Speechworthy Instruction-tuned Language Models

Hyundong Justin Cho1, Nicolaas Jedema2, Leonardo F.R. Ribeiro2, Karishma Sharma2, Pedro Szekely2, Alessandro Moschitti2, Ruben Janssen2, Jonathan May1

1        2 
Paper Code & Data (TBD) arXiv

Speechworthiness

Speechworthy Overview

Current instruction-tuned language models are exclusively trained with textual preference data and thus are often not aligned with the unique requirements of other modalities, such as speech. To better align language models with the speech domain, we explore (i) prompting strategies grounded in radio-industry best practices and (ii) preference learning using a novel speech-based preference data of 20K samples, generated with a wide spectrum of prompts that induce varying dimensions of speech-suitability and labeled by annotators who listen to response pairs. Both human and automatic evaluation show that both prompting and preference learning increase the speech-suitability of popular instruction-tuned LLMs. Interestingly, we find that prompting and preference learning can be additive; combining them achieves the best win rates in head-to-head comparison, resulting in responses that are preferred or tied to the base model in 76.2% of comparisons on average. Lastly, we share lexical, syntactical, and qualitative analyses to showcase how each method contributes to improving the speech-suitability of generated responses.

BibTeX

@inproceedings{cho-etal-2024-speechworthy,
        title = "Speechworthy Instruction-tuned Language Models",
        author = "Cho, Hyundong Justin  and
          Jedema, Nicolaas Paul  and
          Ribeiro, Leonardo F. R.  and
          Sharma, Karishma  and
          Szekely, Pedro  and
          Moschitti, Alessandro  and
          Janssen, Ruben  and
          May, Jonathan",
        editor = "Al-Onaizan, Yaser  and
          Bansal, Mohit  and
          Chen, Yun-Nung",
        booktitle = "Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing",
        month = nov,
        year = "2024",
        address = "Miami, Florida, USA",
        publisher = "Association for Computational Linguistics",
        url = "https://aclanthology.org/2024.emnlp-main.595/",
        doi = "10.18653/v1/2024.emnlp-main.595",
        pages = "10652--10670",
        abstract = "Current instruction-tuned language models are exclusively trained with textual preference data and thus may not be aligned to the unique requirements of other modalities, such as speech. To better align language models with the speech domain, we explore i) prompting strategies based on radio-industry best practices and ii) preference learning using a novel speech-based preference data of 20K samples collected by annotators who listen to response pairs. Both human and automatic evaluation show that both prompting and preference learning increase the speech-suitability of popular instruction tuned LLMs. More interestingly, we show that these methods are additive; combining them achieves the best win rates in head-to-head comparison, resulting in responses that are preferred or tied to the base model in 76.2{\%} of comparisons on average. Lastly, we share lexical, syntactical, and qualitative analyses that elicit how our studied methods differ with baselines in generating more speech-suitable responses."
    }