https://arxiv.org/abs/2305.18654
Faith and Fate: Limits of Transformers on Compositionality
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
Submitted on 29 May 2023 (v1), last revised 31 Oct 2023 (this version, v3)
“…these models simultaneously show failures on surprisingly trivial problems…. transformer LLMs solve compositional tasks by reducing multi-step compositional reasoning into linearized subgraph matching, without necessarily developing systematic problem-solving skills.”