[2305.18654] Faith and Fate: Limits of Transformers on Compositionality

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs. arXiv Operational Status Get status notifications via email or slack

[2305.18654] Faith and Fate: Limits of Transformers on Compositionality --> Computer Science > Computation and Language arXiv:2305.18654 (cs) [Submitted on 29 May 2023 ( v1 ), last revised 31 Oct 2023 (this version, v3)] Title: Faith and Fate: Limits of Transformers on Compositionality Authors: Nouha Dziri , Ximing Lu , Melanie Sclar , Xiang Lorraine Li , Liwei Jiang , Bill Yuchen Lin , Peter West , Chandra Bhagavatula , Ronan Le Bras , Jena D. Hwang , Soumya Sanyal , Sean Welleck , Xiang Ren , Allyson Ettinger , Zaid Harchaoui , Yejin Choi View a PDF of the paper titled Faith and Fate: Limits

saved by

• sashrika pandey

related reading

• 2305.18654arxiv.org
• 2305.18654.pdfarxiv.org
• A Mathematical Framework for Transformer Circuitstransformer-circuits.pub
• [2402.12875] Chain of Thought Empowers Transformers to Solve Inherently Serial Problemsarxiv.org
• [2406.17583] Towards Compositional Interpretability for XAIarxiv.org
• [2506.09501] Understanding and Mitigating Numerical Sources of Nondeterminism in LLM Inferencearxiv.org
• [2401.05566] Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Trainingarxiv.org
• [2312.15159] Understanding the Potential of FPGA-Based Spatial Acceleration for Large Language Model Inferencearxiv.org
• [2503.07003] Large Language Models Often Say One Thing and Do Anotherarxiv.org
• [2508.12773] Online Ensemble Transformer for Accurate Cloud Workload Forecasting in Predictive Auto-Scalingarxiv.org
• [2309.01809] Are Emergent Abilities in Large Language Models just In-Context Learning?arxiv.org
• 2402.12875arxiv.org