Tag
The paper introduces temporal dependency graphs extracted from legal documents to compute filing deadlines, showing a pipeline approach outperforms direct language model answering in accuracy.
The paper proposes GiLT (Graph-Infused Layers Transformer Language Model), which improves syntactic generalization by modulating attention weights using features from dependency graphs constructed incrementally during token prediction, outperforming baselines while maintaining competitive perplexity.
SocratiCode is a zero-config tool that gives AI deep semantic understanding of codebases, reducing context and tool calls while being fully local and free.