Skip to main content ->
Ai2

Research - Papers

Explore a selection of our published work on a variety of key research challenges in AI.

Filter papers

Beyond Summarization: Designing AI Support for Real-World Expository Writing Tasks

Zejiang ShenTal AugustPao SiangliulueDavid Sontag
2023
The Second Workshop on Intelligent and Interactive Writing Assistants @ ACM SIGCHI 2023

Large language models have introduced exciting new opportunities and challenges in designing and developing new AI-assisted writing support tools. Recent work has shown that leveraging this new… 

When Learning Is Out of Reach, Reset: Generalization in Autonomous Visuomotor Reinforcement Learning

Zichen ZhangLuca Weihs
2023
CVPR • Embodied AI workshop

Episodic training, where an agent's environment is reset to some initial condition after every success or failure, is the de facto standard when training embodied reinforcement learning (RL) agents.… 

Queer In AI: A Case Study in Community-Led Participatory AI

Organizers Of Queer in AIAnaelia OvalleArjun SubramonianLuke Stark
2023
FAccT

We present Queer in AI as a case study for community-led participatory design in AI. We examine how participatory design and intersectional tenets started and shaped this community's programs over… 

Scim: Intelligent Faceted Highlights for Interactive, Multi-Pass Skimming of Scientific Papers

Raymond FokHita KambhamettuLuca SoldainiDaniel S. Weld
2023
IUI

Researchers are expected to keep up with an immense literature, yet often find it prohibitively time-consuming to do so. This paper ex-plores how intelligent agents can help scaffold in-situ… 

The Semantic Reader Project: Augmenting Scholarly Documents through AI-Powered Interactive Reading Interfaces

Kyle LoJoseph Chee ChangAndrew HeadDaniel S. Weld
2023
arXiv

Scholarly publications are key to the transfer of knowledge from scholars to others. However, research papers are information-dense, and as the volume of the scientific literature grows, the need… 

CHAMPAGNE: Learning Real-world Conversation from Large-Scale Web Videos

Seungju HanJack HesselNouha DziriYoungjae Yu
2023
arXiv.org

Visual information is central to conversation: body gestures and facial expressions, for example, contribute to meaning that transcends words alone. To date, however, most neural conversational… 

Clever Hans or Neural Theory of Mind? Stress Testing Social Reasoning in Large Language Models

Natalie ShapiraMosh LevyS. AlaviVered Shwartz
2023
EACL

The escalating debate on AI’s capabilities warrants developing reliable metrics to assess machine “intelligence.” Recently, many anecdotal examples were used to suggest that newer Large Language… 

Comparing Sentence-Level Suggestions to Message-Level Suggestions in AI-Mediated Communication

Liye FuBenjamin NewmanMaurice JakeschSarah Kreps
2023
International Conference on Human Factors in Computing Systems

Traditionally, writing assistance systems have focused on short or even single-word suggestions. Recently, large language models like GPT-3 have made it possible to generate significantly longer… 

The Parallelism Tradeoff: Limitations of Log-Precision Transformers

William MerrillAshish Sabharwal
2023
TACL • ACL

Abstract Despite their omnipresence in modern NLP, characterizing the computational power of transformer neural nets remains an interesting open question. We prove that transformers whose arithmetic… 

AdapterSoup: Weight Averaging to Improve Generalization of Pretrained Language Models

Alexandra ChronopoulouMatthew E. PetersAlexander M. FraserJesse Dodge
2023
Findings of EACL 2023

Pretrained language models (PLMs) are trained on massive corpora, but often need to specialize to specific domains. A parameter-efficient adaptation method suggests training an adapter for each…