“Reasoning Like Program Executors”, Xinyu Pi, Qian Liu, Bei Chen, Morteza Ziyadi, Zeqi Lin, Yan Gao, Qiang Fu, Jian-Guang Lou, Weizhu Chen2022-01-27 (inner monologue (AI), instruct-tuning LLMs, T5 Transformer, AI scaling; similar)⁠:

Reasoning over natural language is a long-standing goal for the research community. However, studies have shown that existing language models are inadequate in reasoning. To address the issue, we present POET, a new pre-training paradigm.

Through pre-training language models with programs and their execution results, POET empowers language models to harvest the reasoning knowledge possessed in program executors via a data-driven approach. POET is conceptually simple and can be instantiated by different kinds of programs. In this paper, we show 3 empirically powerful instances, ie. POET-Math, POET-Logic, and POET-SQL.

Experimental results on 6 benchmarks demonstrate that POET can boost model performance on natural language reasoning, such as numerical reasoning, logical reasoning, and multi-hop reasoning. Taking the DROP benchmark as a representative example, POET improves the F1 metric of BART 69.2% → 80.6%. Furthermore, POET shines in giant language models, pushing the F1 metric of T5-11B to 87.6% and achieving a new state-of-the-art performance on DROP.

POET opens a new gate on reasoning-enhancement pre-training and we hope our analysis would shed light on the future research of reasoning like program executors.

Similar Links: