# Generalizable Neuro-symbolic Systems for Commonsense Question Answering

Source: [Generalizable Neuro-symbolic Systems for Commonsense Question Answering](<https://www.sota2.com/research/paper/68fa6b981e209131cea2f232>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-28T13:56:51.454Z

Authors: Alessandro Oltramari, Jonathan Francis, Filip Ilievski, Kaixin Ma, Roshanak Mirzaee

Published: 2022-01-17T06:13:37.000Z

## Abstract

This chapter illustrates how suitable neuro-symbolic models for language understanding can enable domain generalizability and robustness in downstream tasks. Different methods for integrating neural language models and knowledge graphs are discussed. The situations in which this combination is most appropriate are characterized, including quantitative evaluation and qualitative error analysis on a variety of commonsense question answering benchmark datasets.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2201.06230>)

[PDF](<https://arxiv.org/pdf/2201.06230.pdf>)