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 729 for “"language models"”.
-
Sequentialized Language Models
… an optimal, strictly bottom-up parseable metalanguage for a compression scheme comprising multiple grammars; a principled approach to ambiguity and agrammatical text; and an incremental analysis selection algorithm. The metalanguage construction emphasizes lexical left-corner analysis …
-
Towards trustworthy large language models
Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2024-03-01 without embargo terms
-
Language models as semantic indexers
Submission published under a 24 month embargo labeled 'U of I Access', the embargo will last until 2025-12-01
-
Implicit capabilities of language models
We study implicit capabilities of language models: abilities that emerge from standard training without the models being directly trained to possess them. As AI systems become more powerful, understanding such capabilities matters for anticipating these systems' behaviour and designing safety …
-
Phonological Representations in Language Models
Large language models (LLMs) are the dominant tools for processing and generating natural language, typically operating over an input representation consisting of discrete subword tokens derived from web-scraped orthographic text. Understanding and interpreting these models is crucial not only for …
-
Truthfulness in Large Language Models
Large language models (LLMs) have been experiencing a rapid rise in utility, accessibility, and popularity, but there are still many areas in which they can improve. One such area for improvement is their truthfulness. We seek to improve the truthfulness of LLMs by probing their internal …
-
Unforgettable Generalization in Language Models
When language models (LMs) are trained to forget (or “unlearn”) a skill, how precisely does their behavior change? We study the behavior of transformer LMs in which tasks have been forgotten via fine-tuning on randomized labels. Such LMs learn to generate near-random predictions for individual …
-
Knowledge Engineering via Large Language Models
… This thesis investigates how Large Language Models (LLMs) can act as knowledge engineers, transforming raw text into structured, reusable, and queryable information. The central question guiding this work is how far the understanding capabilities of LLMs can automate the organization …
-
Future of Personalized, Aligned Language Models
Aligning Large Language Models (LLMs) to cater to different human preferences, learning new skills, and unlearning harmful behavior is an important problem. Search-based methods, such as Best-of-N or Monte-Carlo Tree Search, are effective, but impractical for LLM adaptation due to their high …
-
Recognizing Speech with Large Language Models
Recent work has shown that large language models can be made to parse the contents of non-text embeddings and use those contents to perform various tasks. However, work focusing on audio inputs to large language models has thus far focused on either training a joint audio-text model from scratch on …
-
Probing Language Models for Contextual ScaleUnderstanding
Pretrained language models (LMs) have demonstrated a remarkable ability to emit linguistic and factual knowledge in certain fields. Additionally, they seem to encode relational information about different concepts in a knowledge base. However, since they are trained solely on textual corpora, it is …
-
Learning human beliefs with language models
… This dissertation introduces new deep, neural language model -based approaches for capturing beliefs reflected in and formed by media. In part one of this dissertation, we introduce a model for automatically summarizing multiple documents about the same subject, which we apply to opinionated …
-
Solving Graph Problems with Large Language Models
This thesis investigates how large language models (LLMs) can be used to solve classical computational problems on graphs. Graphs are a fundamental abstraction for representing real-world systems, such as social, transportation, and communication networks, but they pose unique challenges: their …
-
Scalable information extraction with large language models
… document understanding. Although large language models (LLMs) have broadened the scope of IE through zero-shot and in-context extraction, scalable IE remains challenging in realistic settings, particularly for scientific and other specialized domains where labeled data is scarce, …
-
Radiology Report Summarization With Large Language Models
… both decoder-only and encoder-decoder large language models (LLMs), specifically LLaMa 3.1-8B-Instruct and T5-Base. In the first stage, we fine-tune each model on MIMIC-CXR, a large publicly available dataset of chest radiographs with free-text radiology reports, to transform the Findings …
-
On the Resource Efficiency of Language Models
Large language models (LLMs) have revolutionized a wide range of natural language processing tasks. However, their practical utility faces resource challenges in two dimensions: data efficiency and model efficiency. For post-training, LLMs face data curation challenges where high-quality labeled …
-
Semantic Language models with deep neural Networks
Spoken language systems (SLS) communicate with users in natural language through speech. There are two main problems related to processing the spoken input in SLS. The first one is automatic speech recognition (ASR) which recognizes what the user says. The second one is spoken language …
-
Towards Ecologically Valid Evaluations of Language Models
In recent years, language models have seen widespread adoption across diverse fields and been applied to novel, unprecedented use cases. This calls for a critical need to systematically evaluate how well these models perform in practical, user-centered applications. To ensure these evaluations are …
-
Improving reasoning capabilities of large language models
Submission published under a 24 month embargo labeled 'U of I Access', the embargo will last until 2027-05-01
-
Harnessing large language models for software engineering
Submission published under a 24 month embargo labeled 'U of I Access', the embargo will last until 2026-12-01
Page 1 of 37