Summary of Speechworthy Instruction-tuned Language Models, by Hyundong Cho et al.
Speechworthy Instruction-tuned Language Models
by Hyundong Cho, Nicolaas Jedema, Leonardo F.R. Ribeiro, Karishma Sharma, Pedro Szekely, Alessandro Moschitti, Ruben Janssen, Jonathan May
First submitted to arxiv on: 23 Sep 2024
Categories
- Main: Artificial Intelligence (cs.AI)
- Secondary: None
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 proposed paper explores ways to align language models with the speech domain by developing prompting strategies and preference learning methods using a novel dataset of 20K samples. The approach is based on radio-industry best practices, which involve generating prompts that induce varying dimensions of speech-suitability. The results show that both prompting and preference learning increase the speech-suitability of popular instruction-tuned LLMs, with combining them achieving the best win rates in head-to-head comparison. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The researchers want to make language models better at understanding and generating speech. They try two new ways: giving models special instructions (prompts) that are based on what works well in radio broadcasting, and teaching models what sounds good or bad by showing them lots of examples of different kinds of speech. The results show that both methods can help make the models do a better job with speech-related tasks. |
Keywords
» Artificial intelligence » Prompting
