FOLIO: Natural Language Reasoning with First-Order Logic
Abstract
Large language models (LLMs) have achieved remarkable performance on a variety of natural language understanding tasks. However, existing benchmarks are inadequate in measuring the complex logical reasoning capabilities of a model. We present FOLIO, a human-annotated, logically complex and diverse dataset for reasoning in natural language (NL), equipped with first-order logic (FOL) annotations. FOLIO consists of 1,430 examples (unique conclusions), each paired with one of 487 sets of premises used to deductively reason for the validity of each conclusion. The logical correctness of the premises and conclusions is ensured by their FOL annotations, which are automatically verified by an FOL inference engine. In addition to the main NL reasoning task, NL-FOL pairs in FOLIO constitute a new NL-FOL translation dataset. Our experiments on FOLIO systematically evaluate the FOL reasoning ability of supervised fine-tuning on medium-sized language models. For both NL reasoning and NL-FOL translation, we benchmark multiple state-of-the-art language models. Our results show that a subset of FOLIO presents a challenge for one of the most capable {Large Language Model (LLM)} publicly available, GPT-4.
Cite
@article{arxiv.2209.00840,
title = {FOLIO: Natural Language Reasoning with First-Order Logic},
author = {Simeng Han and Hailey Schoelkopf and Yilun Zhao and Zhenting Qi and Martin Riddell and Wenfei Zhou and James Coady and David Peng and Yujie Qiao and Luke Benson and Lucy Sun and Alex Wardle-Solano and Hannah Szabo and Ekaterina Zubova and Matthew Burtell and Jonathan Fan and Yixin Liu and Brian Wong and Malcolm Sailor and Ansong Ni and Linyong Nan and Jungo Kasai and Tao Yu and Rui Zhang and Alexander R. Fabbri and Wojciech Kryscinski and Semih Yavuz and Ye Liu and Xi Victoria Lin and Shafiq Joty and Yingbo Zhou and Caiming Xiong and Rex Ying and Arman Cohan and Dragomir Radev},
journal= {arXiv preprint arXiv:2209.00840},
year = {2024}
}