Research - Papers
Explore a selection of our published work on a variety of key research challenges in AI.
Modular Transformers: Compressing Transformers into Modularized Layers for Flexible Efficient Inference
Pre-trained Transformer models like T5 and BART have advanced the state of the art on a wide range of text generation tasks. Compressing these models into smaller ones has become critically…
EXCALIBUR: Encouraging and Evaluating Embodied Exploration
Experience precedes understanding. Humans constantly explore and learn about their environment out of curiosity, gather information, and update their models of the world. On the other hand,…
Minding Language Models' (Lack of) Theory of Mind: A Plug-and-Play Multi-Character Belief Tracker
Theory of Mind (ToM)$\unicode{x2014}$the ability to reason about the mental states of other people$\unicode{x2014}$is a key element of our social intelligence. Yet, despite their ever more…
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.…
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…
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…
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…
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…
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…