Papers
See AI2's Award Winning Papers
Learn more about AI2's Lasting Impact Award
Viewing 1-10 of 1033 papers
Climate sensitivity and relative humidity changes in global storm-resolving model simulations of climate change
T. Merlis, Kai-Yuan Cheng, Ilai Guendelman, Lucas M. Harris, Christopher S. Bretherton, M. Bolot, Linjiong Zhou, Alex Kaltenbaugh, S. K. Clark, Gabriel A. Vecchi, Stephan FueglistalerScience Advances • 2024 The climate simulation frontier of a global storm-resolving model (GSRM; or k-scale model because of its kilometer-scale horizontal resolution) is deployed for climate change simulations. The climate sensitivity, effective radiative forcing, and relative…Detection and Measurement of Syntactic Templates in Generated Text
Chantal Shaib, Yanai Elazar, Junyi Jessy Li, Byron C. WallacearXiv • 2024 Recent work on evaluating the diversity of text generated by LLMs has focused on word-level features. Here we offer an analysis of syntactic features to characterize general repetition in models, beyond frequent n-grams. Specifically, we define syntactic…Evaluating n-Gram Novelty of Language Models Using Rusty-DAWG
William Merrill, Noah A. Smith, Yanai ElazararXiv • 2024 How novel are texts generated by language models (LMs) relative to their training corpora? In this work, we investigate the extent to which modern LMs generate /n/-grams from their training data, evaluating both (i) the probability LMs assign to complete…Probabilistic Emulation of a Global Climate Model with Spherical DYffusion
Salva Rühling Cachay, Brian Henn, Oliver Watt‐Meyer, Christopher S. Bretherton, Rose YuICML•ML4ESM • 2024 Data-driven deep learning models are on the verge of transforming global weather forecasting. It is an open question if this success can extend to climate modeling, where long inference rollouts and data complexity pose significant challenges. Here, we…Probabilistic Emulation of a Global Climate Model with Spherical DYffusion
Salva Rühling Cachay, Brian Henn, Oliver Watt‐Meyer, Christopher S. Bretherton, Rose YuICML•ML4ESM • 2024 Data-driven deep learning models are on the verge of transforming global weather forecasting. It is an open question if this success can extend to climate modeling, where long inference rollouts and data complexity pose significant challenges. Here, we…ADaPT: As-Needed Decomposition and Planning with Language Models
Archiki Prasad, Alexander Koller, Mareike Hartmann, Peter Clark, Ashish Sabharwal, Mohit Bansal, Tushar KhotNAACL Findings • 2024 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 ways: iteratively determining the next action (iterative…Evaluating In-Context Learning of Libraries for Code Generation
Arkil Patel, Siva Reddy, Dzmitry Bahdanau, Pradeep DasigiNAACL • 2024 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 unfamiliar libraries for solving user-instructed tasks. Recent work…Impossible Distillation: from Low-Quality Model to High-Quality Dataset&Model for Summarization and Paraphrasing
Jaehun Jung, Peter West, Liwei Jiang, Faeze Brahman, Ximing Lu, Jillian R. Fisher, Taylor Sorensen, Yejin ChoiNAACL • 2024 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 perform these tasks. Unlike prior works that rely on an extreme…JAMDEC: Unsupervised Authorship Obfuscation using Constrained Decoding over Small Language Models
Jillian R. Fisher, Ximing Lu, Jaehun Jung, Liwei Jiang, Zaid Harchaoui, Yejin ChoiNAACL • 2024 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 when needed, e.g., blind reviews for scientific papers…Leveraging Code to Improve In-context Learning for Semantic Parsing
Ben Bogin, Shivanshu Gupta, Peter Clark, Ashish SabharwalNAACL • 2024 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) from just a few demonstrations is challenging, limiting the…