A new benchmark permutes CommonGen concept sets and asks LLMs to compose sentences in the specified order; even the best model achieves only about 75% ordered coverage.
Due to variations in CoT reasoning, unified evaluation is challenging; therefore, we evaluated using reasoning models
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Revisiting Compositional Generalization Capability of Large Language Models Considering Instruction Following Ability
A new benchmark permutes CommonGen concept sets and asks LLMs to compose sentences in the specified order; even the best model achieves only about 75% ordered coverage.