LLMs show consistent performance degradation on higher-arity relational reasoning tasks in a new benchmark REL that isolates relational complexity across scientific domains.
harmful together,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Evaluating Relational Reasoning in LLMs with REL
LLMs show consistent performance degradation on higher-arity relational reasoning tasks in a new benchmark REL that isolates relational complexity across scientific domains.