cycle-consistency

This paper proposes a cycle-consistent neural architecture that generates faithful natural language explanations of formal verification certificates, achieving 90% soundness and 860x faster inference than LLM baselines.

This paper proposes a novel pipeline for multilingual coreference resolution that uses cycle-consistent machine translation from English to low-resource languages to generate training data, validated by back-translation and BERT similarity. Experiments on four low-resource languages show significant performance gains, enabling accurate coreference resolution where no prior corpora existed.

Introduces A2RBench, an automated pipeline for generating formally verifiable abstract reasoning benchmarks for LLMs, using cycle consistency to ensure unique solutions, and reveals that current LLMs underperform humans significantly on 3D reasoning tasks.