (LLMs) by dynamically appending relevant external content to user queries, but the document retrieval and tokenization steps add latency to the critical path. In production deployments, retrieval and …

    texas Repository record for RAG at scale : accelerating prompt assembly for LLM inference with CXL (opens in a new tab)

  8. Uma metodologia baseada em agentes com avaliação autônoma para extração de conhecimento em textos técnicos

    … increase the contextual precision and factual accuracy of the responses, while simultaneously reducing hallucination to 80% faithfulness to the context. The study validates the Multi-Agent RAG as a necessary architectural pattern to guarantee reliability in the transfer of engineering …

    brazil-ufrn Repository record for Uma metodologia baseada em agentes com avaliação autônoma para extração de conhecimento em textos técnicos (opens in a new tab)

  9. Detect, Explain, Ground: A Sustainable Pipeline for Robust Large Language Model–Powered Agents

    … breakdowns, such as incoherence, irrelevance, or factual inaccuracies (hallucinations). This thesis develops a sustainable, three-stage pipeline to detect, manage, and ground LLM-powered agents, enhancing their robustness and reliability. First, to establish a baseline for self-monitoring, we …

    queens Repository record for Detect, Explain, Ground: A Sustainable Pipeline for Robust Large Language Model–Powered Agents (opens in a new tab)

  10. The Charleston approach : a documentary script on urban renewal through historic restoration and preservation

    … (2) dramatic treatment, (3) social purpose, (4) factual accuracy, and (5) problem-solution format.</p><p>The writer attempted to apply these criteria to a documentary film script on urban renewal through historic restoration and preservation in Charleston, South Carolina. He found that although …

    ut-knoxville Repository record for The Charleston approach : a documentary script on urban renewal through historic restoration and preservation (opens in a new tab)

  11. DI kaip informacijos šaltinis: pokalbiai apie Lietuvos istoriją ir kultūros paveldą /

    … of history and cultural heritage, where not only factual accuracy but also cultural context, narrative formation, and interpretive sensitivity are important. The theoretical chapters analyze the use and operating principles of artificial intelligence, the reliability of AI systems as a source of …

    vilnius Repository record for DI kaip informacijos šaltinis: pokalbiai apie Lietuvos istoriją ir kultūros paveldą / (opens in a new tab)

  12. Between Chronicle and Legend: A Two-Scene Environment and Visual Effects Examination of Physical Accuracy and Emotional Exaggeration on the Honey Creek Bridge Collapse

    … the core of storytelling lies a tension between factual accuracy and dramatic stylization. We investigate that tension by examining how narrative truth is conveyed, distorted, or enhanced through visual dramatization by focusing on the psychology of audience perception and the motivations behind …

    clemson Repository record for Between Chronicle and Legend: A Two-Scene Environment and Visual Effects Examination of Physical Accuracy and Emotional Exaggeration on the Honey Creek Bridge Collapse (opens in a new tab)

  13. An Analytical Evaluation of Large Language Models for Verifying Structural Damage and Failure Causality Reports

    … using a five‑metric scoring framework assessing accuracy, completeness, reliability, recency, and depth. The analysis was supplemented by a structured human evaluation survey examining user perceptions of response quality. Results indicate that LLM performance is strongly dependent on the …

    gatech Repository record for An Analytical Evaluation of Large Language Models for Verifying Structural Damage and Failure Causality Reports (opens in a new tab)

  14. A Design Framework for Building Intelligent Tutoring Systems Based on Learning Science Principles

    … evaluation, examining aspects such as the factual accuracy and relevance of its responses. Experts in the field of biology offered favorable remarks, particularly highlighting its capability to break down questions into manageable subproblems and provide encouraging responses to students.

    rice Repository record for A Design Framework for Building Intelligent Tutoring Systems Based on Learning Science Principles (opens in a new tab)

  15. Expert-Driven Evaluation Platforms for Scientific Information Extraction Using Large Language Models

    … necessitates expert-driven evaluation to verify factual accuracy and scientific reasoning. Traditional evaluation workflows rely on generic survey tools and spreadsheets. These tools impose cognitive load and may introduce psychological biases into the evaluation process. This thesis presents the …

    vt Repository record for Expert-Driven Evaluation Platforms for Scientific Information Extraction Using Large Language Models (opens in a new tab)

  16. AI-Generated and Distributed Reality: How AI systems Democratized and Incentivized Visual Disinformation During the 2024 U.S. Election

    … truth in which engagement metrics, rather than factual accuracy, increasingly determine ‘what counts as true’ for voters. In turn, news consumers veer toward either belief in nonfactual information or apathy toward factual information. Both outcomes corrode the intersubjective reality upon which …

    concordia Repository record for AI-Generated and Distributed Reality: How AI systems Democratized and Incentivized Visual Disinformation During the 2024 U.S. Election (opens in a new tab) Download PDF for AI-Generated and Distributed Reality: How AI systems Democratized and Incentivized Visual Disinformation During the 2024 U.S. Election (opens in a new tab)

  17. A multimodal approach to the creation and translation of cinematic biographical dramas: the case of the film “chevalier” (2022) by stephen williams and its lithuanian translation /

    … prioritises entertainment over strict historical accuracy. Moreover, visual and aural elements play a crucial role in conveying dramatic elements to the audience and contributing to the film’s emotional weight. Additionally, it is discovered that external focalisation, withholding characters’ …

    vilnius Repository record for A multimodal approach to the creation and translation of cinematic biographical dramas: the case of the film “chevalier” (2022) by stephen williams and its lithuanian translation / (opens in a new tab)

  18. AI-Powered Multimodal Tour Guide: Enhancing Cultural Tourism with Image Recognition, and Personalized Storytelling

    … style to user preferences while preserving factual accuracy, and a Streamlit interface orchestrates retrieval, multimodal reasoning, and real-time text-to-speech synthesis. The research followed a design science and mixed- methods evaluation strategy. A quantitative study on 100 image–query …

    rit Repository record for AI-Powered Multimodal Tour Guide: Enhancing Cultural Tourism with Image Recognition, and Personalized Storytelling (opens in a new tab)

  19. Automatic Engineering Report Generation Using Multi-Agent Systems and Large Language Models

    … and partitioned RAG artifacts, affect the factual accuracy, structural quality, and practical utility of the generated reports in an engineering context. Performance is assessed through a comparative analysis of three reports: a Multi- Agent System generated, single-agent baseline, and …

    chalmers Repository record for Automatic Engineering Report Generation Using Multi-Agent Systems and Large Language Models (opens in a new tab)

  20. Synthesising Summaries: A novel Retrieval-Augmented Generation-based pipeline for multi-document summarisation

    … improvements in summary quality, coherence, and factual accuracy compared to baseline methods. The fine-tuned Gemma models, coupled with RAG techniques, show promise in handling the complexities of scientific text. The study also shows interesting trade-offs between model size and performance, …

    sheffield-hallam Repository record for Synthesising Summaries: A novel Retrieval-Augmented Generation-based pipeline for multi-document summarisation (opens in a new tab) Download PDF for Synthesising Summaries: A novel Retrieval-Augmented Generation-based pipeline for multi-document summarisation (opens in a new tab)

Page 1 of 2