There are not enough established benchmarks for the task fo speech summarization. Creating new benchmarks demands human annotation, as LLMs could embed systemic errors and bias into datasets. We test ten annotation workflows varying input modality (audio, transcript, or both) and the inclusion of editing (self or peer-editing) to investigate potential quality tradeoffs from using human annotators to summarize audio. We compare human audio-based summaries to human transcript-based summaries to track the impact of the different information modalities on summary quality. We also compare the human outputs against four LLM benchmarks (three text, one audio) to examine whether human-written summaries are less informative than highly fluent automated outputs. We find that audio-based summaries are less informative and more compressed than transcript summaries. However, iterative peer-editing with audio mitigates this difference, enabling audio-based summaries to be as informative as their transcript counterparts and LLM summaries. These findings validate iterative peer-editing among human annotators for the creation of benchmarks informed by both lexical and prosodic information. This enables crucial dataset collection even in setting where transcripts are unavailable.

Although functional specialization in the brain - a phenomenon where different regions process different types of information - is well documented, we still lack precise mathematical methods with which to measure it. This work proposes a technique to quantify how brain regions respond to distinct categories of information. Using a topic encoding model, we identify brain regions that respond strongly to specific semantic categories while responding minimally to all others. We then use a language model to characterize the common themes across each region’s preferred categories. Our technique successfully identifies previously known functionally selective regions and reveals consistent patterns across subjects while also highlighting new areas of high specialization worthy of further study.

This paper presents JHU’s submission to the AmericasNLP shared task on the creation of educational materials for Indigenous languages. The task involves transforming a base sentence given one or more tags that correspond to grammatical features, such as negation or tense. The task also spans four languages: Bribri, Maya, Guaraní, and Nahuatl. We experiment with augmenting prompts to large language models with different information, chain of thought prompting, ensembling large language models by majority voting, and training a pointer-generator network. Our System 1, an ensemble of large language models, achieves the best performance on Maya and Guaraní, building upon the previous successes in leveraging large language models for this task and highlighting the effectiveness of ensembling large language models.