MuSR: Testing the Limits of Chain-of-thought with Multistep Soft Reasoning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Sprague, Zayne, Ye, Xi, Bostrom, Kaj, Chaudhuri, Swarat, Durrett, Greg
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913278972657664
author Sprague, Zayne
Ye, Xi
Bostrom, Kaj
Chaudhuri, Swarat
Durrett, Greg
author_facet Sprague, Zayne
Ye, Xi
Bostrom, Kaj
Chaudhuri, Swarat
Durrett, Greg
contents While large language models (LLMs) equipped with techniques like chain-of-thought prompting have demonstrated impressive capabilities, they still fall short in their ability to reason robustly in complex settings. However, evaluating LLM reasoning is challenging because system capabilities continue to grow while benchmark datasets for tasks like logical deduction have remained static. We introduce MuSR, a dataset for evaluating language models on multistep soft reasoning tasks specified in a natural language narrative. This dataset has two crucial features. First, it is created through a novel neurosymbolic synthetic-to-natural generation algorithm, enabling the construction of complex reasoning instances that challenge GPT-4 (e.g., murder mysteries roughly 1000 words in length) and which can be scaled further as more capable LLMs are released. Second, our dataset instances are free text narratives corresponding to real-world domains of reasoning; this makes it simultaneously much more challenging than other synthetically-crafted benchmarks while remaining realistic and tractable for human annotators to solve with high accuracy. We evaluate a range of LLMs and prompting techniques on this dataset and characterize the gaps that remain for techniques like chain-of-thought to perform robust reasoning.
format Preprint
id arxiv_https___arxiv_org_abs_2310_16049
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle MuSR: Testing the Limits of Chain-of-thought with Multistep Soft Reasoning
Sprague, Zayne
Ye, Xi
Bostrom, Kaj
Chaudhuri, Swarat
Durrett, Greg
Computation and Language
While large language models (LLMs) equipped with techniques like chain-of-thought prompting have demonstrated impressive capabilities, they still fall short in their ability to reason robustly in complex settings. However, evaluating LLM reasoning is challenging because system capabilities continue to grow while benchmark datasets for tasks like logical deduction have remained static. We introduce MuSR, a dataset for evaluating language models on multistep soft reasoning tasks specified in a natural language narrative. This dataset has two crucial features. First, it is created through a novel neurosymbolic synthetic-to-natural generation algorithm, enabling the construction of complex reasoning instances that challenge GPT-4 (e.g., murder mysteries roughly 1000 words in length) and which can be scaled further as more capable LLMs are released. Second, our dataset instances are free text narratives corresponding to real-world domains of reasoning; this makes it simultaneously much more challenging than other synthetically-crafted benchmarks while remaining realistic and tractable for human annotators to solve with high accuracy. We evaluate a range of LLMs and prompting techniques on this dataset and characterize the gaps that remain for techniques like chain-of-thought to perform robust reasoning.
title MuSR: Testing the Limits of Chain-of-thought with Multistep Soft Reasoning
topic Computation and Language
url https://arxiv.org/abs/2310.16049