575 citations
- University of WashingtonUS32 papers
- Carnegie Mellon UniversityUS21 papers
- Allen Institute for Brain ScienceUS16 papers
- Allen Institute for Artificial IntelligenceUS11 papers
- Stanford UniversityUS7 papers
- Johns Hopkins UniversityUS5 papers
- Massachusetts Institute of TechnologyUS5 papers
- California Institute of TechnologyUS4 papers
- Google (United States)US4 papers
- Harvard UniversityUS4 papers
- University of TorontoCA4 papers
- Cold Spring Harbor LaboratoryUS3 papers
15 papers · 1 filter
Reasoning Up the Instruction Ladder for Controllable Language Models
Zishuo Zheng, Vidhisha Balachandran, Chan Young Park +2
As large language model (LLM) based systems take on high-stakes roles in real-world decision-making, they must reconcile competing instructions from multiple sources within a singl…
Event Causality Identification with Synthetic Control
Haoyu Wang, Fengze Liu, Jiayao Zhang +2
Event causality identification (ECI), a process that extracts causal relations between events from text, is crucial for distinguishing causation from correlation. Traditional appro…
Scalable Data Ablation Approximations for Language Models through Modular Training and Merging
Clara Na, Ian Magnusson, Ananya Harsh Jha +4
Training data compositions for Large Language Models (LLMs) can significantly affect their downstream performance. However, a thorough data ablation study exploring large sets of c…
On the Evaluation of Machine-Generated Reports
James Mayfield, Eugene Yang, Dawn Lawrie +10
Large Language Models (LLMs) have enabled new ways to satisfy information needs. Although great strides have been made in applying them to settings like document ranking and short-…
Riveter: Measuring Power and Social Dynamics Between Entities
Maria Antoniak, Anjalie Field, Jimin Mun +3
Riveter provides a complete easy-to-use pipeline for analyzing verb connotations associated with entities in text corpora. We prepopulate the package with connotation frames of sen…
Energy and Carbon Considerations of Fine-Tuning BERT
Xiaorong Wang, Clara Na, Emma Strubell +2
Despite the popularity of the `pre-train then fine-tune' paradigm in the NLP community, existing work quantifying energy costs and associated carbon emissions has largely focused o…