Director-Class AI: Coherence Engine v1.4.1

Real-time LLM hallucination guardrail. Dual-entropy scoring (NLI contradiction via FactCG-DeBERTa-v3-Large plus RAG fact-checking) with token-level streaming halt. 75.8 percent balanced accuracy on LLM-AggreFact (29K samples). v1.4.1 adds ORT_ENABLE_ALL graph optimization, ONNX GPU batch inference at 14.6 ms per pair, and MiniCheck evaluation harness. Integrates with LangChain, LlamaIndex, LangGraph, Haystack, and CrewAI.

Published by ANULUM. Source: https://github.com/anulum/director-ai

Keywords

AI safety, streaming halt, DeBERTa, NLI verification, FactCG, hallucination detection, LLM guardrail, RAG fact-checking

Impact byBIP!

	selected citations These citations are derived from selected sources. This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).	0
	popularity This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.	Average
	influence This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).	Average
	impulse This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.	Average

Found an issue? Give us feedback

0

Average