Research - Papers
Explore a selection of our published work on a variety of key research challenges in AI.
NaturalAdversaries: Can Naturalistic Adversaries Be as Effective as Artificial Adversaries?
While a substantial body of prior work has explored adversarial example generation for natural language understanding tasks, these examples are often unrealistic and diverge from the real-world data…
Quantifying the narrative flow of imagined versus autobiographical stories.
Lifelong experiences and learned knowledge lead to shared expectations about how common situations tend to unfold. Such knowledge of narrative event flow enables people to weave together a story.…
Generating Sequences by Learning to Self-Correct
Sequence generation applications require satisfying semantic constraints, such as ensuring that programs are correct, using certain keywords, or avoiding undesir-able content. Language models,…
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…
Referee: Reference-Free Sentence Summarization with Sharper Controllability through Symbolic Knowledge Distillation
We present Referee, a novel framework for sentence summarization that can be trained reference-free (i.e., requiring no gold summaries for supervision), while allowing direct control for compression…
Neural Theory-of-Mind? On the Limits of Social Intelligence in Large LMs
Social intelligence and Theory of Mind (T O M), i.e., the ability to reason about the different mental states, intents, and reactions of all people involved, allow humans to effectively navigate and…
The Abduction of Sherlock Holmes: A Dataset for Visual Abductive Reasoning
Humans have remarkable capacity to reason abductively and hypothesize about what lies beyond the literal content of an image. By identifying concrete visual clues scattered throughout a scene, we…
NeuroCounterfactuals: Beyond Minimal-Edit Counterfactuals for Richer Data Augmentation
While counterfactual data augmentation offers a promising step towards robust generalization in natural language processing, producing a set of counterfactuals that offer valuable inductive bias for…
Rainier: Reinforced Knowledge Introspector for Commonsense Question Answering
Knowledge underpins reasoning. Recent research demonstrates that when relevant knowledge is provided as additional context to commonsense question answering (QA), it can substantially enhance the…
REV: Information-Theoretic Evaluation of Free-Text Rationales
information. Future work might explore evaluation that penalizes rationales which support incorrect predictions, thus bridging together predictive performance with interpretability metrics.