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

Generated Knowledge Prompting for Commonsense Reasoning

Jiachen LiuAlisa LiuXiming LuHannaneh Hajishirzi
2022
ACL

Despite their ability to capture large amount of knowledge during pretraining, large-scale language models often benefit from incorporating external knowledge bases, especially on commonsense… 

Hey AI, Can You Solve Complex Tasks by Talking to Agents?

Tushar KhotKyle RichardsonDaniel KhashabiAshish Sabharwal
2022
Findings of ACL

Humans often solve complex problems by interacting (in natural language) with existing agents, such as AI assistants, that can solve simpler sub-tasks. These agents themselves can be powerful… 

Is GPT-3 Text Indistinguishable from Human Text? SCARECROW: A Framework for Scrutinizing Machine Text

Yao DouMaxwell ForbesRik Koncel-KedziorskiYejin Choi
2022
ACL

Modern neural text generation systems can produce remarkably fluent and grammatical texts. While earlier language models suffered from repetition and syntactic errors, the errors made by contemporary… 

Reframing Instructional Prompts to GPTk's Language

Swaroop MishraDaniel KhashabiChitta BaralHanna Hajishirzi
2022
Findings of ACL

How can model designers turn task instructions into effective prompts for language models? Backed by extensive empirical analysis on GPT3, we observe important features for successful instructional… 

Situated Dialogue Learning through Procedural Environment Generation

Prithviraj AmmanabroluRenee JiaMark O. Riedl
2022
ACL

We teach goal-driven agents to interactively act and speak in situated environments by training on generated curriculums. Our agents operate in LIGHT (Urbanek et al. 2019)—a large-scale… 

Understanding Dataset Difficulty with 𝒱-Usable Information

Kawin EthayarajhYejin Choiand Swabha Swayamdipta
2022
ICML

Estimating the difficulty of a dataset typically involves comparing state-of-the-art models to humans; the bigger the performance gap, the harder the dataset is said to be. However, this comparison… 

The Curious Case of Commonsense Intelligence

Yejin Choi
2022
Daedalus

Abstract Commonsense intelligence is a long-standing puzzle in AI. Despite considerable advances in deep learning, AI continues to be narrow and brittle due to its lack of common sense. Why is… 

Beam Decoding with Controlled Patience

Jungo KasaiKeisuke SakaguchiRonan Le BrasNoah A. Smith
2022
arXiv

Text generation with beam search has proven successful in a wide range of applications. The commonly-used implementation of beam decoding follows a first come, first served heuris-tic: it keeps a set… 

Benchmarking Generalization via In-Context Instructions on 1, 600+ Language Tasks

Yizhong WangSwaroop MishraPegah AlipoormolabashiDaniel Khashabi
2022
arXiv

How can we measure the generalization of models to a variety of unseen tasks when provided with their language instructions? To facilitate progress in this goal, we introduce N ATURAL -I NSTRUCTIONS… 

COLD Decoding: Energy-based Constrained Text Generation with Langevin Dynamics

Lianhui QinS. WelleckDaniel KhashabiYejin Choi
2022
arXiv

Many applications of text generation require incorporating different constraints to control the semantics or style of generated text. These constraints can be hard (e.g., ensuring certain keywords…