Research - Papers
Explore a selection of our published work on a variety of key research challenges in AI.
Z-ICL: Zero-Shot In-Context Learning with Pseudo-Demonstrations
Although large language models can be prompted for both zero- and few-shot learning, performance drops significantly when no demonstrations are available. In this paper, we introduce Z-ICL, a new…
Improving the reliability of ML-corrected climate models with novelty detection
The use of machine learning (ML) for the online correction of coarse-resolution atmospheric models has proven effective in reducing biases in near-surface temperature and precipitation rate.…
Decomposing Complex Queries for Tip-of-the-tongue Retrieval
When re-finding items, users who forget or are uncertain about identifying details often rely on creative strategies for expressing their information needs -- complex queries that describe content…
A Controllable QA-based Framework for Decontextualization
Many real-world applications require surfacing extracted snippets to users, whether motivated by assistive tools for literature surveys or document cross-referencing, or needs to mitigate and…
Complex Mathematical Symbol Definition Structures: A Dataset and Model for Coordination Resolution in Definition Extraction
Mathematical symbol definition extraction is important for improving scholarly reading interfaces and scholarly information extraction (IE). However, the task poses several challenges: math symbols…
Anthropomorphization of AI: Opportunities and Risks
Anthropomorphization is the tendency to attribute human-like traits to non-human entities. It is prevalent in many social contexts -- children anthropomorphize toys, adults do so with brands, and it…
CSTS: Conditional Semantic Textual Similarity
Semantic textual similarity (STS) has been a cornerstone task in NLP that measures the degree of similarity between a pair of sentences, with applications in information retrieval, question…
Aligning Language Models to User Opinions
An important aspect of developing LLMs that interact with humans is to align models' behavior to their users. It is possible to prompt an LLM into behaving as a certain persona, especially a user…
OpenPI2.0: An Improved Dataset for Entity Tracking in Texts
Representing texts as information about entities has long been deemed effective in event reasoning. We propose OpenPI2.0, an improved dataset for tracking entity states in procedural texts.…
Just CHOP: Embarrassingly Simple LLM Compression
Large language models (LLMs) enable unparalleled few- and zero-shot reasoning capabilities but at a high computational footprint. A growing assortment of methods for compression promises to reduce…