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

Localized Symbolic Knowledge Distillation for Visual Commonsense Models

Jae Sung ParkJack HesselKhyathi Raghavi ChanduYejin Choi
2023
NeurIPS

Instruction following vision-language (VL) models offer a flexible interface that supports a broad range of multimodal tasks in a zero-shot fashion. However, interfaces that operate on full images… 

COBRA Frames: Contextual Reasoning about Effects and Harms of Offensive Statements

Xuhui ZhouHao ZhuAkhila YerukolaMaarten Sap
2023
ACL Findings

Warning: This paper contains content that may be offensive or upsetting. Understanding the harms and offensiveness of statements requires reasoning about the social and situational context in which… 

Detoxifying Text with MaRCo: Controllable Revision with Experts and Anti-Experts

Skyler HallinanAlisa LiuYejin ChoiMaarten Sap
2023
ACL

Text detoxification has the potential to miti- 001 gate the harms of toxicity by rephrasing text to 002 remove offensive meaning, but subtle toxicity 003 remains challenging to tackle. We introduce… 

From Dogwhistles to Bullhorns: Unveiling Coded Rhetoric with Language Models

Julia MendelsohnRonan Le BrasYejin ChoiMaarten Sap
2023
ACL

Dogwhistles are coded expressions that simultaneously convey one meaning to a broad audience and a second one, often hateful or provocative, to a narrow in-group; they are deployed to evade both… 

NLPositionality: Characterizing Design Biases of Datasets and Models

Sebastin SantyJenny T. LiangRonan Le BrasMaarten Sap
2023
ACL

Design biases in NLP systems, such as performance differences for different populations, often stem from their creator's positionality, i.e., views and lived experiences shaped by identity and… 

ClarifyDelphi: Reinforced Clarification Questions with Defeasibility Rewards for Social and Moral Situations

Valentina PyatkinJena D. HwangVivek SrikumarChandra Bhagavatula
2023
ACL

Context is everything, even in commonsense moral reasoning. Changing contexts can flip the moral judgment of an action; Lying to a friend is wrong in general, but may be morally acceptable if it is… 

Do Androids Laugh at Electric Sheep? Humor"Understanding"Benchmarks from The New Yorker Caption Contest

Jack HesselAna MarasovićJena D. HwangYejin Choi
2023
ACL

We challenge AI models to “demonstrate un-derstanding” of the sophisticated multimodal humor of The New Yorker Caption Contest. Concretely, we develop three carefully cir-cumscribed tasks for which… 

Riveter: Measuring Power and Social Dynamics Between Entities

Maria AntoniakAnjalie FieldJimin MunMaarten Sap
2023
ACL

Riveter provides a complete easy-to-use pipeline for analyzing verb connotations associated with entities in text corpora. We prepopulate the package with connotation frames of sentiment, power, and… 

I2D2: Inductive Knowledge Distillation with NeuroLogic and Self-Imitation

Chandra BhagavatulaJena D. HwangDoug DowneyYejin Choi
2023
Annual Meeting of the Association for Computational Linguistics

Commonsense capabilities of pre-trained language models dramatically improve with scale, leading many to believe that scale is the only winning recipe. But is it? Here, we investigate an alternative… 

LLM-Blender: Ensembling Large Language Models with Pairwise Ranking and Generative Fusion

Dongfu JiangXiang RenBill Yuchen Lin
2023
ACL

We present LLM-Blender, an ensembling framework designed to attain consistently superior performance by leveraging the diverse strengths of multiple open-source large language models (LLMs). Our…