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 41 for “"generative language"”.
-
Generative Language Models for Program Synthesis and Evaluation
Recent advances in Large Language Models (LLMs), such as GPT and Claude, have significantly advanced the field of program synthesis. To evaluate the performance of these models, traditional benchmarks like APPS, MBPP, and HumanEval reveal limitations due to potential data leakage and their …
-
A Two-Stage Approach for Implicit Bias Detection in Generative Language Models
… The release of OpenAI’s ChatGPT has brought generative language models to the spotlight, creating interest in developing and integrating them into many industries and applications. However, machine learning models and AI systems are known to exhibit and propagate bias and generative language …
-
Semantic enrichment of database columns using generative language models for advanced query searches
… study introduces a novel application of natural language generation (NLG) models to improve database table retrieval. Unlike previous works primarily utilizing embeddings and natural language processing (NLP) models, this work explores using NLGs to generate database column descriptions to …
-
How Generative Language Models Shape Human Problem Solving: A Phenomenon-centered, Sociotechnical Perspective
… work and innovation in organizations. Textbased generative large language models (GLMs) are being rapidly adopted across domains, offering potentially substantial performance improvements. Yet, GLMs can also introduce risks and negatively affect outcomes, creating a pressing practical need to …
-
Accelerating Molecular Discovery with Generative Language Models: A journey through the chemical space
… materials and molecules. Recently, molecular generative models coupled with virtual screening methods have shown promising results in efficient and systematic chemical space exploration. The hopes are high that such methods can accelerate the molecular discovery process, in particular when …
-
“The Limits of Our Language are the Limits of Our World”: The Use of Generative Language to Create More Inspiring Realities of the World
… of the individual. It introduces the idea that language use is important to wellbeing in the individual and can be used more intentionally to impact outcomes. Through the lens of positive psychology, this paper analyzes the use of language and the outcomes it drives, as well as how the more …
-
Understanding Generative Language Models From the Inside-Out and the Outside-In: Examining Teens’ Technical and Socio-Ethical Pieces of Understandings When Designing and Auditing Models
The pervasive push for the adoption of generative artificial intelligence/machine learning (AI/ML) technologies has increased the need to support teens in developing AI/ML literacies. However, most work has centered on preparing young people to use these systems, with less attention to how they can …
-
Social-communicative control and its effect on echolalia in children with autism
… between the cognitive, social, and language demands of interactive contexts is vital if we are to begin to understand the foundations of echolalia in autism. It is also important to investigate the dynamics of echolalia in natural contexts if we are to develop appropriate …
-
Responsible and healthy conversations: Developing and evaluating engaging chatbots through controlled use of language models
… abandoning interventions prematurely. Recent generative language models bring greater flexibility and variety to dialogue, allowing for more adaptable and personalized interventions, but their unpredictability risks causing miscommunication. Ensuring that chatbots are implemented ethically, …
-
Use of Matrix Training for Teaching Noun-Verb Combinations
… often experience difficulties acquiring generative language skills and generalizing learned responses across settings and people. Matrix training is a teaching procedure designed to promote recombinative generalization by directly teaching a subset of targets while probing for the …
-
Automated Vulnerability Detection and Patching in IEC 61131-3 Code Using Large Language Models
… these sophisticated attacks. Conversely, modern generative language models possess advanced semantic reasoning capabilities but are inherently probabilistic; when applied to industrial programming, they frequently hallucinate non-standard syntax or structural logic that violates the strict …
-
Automated Vulnerability Detection and Patching in IEC 61131-3 Code Using Large Language Models
… these sophisticated attacks. Conversely, modern generative language models possess advanced semantic reasoning capabilities but are inherently probabilistic; when applied to industrial programming, they frequently hallucinate non-standard syntax or structural logic that violates the strict …
-
Comparison of State-of-the-art Algorithms for de novo Drug Design
… de novo drug design has increased. By employing generative models, in combination with suitable optimization algorithms, the chemical space can be explored to generate new and useful molecular compounds. Multiple models have been published for this purpose. While they all report promising results …
-
Mapping AI and public relations research: trends, theories, and ethics
… (PR) through automated content production, generative language models, audience segmentation, and data-driven decision-making. While scholars highlight AI's potential to enhance efficiency and strategic capability, concerns around transparency, privacy, algorithmic bias, governance, …
-
Recommender Systems with Fairness Considerations and Strategic Agent Dynamics.
… and user welfare. Finally, we introduce GLoSS (Generative Language Models with Semantic Search), which combines generative query modeling with dense semantic retrieval to enable recommendation beyond direct lexical overlap, achieving state-of-the-art performance, particularly for cold-start …
-
LANGUAGE MODELS FOR ROBOT TASK PLANNING WITH HUMAN DEMONSTRATIONS
… addresses these challenges leveraging Large Language Models (LLMs) and Vision-Language Models (VLMs) to convert task demonstrations to robot code offline, then adapt to changes planning online. This work is divided into three connected components. Firstly, we developed DEMO2CODE, that …
-
Towards Interpretable Machine Reading Comprehension with Mixed Effects Regression and Exploratory Prompt Analysis
We investigate the properties of natural language prompts that determine their difficulty in machine reading comprehension tasks. While much work has been done benchmarking language model performance at the task level, there is considerably less literature focused on how individual task items can …
-
Towards Explainability for Language Models in Security Testing
Modern generative Language Models (LMs) present as black boxes, requiring significant trust in their capabilities and making it difficult to understand the reasoning behind their decisions. As these LMs are increasingly used for code and test-case generation, testers must trust them without knowing …
-
Towards Large Language Models for Everyone: Instruction Following, Knowledge Retrieval and Multilingualism
Large language models (LLMs) have significantly advanced the field of Natural Language Processing and demonstrated the potential to fuel a variety of AI applications. Nonetheless, building them in a way that maximally benefits the very wide range of everyday use cases is challenging. Firstly, LLMs …
-
DEEP LEARNING METHODS FOR ANTIBODY STRUCTURE PREDICTION AND DESIGN
… In the second half, I present work on generative language models for protein sequences. The first project describes ProGen2, a suite of language models trained at massive scale. I demonstrate that these models can be used to generate protein sequences resembling those produced by nature …
Page 1 of 3