Lydia Chilton — accepted AI-conference papers

2024

STORYSUMM: Evaluating Faithfulness in Story Summarization

Melanie Subbiah, Faisal Ladhak, Akankshya Mishra, Griffin Thomas Adams, Lydia Chilton, Kathleen McKeown

EMNLP 2024main

Human evaluation has been the gold standard for checking faithfulness in abstractive summarization. However, with a challenging source domain like narrative, multiple annotators can agree a summary is faithful, while missing details that are obvious errors only once pointed out. We therefore introdu…

Cited by 5 Source ↗PDF ↗code ↗Scholar ↗

2023

StoryWars: A Dataset and Instruction Tuning Baselines for Collaborative Story Understanding and Generation

Yulun Du, Lydia Chilton

ACL 2023long

Collaborative stories, which are texts created through the collaborative efforts of multiple authors with different writing styles and intentions, pose unique challenges for NLP models. Understanding and generating such stories remains an underexplored area due to the lack of open-domain corpora. To…

Cited by 8 Source ↗PDF ↗code ↗Scholar ↗

2022

SafeText: A Benchmark for Exploring Physical Safety in Language Models

Sharon Levy, Emily Allaway, Melanie Subbiah, Lydia Chilton, Desmond Patton, Kathleen McKeown +1

EMNLP 2022main

Understanding what constitutes safe text is an important issue in natural language processing and can often prevent the deployment of models deemed harmful and unsafe. One such type of safety that has been scarcely studied is commonsense physical safety, i.e. text that is not explicitly violent and…

Cited by 40 Source ↗PDF ↗code ↗Scholar ↗