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

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… 

DISCO: Distilling Phrasal Counterfactuals with Large Language Models

Zeming ChenQiyue GaoKyle RichardsonAshish Sabharwal
2023
ACL

Recent methods demonstrate that data augmentation using counterfactual knowledge can teach models the causal structure of a task, leading to robust and generalizable models. However, such… 

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… 

HINT: Hypernetwork Instruction Tuning for Efficient Few- and Zero-Shot Generalisation

Hamish IvisonAkshita BhagiaYizhong WangMatthew E. Peters
2023
ACL

Recent NLP models have shown the remarkable ability to effectively generalise `zero-shot' to new tasks using only natural language instructions as guidance. However, many of these approaches suffer… 

Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questions

Harsh TrivediNiranjan BalasubramanianTushar KhotAshish Sabharwal
2023
ACL

Prompting-based large language models (LLMs) are surprisingly powerful at generating natural language reasoning steps or Chains-of-Thoughts (CoT) for multi-step question answering (QA). They… 

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… 

Reproducibility in NLP: What Have We Learned from the Checklist?

Ian H. MagnussonNoah A. SmithJesse Dodge
2023
Findings of ACL

Scientific progress in NLP rests on the reproducibility of researchers' claims. The *CL conferences created the NLP Reproducibility Checklist in 2020 to be completed by authors at submission to… 

Are Layout-Infused Language Models Robust to Layout Distribution Shifts? A Case Study with Scientific Documents

Catherine ChenZejiang ShenDan KleinKyle Lo
2023
Findings of ACL

Recent work has shown that infusing layout features into language models (LMs) improves processing of visually-rich documents such as scientific papers. Layout-infused LMs are often evaluated on… 

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… 

CREPE: Open-Domain Question Answering with False Presuppositions

Xinyan Velocity YuSewon MinLuke ZettlemoyerHannaneh Hajishirzi
2023
ACL

When asking about unfamiliar topics, information seeking users often pose questions with false presuppositions. Most existing question answering (QA) datasets, in contrast, assume all questions have…