Skip to main content -> Ai2 Navigation Menu Open technologies Open models Open data AI for the environment AI for science On-device Research Research principles Papers Foundations of AI About Us Blog Playground Research - Papers Filter Yue Yang Fan-Yun Sun Luca Weihs +10 authors Christopher Clark Expand Mingqi Gao Yixin Liu Xinyu Hu +2 authors Arman Cohan Expand Ruotong Wang Xinyi Zhou Lin Qiu +2 authors Amy X. Zhang Expand Sarah Wiegreffe Oyvind Tafjord Yonatan Belinkov +1 authors Ashish Sabharwal Expand Bodhisattwa Prasad Majumder Harshit Surana Dhruv Agarwal +6 authors Peter Clark Expand Antonis Antoniades Xinyi Wang Yanai Elazar +3 authors W. Wang Expand Parshin Shojaee Kazem Meidani Shashank Gupta +1 authors Chandan K Reddy Expand Jack Merullo Noah A. Smith Sarah Wiegreffe Yanai Elazar Expand William Merrill Ashish Sabharwal Expand Bill Yuchen Lin Ronan Le Bras Kyle Richardson +3 authors Yejin Choi Expand Previous 1-10 Next Get in touch Working at Ai2 Legal Follow Ai2 Explore a selection of our published work on a variety of key research challenges in AI. 3D simulated environments play a critical role in Embodied AI, but their creation requires expertise and extensive manual effort, restricting their diversity and scope. To miti-gate this limitation,… Expand Evaluating and ranking the capabilities of different LLMs is crucial for understanding their performance and alignment with human preferences. Due to the high cost and time-consuming nature of human… Expand AI agents are increasingly tasked with making proactive suggestions in online spaces where groups collaborate, but can be unhelpful or even annoying, due to not fitting the group's preferences or… Expand Multiple-choice question answering (MCQA) is a key competence of performant transformer language models that is tested by mainstream benchmarks. However, recent evidence shows that models can have… Expand Can the rapid advances in code generation, function calling, and data analysis using large language models (LLMs) help automate the search and verification of hypotheses purely from a set of… Expand The impressive capabilities of large language models (LLMs) have sparked debate over whether these models genuinely generalize to unseen tasks or predominantly rely on memorizing vast amounts of… Expand Mathematical equations have been unreasonably effective in describing complex natural phenomena across various scientific disciplines. However, discovering such insightful equations from data… Expand Pretraining data has a direct impact on the behaviors and quality of language models (LMs), but we only understand the most basic principles of this relationship. While most work focuses on… Expand Recent theoretical results show transformers cannot express sequential reasoning problems over long input lengths, intuitively because their computational depth is bounded. However, prior work… Expand We investigate the logical reasoning capabilities of large language models (LLMs) and their scalability in complex non-monotonic reasoning. To this end, we introduce ZebraLogic, a comprehensive… Expand Questions about our work, or need support with one of our technologies? Get in touch © The Allen Institute for Artificial Intelligence - All Rights Reserved.