Summary of Small but Funny: a Feedback-driven Approach to Humor Distillation, by Sahithya Ravi et al.
Small But Funny: A Feedback-Driven Approach to Humor Distillation
by Sahithya Ravi, Patrick Huber, Akshat Shrivastava, Aditya Sagar, Ahmed Aly, Vered Shwartz, Arash Einolghozati
First submitted to arxiv on: 28 Feb 2024
Categories
- Main: Computation and Language (cs.CL)
- Secondary: Artificial Intelligence (cs.AI)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The emergence of Large Language Models (LLMs) has brought forth promising capabilities in tasks like complex reasoning and creative writing. A popular technique to transfer knowledge from LLMs to more accessible, Small Language Models (SLMs), is distillation through imitation of teacher responses. However, there exists a significant performance gap on tasks requiring intricate language comprehension and creativity, such as humor generation. This paper hypothesizes that the gap may stem from creative tasks being hard to learn by imitation alone and explores whether an approach involving supplementary guidance from the teacher could yield higher performance. The study investigates 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. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper is about using special language models called Large Language Models (LLMs) to help smaller language models, called Small Language Models (SLMs), do tasks like writing humor. The LLM can teach the SLM by generating data for it to learn from and then evaluating its performance. This approach can close the gap between what the SLM can do and what the LLM can do. |
Keywords
» Artificial intelligence » Distillation
