Reasoning Like Program Executors
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 novel reasoning pre-training paradigm. Through pre-training language models with programs and their execution results, POET empowers language models to harvest the reasoning knowledge possessed by program executors via a data-driven approach. POET is conceptually simple and can be instantiated by different kinds of program executors. In this paper, we showcase two simple instances POET-Math and POET-Logic, in addition to a complex instance, POET-SQL. Experimental results on six benchmarks demonstrate that POET can significantly boost model performance in natural language reasoning, such as numerical reasoning, logical reasoning, and multi-hop reasoning. 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.
PDF AbstractCode
SQuAD
MultiNLI
HotpotQA
DROP
SVAMP
LogiQA
Quoref
Results from the Paper
Ranked #2 on
Question Answering
on DROP Test
(using extra training data)
| Task | Dataset | Model | Metric Name | Metric Value | Global Rank | Uses Extra Training Data |
Benchmark |
|---|---|---|---|---|---|---|---|
| Question Answering | DROP Test | POET | F1 | 87.6 | # 2 |
