Chain of Thought risk decomposes into oracle-trajectory benefit and trajectory-mismatch cost, with stability determining bounded, linear, or exponential error growth.
Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
A neuro-symbolic pipeline pairing 4B-parameter LLMs with a symbolic theorem prover delivers competitive accuracy and low content effects on syllogistic reasoning subtasks.
citing papers explorer
-
UFAL-CUNI at SemEval-2026 Task 11: An Efficient Modular Neuro-symbolic Method for Syllogistic Reasoning
A neuro-symbolic pipeline pairing 4B-parameter LLMs with a symbolic theorem prover delivers competitive accuracy and low content effects on syllogistic reasoning subtasks.