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

Impact of Warmer Sea Surface Temperature on the Global Pattern of Intense Convection: Insights From a Global Storm Resolving Model

K. ChengL. HarrisC. BrethertonS. Fueglistaler
2022
Geophysical Research Letters

Intense convection (updrafts exceeding 10 m s−1) plays an essential role in severe weather and Earth's energy balance. Despite its importance, how the global pattern of intense convection changes in… 

Linear Adversarial Concept Erasure

Shauli RavfogelMichael TwitonYoav GoldbergRyan Cotterell
2022
ICML

We formulate the problem of identifying and erasing a linear subspace that corresponds to a given concept, in order to prevent linear predictors from recovering the concept. We model this problem as… 

Dyna-bAbI: unlocking bAbI’s potential with dynamic synthetic benchmarking

Ronen TamariKyle RichardsonAviad Sar-ShalomDafna Shahaf
2022
SEM

While neural language models often perform surprisingly well on natural language understanding (NLU) tasks, their strengths and limitations remain poorly understood. Controlled synthetic tasks are… 

Learning to Repair: Repairing model output errors after deployment using a dynamic memory of feedback

Niket TandonAman MadaanPeter ClarkYiming Yang
2022
Findings of NAACL

Large language models (LMs), while power-ful, are not immune to mistakes, but can be difficult to retrain. Our goal is for an LM to continue to improve after deployment, without retraining, using… 

Aligning to Social Norms and Values in Interactive Narratives

Prithviraj AmmanabroluLiwei JiangMaarten SapYejin Choi
2022
NAACL

We focus on creating agents that act in alignment with socially beneficial norms and values in interactive narratives or text-based games—environments wherein an agent perceives and interacts with a… 

MultiVerS: Improving scientific claim verification with weak supervision and full-document context

David WaddenKyle LoLucy Lu WangHannaneh Hajishirzi
2022
Findings of NAACL

The scientific claim verification task requires an NLP system to label scientific documents which Support or Refute an input claim, and to select evidentiary sentences (or rationales) justifying… 

Time Waits for No One! Analysis and Challenges of Temporal Misalignment

Kelvin LuuDaniel KhashabiSuchin GururanganNoah A. Smith
2022
NAACL

When an NLP model is trained on text data from one time period and tested or deployed on data from another, the resulting temporal misalignment can degrade end-task performance. In this work, we… 

NeuroLogic A*esque Decoding: Constrained Text Generation with Lookahead Heuristics

Ximing LuS. WelleckPeter WestYejin Choi
2022
NAACL

The dominant paradigm for neural text generation is left-to-right decoding from autoregressive language models. Constrained or controllable generation under complex lexical constraints, however,… 

Few-Shot Self-Rationalization with Natural Language Prompts

Ana MarasovićIz BeltagyDoug DowneyMatthew E. Peters
2022
Findings of NAACL

Self-rationalization models that predict task labels and generate free-text elaborations for their predictions could enable more intuitive interaction with NLP systems. These models are, however,… 

Transparent Human Evaluation for Image Captioning

Jungo KasaiKeisuke SakaguchiLavinia DunaganNoah A. Smith
2022
NAACL

We establish a rubric-based human evaluation protocol for image captioning models. Our scoring rubrics and their definitions are carefully developed based on machineand humangenerated captions on…