A parametrized benchmark of argumentation-based reasoning puzzles shows that leading LLMs are brittle even at low complexity, with perfect linear performance only from OpenAI's o1-preview.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Parameterized Argumentation-based Reasoning Tasks for Benchmarking Generative Language Models
A parametrized benchmark of argumentation-based reasoning puzzles shows that leading LLMs are brittle even at low complexity, with perfect linear performance only from OpenAI's o1-preview.