LLMs
Bringing Structure and Faithfulness to LLM Outputs
Exploring Grammar-Constrained Decoding (GCD) for LLMs. Comparing EGG, GAD, and FEG methods for improving efficiency, faithfulness, and flexibility in generating structured output.
LLMs
Exploring Grammar-Constrained Decoding (GCD) for LLMs. Comparing EGG, GAD, and FEG methods for improving efficiency, faithfulness, and flexibility in generating structured output.
Case Study
In this case study, we demonstrate how a Retrieval-Augmented Generation (RAG) pipeline supports an automated therapy bot based on Darwinian Enhanced Cognitive Behavioral Therapy (DE-CBT) within the ABCDE framework (Activating Events, Beliefs, Consequences, Disputing, and New Emotions/Behaviors). The pipeline employs hybrid semantic embedding methods (BGE-M3), multi-level memory design, and