SubData: A Python Library to Collect and Combine Datasets for Evaluating LLM Alignment on Downstream Tasks

Guardat en:
Dades bibliogràfiques
Publicat a:arXiv.org (Dec 21, 2024), p. n/a
Autor principal: Fröhling, Leon
Altres autors: Bernardelle, Pietro, Demartini, Gianluca
Publicat:
Cornell University Library, arXiv.org
Matèries:
Accés en línia:Citation/Abstract
Full text outside of ProQuest
Etiquetes: Afegir etiqueta
Sense etiquetes, Sigues el primer a etiquetar aquest registre!

MARC

LEADER 00000nab a2200000uu 4500
001 3148978562
003 UK-CbPIL
022 |a 2331-8422 
035 |a 3148978562 
045 0 |b d20241221 
100 1 |a Fröhling, Leon 
245 1 |a SubData: A Python Library to Collect and Combine Datasets for Evaluating LLM Alignment on Downstream Tasks 
260 |b Cornell University Library, arXiv.org  |c Dec 21, 2024 
513 |a Working Paper 
520 3 |a With the release of ever more capable large language models (LLMs), researchers in NLP and related disciplines have started to explore the usability of LLMs for a wide variety of different annotation tasks. Very recently, a lot of this attention has shifted to tasks that are subjective in nature. Given that the latest generations of LLMs have digested and encoded extensive knowledge about different human subpopulations and individuals, the hope is that these models can be trained, tuned or prompted to align with a wide range of different human perspectives. While researchers already evaluate the success of this alignment via surveys and tests, there is a lack of resources to evaluate the alignment on what oftentimes matters the most in NLP; the actual downstream tasks. To fill this gap we present SubData, a Python library that offers researchers working on topics related to subjectivity in annotation tasks a convenient way of collecting, combining and using a range of suitable datasets. 
653 |a Datasets 
653 |a Python 
653 |a Alignment 
653 |a Annotations 
653 |a Large language models 
700 1 |a Bernardelle, Pietro 
700 1 |a Demartini, Gianluca 
773 0 |t arXiv.org  |g (Dec 21, 2024), p. n/a 
786 0 |d ProQuest  |t Engineering Database 
856 4 1 |3 Citation/Abstract  |u https://www.proquest.com/docview/3148978562/abstract/embedded/6A8EOT78XXH2IG52?source=fedsrch 
856 4 0 |3 Full text outside of ProQuest  |u http://arxiv.org/abs/2412.16783