Research - Papers
Explore a selection of our published work on a variety of key research challenges in AI.
Teaching Broad Reasoning Skills via Decomposition-Guided Contexts
Question-answering datasets require a broad set of reasoning skills. We show how to use question decompositions to teach language models these broad reasoning skills in a robust fashion.…
Towards Teachable Reasoning Systems: Using a Dynamic Memory of User Feedback for Continual System Improvement
Our goal is a teachable reasoning system for question-answering (QA), where a user can interact with faithful answer explanations, and correct its errors so that the system improves over time. Our…
Twist Decoding: Diverse Generators Guide Each Other
Natural language generation technology has recently seen remarkable progress with large-scale training, and many natural language applications are now built upon a wide range of generation models.…
UnifiedSKG: Unifying and Multi-Tasking Structured Knowledge Grounding with Text-to-Text Language Models
Structured knowledge grounding (SKG) leverages structured knowledge to complete user requests, such as semantic parsing over databases and question answering over knowledge bases. Since the inputs…
Unsupervised Learning of Hierarchical Conversation Structure
Human conversations can evolve in many different ways, creating challenges for automatic understanding and summarization. Goal-oriented conversations often have meaningful sub-dialogue structure,…
WANLI: Worker and AI Collaboration for Natural Language Inference Dataset Creation
A recurring challenge of crowdsourcing NLP datasets at scale is that human writers often rely on repetitive patterns when crafting examples, leading to a lack of linguistic diversity. We introduce a…
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…
Whose Language Counts as High Quality? Measuring Language Ideologies in Text Data Selection
Language models increasingly rely on massive web dumps for diverse text data. However, these sources are rife with undesirable content. As such, resources like Wikipedia, books, and news often…
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…
Ask4Help: Learning to Leverage an Expert for Embodied Tasks
Embodied AI agents continue to become more capable every year with the advent of new models, environments, and benchmarks, but are still far away from being performant and reliable enough to be…