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

Commonsense Knowledge Transfer for Pre-trained Language Models

Wangchunshu ZhouRonan Le BrasYejin Choi
2023
ACL • Findings

Despite serving as the foundation models for a wide range of NLP benchmarks, pre-trained language models have shown limited capabilities of acquiring implicit commonsense knowledge from… 

EXCALIBUR: Encouraging and Evaluating Embodied Exploration

Hao ZhuRaghav KapoorSo Yeon MinLuca Weihs
2023
CVPR

Experience precedes understanding. Humans constantly explore and learn about their environment out of curiosity, gather information, and update their models of the world. On the other hand,… 

Minding Language Models' (Lack of) Theory of Mind: A Plug-and-Play Multi-Character Belief Tracker

Melanie SclarSachin KumarPeter WestYulia Tsvetkov
2023
ACL

Theory of Mind (ToM)$\unicode{x2014}$the ability to reason about the mental states of other people$\unicode{x2014}$is a key element of our social intelligence. Yet, despite their ever more… 

Z-ICL: Zero-Shot In-Context Learning with Pseudo-Demonstrations

Xinxi LyuSewon MinIz BeltagyHannaneh Hajishirzi
2023
ACL 2023

Although large language models can be prompted for both zero- and few-shot learning, performance drops significantly when no demonstrations are available. In this paper, we introduce Z-ICL, a new… 

Improving the reliability of ML-corrected climate models with novelty detection

Clayton SanfordAnna KwaOliver Watt-Meyerand Christopher S. Bretherton
2023
JAMES (Journal of Advances in Modeling Earth Systems)

The use of machine learning (ML) for the online correction of coarse-resolution atmospheric models has proven effective in reducing biases in near-surface temperature and precipitation rate.… 

Decomposing Complex Queries for Tip-of-the-tongue Retrieval

Kevin LinKyle LoJoseph E. GonzalezDan Klein
2023
arXiv

When re-finding items, users who forget or are uncertain about identifying details often rely on creative strategies for expressing their information needs -- complex queries that describe content… 

A Controllable QA-based Framework for Decontextualization

Benjamin NewmanLuca SoldainiRaymond FokKyle Lo
2023
arXiv

Many real-world applications require surfacing extracted snippets to users, whether motivated by assistive tools for literature surveys or document cross-referencing, or needs to mitigate and… 

Complex Mathematical Symbol Definition Structures: A Dataset and Model for Coordination Resolution in Definition Extraction

Anna Martin-BoyleAndrew HeadKyle LoDongyeop Kang
2023
arXiv

Mathematical symbol definition extraction is important for improving scholarly reading interfaces and scholarly information extraction (IE). However, the task poses several challenges: math symbols… 

Anthropomorphization of AI: Opportunities and Risks

A. DeshpandeTanmay RajpurohitKarthik NarasimhanA. Kalyan
2023
arXiv.org

Anthropomorphization is the tendency to attribute human-like traits to non-human entities. It is prevalent in many social contexts -- children anthropomorphize toys, adults do so with brands, and it… 

CSTS: Conditional Semantic Textual Similarity

A. DeshpandeCarlos E. JimenezHoward ChenKarthik Narasimhan
2023
arXiv.org

Semantic textual similarity (STS) has been a cornerstone task in NLP that measures the degree of similarity between a pair of sentences, with applications in information retrieval, question…