SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2211.05417 · EMNLP · 2022

Can Transformers Reason in Fragments of Natural Language?

Viktor Schlegel, Ian Pratt-Hartmann, Kamen Pavlov

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 1 functions out of this paper's own repositories and ran 0 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

RepositoryRoleRan
schlevik/nlr canonical 0 of 1
FunctionStatusWhere it lives
generate Not yet run schlevik/nlr/scripts/verify_vampire.py
pointer only (licence: NONE) · get_code("b525b5145e14727a")

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

deep-learning-based approaches to Natural Language Processing (NLP) are credited with various capabilities that involve reasoning with natural language texts. In this paper we carry out a large-scale empirical study investigating the detection of formally valid inferences in controlled fragments of natural language for which the satisfiability problem becomes increasingly complex. We find that, while transformerbased language models perform surprisingly well in these scenarios, a deeper analysis reveals that they appear to overfit to superficial patterns in the data rather than acquiring the logical principles governing the reasoning in these fragments.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2211.05417")
get_code_for_paper("2211.05417")
have("2211.05417")

Connect an agent — have() is free.