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

What Makes Instruction Learning Hard? An Investigation and a New Challenge in a Synthetic Environment

Matthew FinlaysonKyle RichardsonAshish SabharwalPeter Clark
2022
EMNLP

The instruction learning paradigm—where a model learns to perform new tasks from task descriptions alone—has become popular in general-purpose model research. The capabilities of large transformer… 

Learn to Explain: Multimodal Reasoning via Thought Chains for Science Question Answering

Pan LuSwaroop MishraTony XiaA. Kalyan
2022
NeurIPS 2022

When answering a question, humans utilize the information available across different modalities to synthesize a consistent and complete chain of thought (CoT). This process is normally a black box… 

One Venue, Two Conferences: The Separation of Chinese and American Citation Networks

Bingchen ZhaoYuling GuJessica Zosa FordeNaomi Saphra
2022
NeurIPS • AI Cultures Workshop

At NeurIPS, American and Chinese institutions cite papers from each other’s regions substantially less than they cite endogamously. We build a citation graph to quantify this divide, compare it to… 

Breakpoint Transformers for Modeling and Tracking Intermediate Beliefs

Kyle RichardsonRonen TamariOren SultanAshish Sabharwal
2022
EMNLP

Can we teach natural language understanding models to track their beliefs through intermediate points in text? We propose a representation learning framework called breakpoint modeling that allows… 

Learning to Decompose: Hypothetical Question Decomposition Based on Comparable Texts

Ben ZhouKyle RichardsonXiaodong YuDan Roth
2022
EMNLP

Explicit decomposition modeling, which involves breaking down complex tasks into more straightforward and often more interpretable sub-tasks, has long been a central theme in developing robust and… 

Just-DREAM-about-it: Figurative Language Understanding with DREAM-FLUTE

Yuling GuYao FuValentina PyatkinPeter Clark
2022
EMNLP • The Third Workshop on Figurative Language Processing

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… 

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… 

DeepA2: A Modular Framework for Deep Argument Analysis with Pretrained Neural Text2Text Language Models

Gregor BetzKyle Richardson
2022
SEM

In this paper, we present and implement a multi-dimensional, modular framework for performing deep argument analysis (DeepA2) using current pre-trained language models (PTLMs). ArgumentAnalyst – a… 

Retrieval Data Augmentation Informed by Downstream Question Answering Performance

James FergusonPradeep DasigiTushar KhotHannaneh Hajishirzi
2022
ACL • FEVER

Training retrieval models to fetch contexts for Question Answering (QA) over large corpora requires labeling relevant passages in those corpora. Since obtaining exhaustive manual annotations of all…