Saved in:
Bibliographic Details
Main Authors: Sun, Jing Han, Emami, Ali
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2402.13372
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916134028050432
author Sun, Jing Han
Emami, Ali
author_facet Sun, Jing Han
Emami, Ali
contents While Large Language Models (LLMs) excel at the Winograd Schema Challenge (WSC), a coreference resolution task testing common-sense reasoning through pronoun disambiguation, they struggle with instances that feature minor alterations or rewording. To address this, we introduce EvoGrad, an open-source platform that harnesses a human-in-the-loop approach to create a dynamic dataset tailored to such altered WSC instances. Leveraging ChatGPT's capabilities, we expand our task instances from 182 to 3,691, setting a new benchmark for diverse common-sense reasoning datasets. Additionally, we introduce the error depth metric, assessing model stability in dynamic tasks. Our results emphasize the challenge posed by EvoGrad: Even the best performing LLM, GPT-3.5, achieves an accuracy of 65.0% with an average error depth of 7.2, a stark contrast to human performance of 92. 8% accuracy without perturbation errors. This highlights ongoing model limitations and the value of dynamic datasets in uncovering them.
format Preprint
id arxiv_https___arxiv_org_abs_2402_13372
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle EvoGrad: A Dynamic Take on the Winograd Schema Challenge with Human Adversaries
Sun, Jing Han
Emami, Ali
Computation and Language
While Large Language Models (LLMs) excel at the Winograd Schema Challenge (WSC), a coreference resolution task testing common-sense reasoning through pronoun disambiguation, they struggle with instances that feature minor alterations or rewording. To address this, we introduce EvoGrad, an open-source platform that harnesses a human-in-the-loop approach to create a dynamic dataset tailored to such altered WSC instances. Leveraging ChatGPT's capabilities, we expand our task instances from 182 to 3,691, setting a new benchmark for diverse common-sense reasoning datasets. Additionally, we introduce the error depth metric, assessing model stability in dynamic tasks. Our results emphasize the challenge posed by EvoGrad: Even the best performing LLM, GPT-3.5, achieves an accuracy of 65.0% with an average error depth of 7.2, a stark contrast to human performance of 92. 8% accuracy without perturbation errors. This highlights ongoing model limitations and the value of dynamic datasets in uncovering them.
title EvoGrad: A Dynamic Take on the Winograd Schema Challenge with Human Adversaries
topic Computation and Language
url https://arxiv.org/abs/2402.13372