Research - Papers
Explore a selection of our published work on a variety of key research challenges in AI.
What Makes Instruction Learning Hard? An Investigation and a New Challenge in a Synthetic Environment
The instruction learning paradigm—where a model learns to perform new tasks from task descriptions alone—has become popular in general-purpose model research. The capabilities of large transformer…
Learn to Explain: Multimodal Reasoning via Thought Chains for Science Question Answering
When answering a question, humans utilize the information available across different modalities to synthesize a consistent and complete chain of thought (CoT). This process is normally a black box…
One Venue, Two Conferences: The Separation of Chinese and American Citation Networks
At NeurIPS, American and Chinese institutions cite papers from each other’s regions substantially less than they cite endogamously. We build a citation graph to quantify this divide, compare it to…
Breakpoint Transformers for Modeling and Tracking Intermediate Beliefs
Can we teach natural language understanding models to track their beliefs through intermediate points in text? We propose a representation learning framework called breakpoint modeling that allows…
Learning to Decompose: Hypothetical Question Decomposition Based on Comparable Texts
Explicit decomposition modeling, which involves breaking down complex tasks into more straightforward and often more interpretable sub-tasks, has long been a central theme in developing robust and…
Just-DREAM-about-it: Figurative Language Understanding with DREAM-FLUTE
Figurative language (e.g., “he flew like the wind”) is challenging to understand, as it is hard to tell what implicit information is being conveyed from the surface form alone. We hypothesize that…
Dyna-bAbI: unlocking bAbI’s potential with dynamic synthetic benchmarking
While neural language models often perform surprisingly well on natural language understanding (NLU) tasks, their strengths and limitations remain poorly understood. Controlled synthetic tasks are…
Learning to Repair: Repairing model output errors after deployment using a dynamic memory of feedback
Large language models (LMs), while power-ful, are not immune to mistakes, but can be difficult to retrain. Our goal is for an LM to continue to improve after deployment, without retraining, using…
DeepA2: A Modular Framework for Deep Argument Analysis with Pretrained Neural Text2Text Language Models
In this paper, we present and implement a multi-dimensional, modular framework for performing deep argument analysis (DeepA2) using current pre-trained language models (PTLMs). ArgumentAnalyst – a…
Retrieval Data Augmentation Informed by Downstream Question Answering Performance
Training retrieval models to fetch contexts for Question Answering (QA) over large corpora requires labeling relevant passages in those corpora. Since obtaining exhaustive manual annotations of all…