Research - Papers
Explore a selection of our published work on a variety of key research challenges in AI.
Words as Gatekeepers: Measuring Discipline-specific Terms and Meanings in Scholarly Publications
Scholarly text is often laden with jargon, or specialized language that can facilitate efficient in-group communication within fields but hinder understanding for out-groups. In this work, we…
ARIES: A Corpus of Scientific Paper Edits Made in Response to Peer Reviews
Revising scientific papers based on peer feedback is a challenging task that requires not only deep scientific knowledge and reasoning, but also the ability to recognize the implicit requests in…
Perspective: Large Language Models in Applied Mechanics
Large language models (LLMs), such as ChatGPT and PaLM, are able to perform sophisticated text comprehension and generation tasks with little or no training. Alongside their broader societal…
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…
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…
Learning to Generate Novel Scientific Directions with Contextualized Literature-based Discovery
Literature-Based Discovery (LBD) aims to discover new scientific knowledge by mining papers and generating hypotheses. Standard LBD is limited to predicting pairwise relations between discrete…
TESS: Text-to-Text Self-Conditioned Simplex Diffusion
Diffusion models have emerged as a powerful paradigm for generation, obtaining strong performance in various domains with continuous-valued inputs. Despite the promises of fully non-autoregressive…
Embedding Recycling for Language Models
Training and inference with large neural models is expensive. However, for many application domains, while new tasks and models arise frequently, the underlying doc-uments being modeled remain…
LongEval: Guidelines for Human Evaluation of Faithfulness in Long-form Summarization
While human evaluation remains best practice for accurately judging the faithfulness of automatically-generated summaries, few solutions exist to address the increased difficulty and workload when…