Paired Completion: Flexible Quantification of Issue-framing at Scale with LLMs
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866916791237738496 |
|---|---|
| author | Angus, Simon D O'Neill, Lachlan |
| author_facet | Angus, Simon D O'Neill, Lachlan |
| contents | Detecting issue framing in text - how different perspectives approach the same topic - is valuable for social science and policy analysis, yet challenging for automated methods due to subtle linguistic differences. We introduce `paired completion', a novel approach using LLM next-token log probabilities to detect contrasting frames using minimal examples. Through extensive evaluation across synthetic datasets and a human-labeled corpus, we demonstrate that paired completion is a cost-efficient, low-bias alternative to both prompt-based and embedding-based methods, offering a scalable solution for analyzing issue framing in large text collections, especially suited to low-resource settings. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_09742 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Paired Completion: Flexible Quantification of Issue-framing at Scale with LLMs Angus, Simon D O'Neill, Lachlan Computation and Language Artificial Intelligence General Economics Economics I.2.7 Detecting issue framing in text - how different perspectives approach the same topic - is valuable for social science and policy analysis, yet challenging for automated methods due to subtle linguistic differences. We introduce `paired completion', a novel approach using LLM next-token log probabilities to detect contrasting frames using minimal examples. Through extensive evaluation across synthetic datasets and a human-labeled corpus, we demonstrate that paired completion is a cost-efficient, low-bias alternative to both prompt-based and embedding-based methods, offering a scalable solution for analyzing issue framing in large text collections, especially suited to low-resource settings. |
| title | Paired Completion: Flexible Quantification of Issue-framing at Scale with LLMs |
| topic | Computation and Language Artificial Intelligence General Economics Economics I.2.7 |
| url | https://arxiv.org/abs/2408.09742 |