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

BotPercent: Estimating Twitter Bot Populations from Groups to Crowds

Zhaoxuan TanShangbin FengMelanie SclarYulia Tsvetkov
2023
arXiv

Twitter bot detection has become increasingly important in combating misinformation, identifying malicious online campaigns, and protecting the integrity of social media discourse. While existing… 

Specializing Smaller Language Models towards Multi-Step Reasoning

Yao FuHao PengLitu OuTushar Khot
2023
ICML

The surprising ability of Large Language Models (LLMs) to perform well on complex reasoning with only few-shot chain-of-thought prompts is believed to emerge only in very large-scale models (100+… 

Do Embodied Agents Dream of Pixelated Sheep?: Embodied Decision Making using Language Guided World Modelling

Kolby NottinghamPrithviraj AmmanabroluAlane SuhrRoy Fox
2023
arXiv

Reinforcement learning (RL) agents typically learn tabula rasa, without prior knowledge of the world, which makes learning complex tasks with sparse rewards difficult. If initialized with knowledge… 

The Semantic Scholar Open Data Platform

Rodney Michael KinneyChloe AnastasiadesRussell AuthurDaniel S. Weld
2023
arXiv

The volume of scientific output is creating an urgent need for automated tools to help scientists keep up with developments in their field. Semantic Scholar (S2) is an open data platform and website… 

Does progress on ImageNet transfer to real-world datasets?

Alexander W. FangSimon KornblithLudwig Schmidt
2023
arXiv

Does progress on ImageNet transfer to real-world datasets? We investigate this question by evaluating ImageNet pre-trained models with varying accuracy (57% - 83%) on six practical image… 

ProKnow: Process knowledge for safety constrained and explainable question generation for mental health diagnostic assistance

Kaushik RoyManas GaurMisagh SoltaniAmit P. Sheth
2023
Frontiers in Big Data

Virtual Mental Health Assistants (VMHAs) are utilized in health care to provide patient services such as counseling and suggestive care. They are not used for patient diagnostic assistance because… 

MAUVE Scores for Generative Models: Theory and Practice

Krishna PillutlaLang LiuJohn ThickstunZ. Harchaoui
2022
arXiv

Generative AI has matured to a point where large-scale models can generate text that seems indistinguishable from human-written text and remarkably photorealistic images. Automatically measuring how… 

I Cast Detect Thoughts: Learning to Converse and Guide with Intents and Theory-of-Mind in Dungeons and Dragons

Pei ZhouAndrew ZhuJennifer HuPrithviraj Ammanabrolu
2022
arXiv

We propose a novel task, G4C, to study teacher-student natural language interactions in a goal-driven and grounded environment. Dungeons and Dragons (D&D), a role-playing game, provides an ideal… 

Exploring the Challenges of Open Domain Multi-Document Summarization

John GiorgiLuca SoldainiBo WangArman Cohan
2022
arXiv

Multi-document summarization (MDS) has traditionally been studied assuming a set of ground-truth topic-related input documents is provided. In practice, the input document set is unlikely to be… 

I2D2: Inductive Knowledge Distillation with NeuroLogic and Self-Imitation

Chandra BhagavatulaJena D. HwangDoug DowneyYejin Choi
2022
ACL

Pre-trained language models, despite their rapid advancements powered by scale, still fall short of robust commonsense capabilities. And yet, scale appears to be the win-ning recipe; after all, the…