RAG-020RAG · Staying truthfullayaeval.ContextConflictDetection

Context Conflict

Do two fetched sources disagree with each other?

Simulation state:

When it passes

Sources agree.

Threshold satisfied: evaluation score <= 0.30.

When it fails

Sources conflict.

Violation detected: execution flagged for human review or fallback routing.

SDK Specification

Parameter	Value	Description
Class	ContextConflictDetection	Python evaluator class in layaeval
Required Fields	"query", "retrieved_context"	Arguments expected in the call signature
Default Threshold	<= 0.30	Passes when risk score is at or below this value
Category	RAG Evaluation	Staying truthful (Does every line come from the pages, with nothing made up?)

Python Example

pip install layaeval

context-conflict.py

1from layaeval import ContextConflictDetection
2
3metric = ContextConflictDetection(threshold=0.30)  # passes when risk is at or below 0.30
4
5res = metric(
6    query="What is the capital of France?",
7    retrieved_context="Paris is the capital of France, with 2.1M residents.",
8)
9
10print(res.passed, res.value, res.confidence)