{"id":{"repo_id":"poli-torino","oai_identifier":"oai:iris.polito.it:11583/3013101"},"canonical_url":"https://search.dev.ndltd.org/etd/poli-torino/oai:iris.polito.it:11583/3013101","repository":{"repo_id":"poli-torino","name":"Politecnico di Torino","base_url":"https://iris.polito.it/oai/request"},"display":{"title":"Efficient Adaptation of Large Language Models in Natural Language Processing","abstract":"The rapid growth of Large Language Models (LLMs) has significantly improved performance across a wide range of Natural Language Processing (NLP) tasks, including Information Retrieval (IR). Despite their strong generalisation capabilities, LLMs still require domain- and task-specific fine-tuning to achieve competitive performance in highly specialised scenarios. LLMs exhibit some generalisation abilities, though these are not uniformly reliable across tasks and domains. In particular, adapting these models to downstream domains and tasks has become challenging as full fine-tuning is computationally expensive, memory-intensive and difficult to scale across multiple domains and tasks. Over the past few years, substantial research has been made into efficient fine-tuning of LLMs, resulting in various proposed approaches. Nevertheless, it remains an ongoing research area with several unresolved issues and challenges.","abstract_html":"The rapid growth of Large Language Models (LLMs) has significantly improved performance across a wide range of Natural Language Processing (NLP) tasks, including Information Retrieval (IR). Despite their strong generalisation capabilities, LLMs still require domain- and task-specific fine-tuning to achieve competitive performance in highly specialised scenarios. LLMs exhibit some generalisation abilities, though these are not uniformly reliable across tasks and domains. In particular, adapting these models to downstream domains and tasks has become challenging as full fine-tuning is computationally expensive, memory-intensive and difficult to scale across multiple domains and tasks. Over the past few years, substantial research has been made into efficient fine-tuning of LLMs, resulting in various proposed approaches. Nevertheless, it remains an ongoing research area with several unresolved issues and challenges.","abstract_has_math":false,"creators":["Braga, Marco"],"institution":"Politecnico di Torino","degree_name":null,"degree_level":null,"degree_discipline":null,"degree_department":null,"school":null,"contributors":[],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2026,"date_issued":"2026","date_published":"2026","updated_at":"2026-07-24T03:50:54Z","subjects":["Settore INFO-01/A - Informatica"],"languages":["eng"],"rights":["info:eu-repo/semantics/openAccess","license:Creative commons","license uri:http://creativecommons.org/licenses/by-nc-nd/4.0/"],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"https://hdl.handle.net/11583/3013101","outbound_label":"Handle","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Braga, Marco"]},{"key":"dc:creator","label":"Author","values":["Braga, Marco"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2026"]},{"key":"dc:publisher","label":"Institution","values":["Politecnico di Torino","country:Italy"]},{"key":"dc:relation","label":"Dc Relation","values":["numberofpages:262"]},{"key":"dc:type","label":"Dc Type","values":["info:eu-repo/semantics/doctoralThesis"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Settore INFO-01/A - Informatica"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language","label":"Dc Language","values":["eng"]},{"key":"dc:rights","label":"Dc Rights","values":["info:eu-repo/semantics/openAccess","license:Creative commons","license uri:http://creativecommons.org/licenses/by-nc-nd/4.0/"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["https://hdl.handle.net/11583/3013101"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["The rapid growth of Large Language Models (LLMs) has significantly improved performance across a wide range of Natural Language Processing (NLP) tasks, including Information Retrieval (IR). Despite their strong generalisation capabilities, LLMs still require domain- and task-specific fine-tuning to achieve competitive performance in highly specialised scenarios. LLMs exhibit some generalisation abilities, though these are not uniformly reliable across tasks and domains. In particular, adapting these models to downstream domains and tasks has become challenging as full fine-tuning is computationally expensive, memory-intensive and difficult to scale across multiple domains and tasks. Over the past few years, substantial research has been made into efficient fine-tuning of LLMs, resulting in various proposed approaches. Nevertheless, it remains an ongoing research area with several unresolved issues and challenges."]},{"key":"dc:title","label":"Title","values":["Efficient Adaptation of Large Language Models in Natural Language Processing"]}]}],"canonical_facts":{"dc:contributor":["Braga, Marco"],"dc:creator":["Braga, Marco"],"dc:date":["2026"],"dc:description":["The rapid growth of Large Language Models (LLMs) has significantly improved performance across a wide range of Natural Language Processing (NLP) tasks, including Information Retrieval (IR). Despite their strong generalisation capabilities, LLMs still require domain- and task-specific fine-tuning to achieve competitive performance in highly specialised scenarios. LLMs exhibit some generalisation abilities, though these are not uniformly reliable across tasks and domains. In particular, adapting these models to downstream domains and tasks has become challenging as full fine-tuning is computationally expensive, memory-intensive and difficult to scale across multiple domains and tasks. Over the past few years, substantial research has been made into efficient fine-tuning of LLMs, resulting in various proposed approaches. Nevertheless, it remains an ongoing research area with several unresolved issues and challenges."],"dc:identifier":["https://hdl.handle.net/11583/3013101"],"dc:language":["eng"],"dc:publisher":["Politecnico di Torino","country:Italy"],"dc:relation":["numberofpages:262"],"dc:rights":["info:eu-repo/semantics/openAccess","license:Creative commons","license uri:http://creativecommons.org/licenses/by-nc-nd/4.0/"],"dc:subject":["Settore INFO-01/A - Informatica"],"dc:title":["Efficient Adaptation of Large Language Models in Natural Language Processing"],"dc:type":["info:eu-repo/semantics/doctoralThesis"]},"updated_at":"2026-07-24T03:50:54Z"}