Chiral Narrative Synthesis workspace for Thinker/Tinker LoRA pipelines, semantic fact-checking, telemetry, and reviewer-ready CNS docs.
-
Updated
Nov 19, 2025 - Python
Chiral Narrative Synthesis workspace for Thinker/Tinker LoRA pipelines, semantic fact-checking, telemetry, and reviewer-ready CNS docs.
A modular, explainable Retrieval-Augmented Generation (RAG) pipeline for automated fact-checking on the FEVER dataset. Includes multi-model evaluation (Mistral, Qwen, GPT), PEFT & DPO fine-tuning, and token-level explainability with Captum, SHAP, and LIME
Add a description, image, and links to the fever-dataset topic page so that developers can more easily learn about it.
To associate your repository with the fever-dataset topic, visit your repo's landing page and select "manage topics."