Formal structure boosts LLM accuracy on legal entailment but does not produce faithful reasoning, with scope laundering and other failures persisting across models on ContractNLI.
Divide and translate: Compositional first-order logic translation and verification for complex logical reasoning
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.AI 2representative citing papers
LogicAgent uses a semiotic-square-guided approach to enhance logical reasoning in LLMs on the new RepublicQA benchmark and others, reporting average gains of 6.25% and 7.05% respectively.
citing papers explorer
-
Know Your Limits : On the Faithfulness of LLMs as Solvers and Autoformalizers in Legal Reasoning
Formal structure boosts LLM accuracy on legal entailment but does not produce faithful reasoning, with scope laundering and other failures persisting across models on ContractNLI.
-
Semantic-Aware Logical Reasoning via a Semiotic Framework
LogicAgent uses a semiotic-square-guided approach to enhance logical reasoning in LLMs on the new RepublicQA benchmark and others, reporting average gains of 6.25% and 7.05% respectively.