activity
20192026
most citedSparks: Inspiration for Science Writing using Language Models

3 citations · 8 across the 8 of their papers we have counts for

collaborators
Showing cs.CLShow all

6 papers · 1 filter

cs.CL2024

Reading Subtext: Evaluating Large Language Models on Short Story Summarization with Writers

Melanie Subbiah, Sean Zhang, Lydia B. Chilton +1

We evaluate recent Large Language Models (LLMs) on the challenging task of summarizing short stories, which can be lengthy, and include nuanced subtext or scrambled timelines. Impo…

cs.CL2023

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

Yulun Du, Lydia Chilton

Collaborative stories, which are texts created through the collaborative efforts of multiple authors with different writing styles and intentions, pose unique challenges for NLP mo…

cs.CL20223 cited

SafeText: A Benchmark for Exploring Physical Safety in Language Models

Sharon Levy, Emily Allaway, Melanie Subbiah +4

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 typ…

cs.CL2021

Lightweight Decoding Strategies for Increasing Specificity

Katy Ilonka Gero, Chris Kedzie, Savvas Petridis +1

Language models are known to produce vague and generic outputs. We propose two unsupervised decoding strategies based on either word-frequency or point-wise mutual information to i…

cs.CL2021

Hierarchical Summarization for Longform Spoken Dialog

Daniel Li, Thomas Chen, Albert Tung +1

Every day we are surrounded by spoken dialog. This medium delivers rich diverse streams of information auditorily; however, systematically understanding dialog can often be non-tri…

cs.CL2019

Low-Level Linguistic Controls for Style Transfer and Content Preservation

Katy Gero, Chris Kedzie, Jonathan Reeve +1

Despite the success of style transfer in image processing, it has seen limited progress in natural language generation. Part of the problem is that content is not as easily decoupl…