Small But Funny: A Feedback-Driven Approach to Humor Distillation

Sahithya Ravi, Patrick Huber, Akshat Shrivastava, Vered Shwartz, Arash Einolghozati


Abstract
The emergence of Large Language Models (LLMs) has brought to light promising language generation capabilities, particularly in performing tasks like complex reasoning and creative writing. Consequently, distillation through imitation of teacher responses has emerged as a popular technique to transfer knowledge from LLMs to more accessible, Small Language Models (SLMs). While this works well for simpler tasks, there is a substantial performance gap on tasks requiring intricate language comprehension and creativity, such as humor generation. We hypothesize that this gap may stem from the fact that creative tasks might be hard to learn by imitation alone and explore whether an approach, involving supplementary guidance from the teacher, could yield higher performance. To address this, we study the effect of assigning a dual role to the LLM - as a “teacher” generating data, as well as a “critic” evaluating the student’s performance. Our experiments on humor generation reveal that the incorporation of feedback significantly narrows the performance gap between SLMs and their larger counterparts compared to merely relying on imitation. As a result, our research highlights the potential of using feedback as an additional dimension to data when transferring complex language abilities via distillation.
Anthology ID:
2024.acl-long.706
Volume:
Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Month:
August
Year:
2024
Address:
Bangkok, Thailand
Editors:
Lun-Wei Ku, Andre Martins, Vivek Srikumar
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
13078–13090
Language:
URL:
https://aclanthology.org/2024.acl-long.706
DOI:
10.18653/v1/2024.acl-long.706
Bibkey:
Cite (ACL):
Sahithya Ravi, Patrick Huber, Akshat Shrivastava, Vered Shwartz, and Arash Einolghozati. 2024. Small But Funny: A Feedback-Driven Approach to Humor Distillation. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 13078–13090, Bangkok, Thailand. Association for Computational Linguistics.
Cite (Informal):
Small But Funny: A Feedback-Driven Approach to Humor Distillation (Ravi et al., ACL 2024)
Copy Citation:
PDF:
https://preview.aclanthology.org/add_acl24_videos/2024.acl-long.706.pdf
Video:
 https://preview.aclanthology.org/add_acl24_videos/2024.acl-long.706.mp4