Are Checklists Really Useful for Automatic Evaluation of Generative Tasks?
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866908497054007296 |
|---|---|
| author | Furuhashi, Momoka Nakayama, Kouta Kodama, Takashi Sugawara, Saku |
| author_facet | Furuhashi, Momoka Nakayama, Kouta Kodama, Takashi Sugawara, Saku |
| contents | Automatic evaluation of generative tasks using large language models faces challenges due to ambiguous criteria. Although automatic checklist generation is a potentially promising approach, its usefulness remains underexplored. We investigate whether checklists should be used for all questions or selectively, generate them using six methods, evaluate their effectiveness across eight model sizes, and identify checklist items that correlate with human evaluations. Through experiments on pairwise comparison and direct scoring tasks, we find that selective checklist use tends to improve evaluation performance in pairwise settings, while its benefits are less consistent in direct scoring. Our analysis also shows that even checklist items with low correlation to human scores often reflect human-written criteria, indicating potential inconsistencies in human evaluation. These findings highlight the need to more clearly define objective evaluation criteria to guide both human and automatic evaluations. \footnote{Our code is available at~https://github.com/momo0817/checklist-effectiveness-study |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_15218 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Are Checklists Really Useful for Automatic Evaluation of Generative Tasks? Furuhashi, Momoka Nakayama, Kouta Kodama, Takashi Sugawara, Saku Computation and Language Automatic evaluation of generative tasks using large language models faces challenges due to ambiguous criteria. Although automatic checklist generation is a potentially promising approach, its usefulness remains underexplored. We investigate whether checklists should be used for all questions or selectively, generate them using six methods, evaluate their effectiveness across eight model sizes, and identify checklist items that correlate with human evaluations. Through experiments on pairwise comparison and direct scoring tasks, we find that selective checklist use tends to improve evaluation performance in pairwise settings, while its benefits are less consistent in direct scoring. Our analysis also shows that even checklist items with low correlation to human scores often reflect human-written criteria, indicating potential inconsistencies in human evaluation. These findings highlight the need to more clearly define objective evaluation criteria to guide both human and automatic evaluations. \footnote{Our code is available at~https://github.com/momo0817/checklist-effectiveness-study |
| title | Are Checklists Really Useful for Automatic Evaluation of Generative Tasks? |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2508.15218 |