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

Unified-IO 2: Scaling Autoregressive Multimodal Models with Vision, Language, Audio, and Action

Jiasen Lu*Christopher Clark*Sangho Lee*Aniruddha Kembhavi
2024
CVPR

We present Unified-IO 2, the first autoregressive multimodal model that is capable of understanding and generating images, text, audio, and action. To unify different modalities, we tokenize inputs… 

ADaPT: As-Needed Decomposition and Planning with Language Models

Archiki PrasadAlexander KollerMareike HartmannTushar Khot
2024
NAACL Findings

Large Language Models (LLMs) are increasingly being used for interactive decision-making tasks requiring planning and adapting to the environment. Recent works employ LLMs-as-agents in broadly two… 

Evaluating In-Context Learning of Libraries for Code Generation

Arkil PatelSiva ReddyDzmitry BahdanauPradeep Dasigi
2024
NAACL

Contemporary Large Language Models (LLMs) exhibit a high degree of code generation and comprehension capability. A particularly promising area is their ability to interpret code modules from… 

Impossible Distillation: from Low-Quality Model to High-Quality Dataset&Model for Summarization and Paraphrasing

Jaehun JungPeter WestLiwei JiangYejin Choi
2024
NAACL

We present Impossible Distillation, a novel framework for paraphrasing and sentence summarization, that distills a high-quality dataset and model from a low-quality teacher that itself cannot… 

JAMDEC: Unsupervised Authorship Obfuscation using Constrained Decoding over Small Language Models

Jillian R. FisherXiming LuJaehun JungYejin Choi
2024
NAACL

The permanence of online content combined with the enhanced authorship identification techniques calls for stronger computational methods to protect the identity and privacy of online authorship… 

Leveraging Code to Improve In-context Learning for Semantic Parsing

Ben BoginShivanshu GuptaPeter ClarkAshish Sabharwal
2024
NAACL

In-context learning (ICL) is an appealing approach for semantic parsing due to its few-shot nature and improved generalization. However, learning to parse to rare domain-specific languages (DSLs)… 

MacGyver: Are Large Language Models Creative Problem Solvers?

Yufei TianAbhilasha RavichanderLianhui QinFaeze Brahman
2024
NAACL

We explore the creative problem-solving capabilities of modern LLMs in a novel constrained setting. To this end, we create MACGYVER, an automatically generated dataset consisting of over 1,600… 

NeuroComparatives: Neuro-Symbolic Distillation of Comparative Knowledge

Phillip HowardJunlin WangVasudev LalSwabha Swayamdipta
2024
NAACL

Comparative knowledge (e.g., steel is stronger and heavier than styrofoam) is an essential component of our world knowledge, yet understudied in prior literature. In this paper, we harvest the… 

On-the-fly Definition Augmentation of LLMs for Biomedical NER

Monica MunnangiSergey FeldmanByron C WallaceAakanksha Naik
2024
NAACL 2024

Despite their general capabilities, LLMs still struggle on biomedical NER tasks, which are difficult due to the presence of specialized terminology and lack of training data. In this work we set out… 

Personalized Jargon Identification for Enhanced Interdisciplinary Communication

Yue GuoJoseph Chee ChangMaria AntoniakTal August
2024
NAACL

Scientific jargon can impede researchers when they read materials from other domains. Current methods of jargon identification mainly use corpus-level familiarity indicators (e.g., Simple Wikipedia…