Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2508.18709 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915540616871936 |
|---|---|
| author | Le, Duy Ziti, Kent Girard-Sun, Evan Bouhaya, Bakr O'Brien, Sean Sharma, Vasu Zhu, Kevin |
| author_facet | Le, Duy Ziti, Kent Girard-Sun, Evan Bouhaya, Bakr O'Brien, Sean Sharma, Vasu Zhu, Kevin |
| contents | Language models are increasingly tested on multilingual creativity, demanding culturally grounded, abstract generations. Standard prompting methods often produce repetitive or shallow outputs. We introduce Adaptive Originality Filtering (AOF), a prompting strategy that enforces novelty and cultural fidelity via semantic rejection. To assess quality, we propose RiddleScore, a metric combining novelty, diversity, fluency, and answer alignment. AOF improves Distinct-2 (0.915 in Japanese), reduces Self-BLEU (0.177), and raises RiddleScore (up to +57.1% in Arabic). Human evaluations confirm fluency, creativity, and cultural fit gains. However, improvements vary: Arabic shows greater RiddleScore gains than Distinct-2; Japanese sees similar changes. Though focused on riddles, our method may apply to broader creative tasks. Overall, semantic filtering with composite evaluation offers a lightweight path to culturally rich generation without fine-tuning. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_18709 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Adaptive Originality Filtering: Rejection Based Prompting and RiddleScore for Culturally Grounded Multilingual Riddle Generation Le, Duy Ziti, Kent Girard-Sun, Evan Bouhaya, Bakr O'Brien, Sean Sharma, Vasu Zhu, Kevin Computation and Language Language models are increasingly tested on multilingual creativity, demanding culturally grounded, abstract generations. Standard prompting methods often produce repetitive or shallow outputs. We introduce Adaptive Originality Filtering (AOF), a prompting strategy that enforces novelty and cultural fidelity via semantic rejection. To assess quality, we propose RiddleScore, a metric combining novelty, diversity, fluency, and answer alignment. AOF improves Distinct-2 (0.915 in Japanese), reduces Self-BLEU (0.177), and raises RiddleScore (up to +57.1% in Arabic). Human evaluations confirm fluency, creativity, and cultural fit gains. However, improvements vary: Arabic shows greater RiddleScore gains than Distinct-2; Japanese sees similar changes. Though focused on riddles, our method may apply to broader creative tasks. Overall, semantic filtering with composite evaluation offers a lightweight path to culturally rich generation without fine-tuning. |
| title | Adaptive Originality Filtering: Rejection Based Prompting and RiddleScore for Culturally Grounded Multilingual Riddle Generation |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2508.18709 |