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

Editing Models with Task Arithmetic

Gabriel IlharcoMarco Tulio RibeiroMitchell WortsmanAli Farhadi
2023
ICLR

Changing how pre-trained models behave -- e.g., improving their performance on a downstream task or mitigating biases learned during pre-training -- is a common practice when developing machine… 

InSCIt: Information-Seeking Conversations with Mixed-Initiative Interactions

Zeqiu WuRyu ParishHao ChengHannaneh Hajishirzi
2023
TACL

In an information-seeking conversation, a user may ask questions that are under-specified or unanswerable. An ideal agent would interact by initiating different response types according to the… 

Is Reinforcement Learning (Not) for Natural Language Processing?: Benchmarks, Baselines, and Building Blocks for Natural Language Policy Optimization

Rajkumar RamamurthyPrithviraj AmmanabroluKianté BrantleyYejin Choi
2023
ICLR

We tackle the problem of aligning pre-trained large language models (LMs) with human preferences. If we view text generation as a sequential decision-making problem, reinforcement learning (RL)… 

LongEval: Guidelines for Human Evaluation of Faithfulness in Long-form Summarization

Kalpesh KrishnaErin BransomBailey KuehlKyle Lo
2023
EACL

While human evaluation remains best practice for accurately judging the faithfulness of automatically-generated summaries, few solutions exist to address the increased difficulty and workload when… 

Moving Forward by Moving Backward: Embedding Action Impact over Action Semantics

Kuo-Hao ZengLuca WeihsRoozbeh MottaghiAli Farhadi
2023
ICLR

A common assumption when training embodied agents is that the impact of taking an action is stable; for instance, executing the"move ahead"action will always move the agent forward by a fixed… 

Selective Annotation Makes Language Models Better Few-Shot Learners

Hongjin SuJungo KasaiChen Henry WuTao Yu
2023
ICLR • Proceedings

Many recent approaches to natural language tasks are built on the remarkable abilities of large language models. Large language models can perform in-context learning, where they learn a new task… 

Old dog, new trick: Reservoir computing advances machine learning for climate modeling

Christopher S. Bretherton
2023
Geophysical Research Letters

Physics-informed machine learning (ML) applied to geophysical simulation is developing explosively. Recently, graph neural net and vision transformer architectures have shown 1-7 day global weather… 

S2abEL: A Dataset for Entity Linking from Scientific Tables

Yuze LouBailey KuehlErin BransomDoug Downey
2023
EMNLP

Entity linking (EL) is the task of linking a textual mention to its corresponding entry in a knowledge base, and is critical for many knowledge-intensive NLP applications. When applied to tables in… 

Answering Questions by Meta-Reasoning over Multiple Chains of Thought

Ori YoranTomer WolfsonBen BoginJonathan Berant
2023
EMNLP

Modern systems for multi-hop question answering (QA) typically break questions into a sequence of reasoning steps, termed chain-of-thought (CoT), before arriving at a final answer. Often, multiple… 

A Global Survey of Rotating Convective Updrafts in the GFDL X‐SHiELD 2021 Global Storm Resolving Model

Lucas HarrisLinjiong ZhouAlex KaltenbaughChristopher S. Bretherton
2023
Journal of Geophysical Research: Atmospheres

We present the global characteristics of rotating convective updrafts in the 2021 version of GFDL's eXperimental System for High‐resolution prediction on Earth‐to‐Local Domains (X‐SHiELD), a…