jevragaschoiceper chunkmirrors ragas.faithfulness (per-chunk attribution) / autoevals.Faithfulness

Chunk support

Chunk support asks, for each retrieved chunk, whether it supports the output's claims, contradicts them, or says nothing about them. Contradictions are the hallucination signal, located to the chunk. It is per-chunk faithfulness attribution in one request.

Run this example in the console 3 jev questions · answered inside one request
how it works // frame by frame

What the evaluator does

N Choice questions (supports / contradicts / unrelated) in the same request. Score is (supporting − contradicting) / N, clipped at 0; a single contradiction fails the check.

frame 1/4 · the question
question · asked once per chunk

How does `context[i]` relate to the claims in `output`: supports, contradicts, or unrelated?

chunk 1supports · 93%

Price: $42 per billion input tokens. Output tokens are free.

chunk 2unrelated · 90%

The company was founded in 2024 and is headquartered in San Francisco.

chunk 3contradicts · 88%

Output tokens are billed at $8 per million on the legacy v0 endpoint, which is deprecated.

1 supports · 1 contradicts → fail · the contradicting chunk is named3 questions · 1 request
exactly what jev is asked

The question, verbatim

This is the question the API sends for the example below, generated from the same code path the playground and API use. Jev sees the request fields as state and returns a probability for each outcome. Nothing is generated, so there is nothing to parse.

c0choice · one of n

How does `context[0]` relate to the claims made in `output`? Judge this chunk on its own.

  1. supportsThe chunk contains evidence that supports one or more claims in the output
  2. contradictsThe chunk contradicts one or more claims in the output
  3. unrelatedThe chunk neither supports nor contradicts the output
c1choice · one of n

How does `context[1]` relate to the claims made in `output`? Judge this chunk on its own.

  1. supportsThe chunk contains evidence that supports one or more claims in the output
  2. contradictsThe chunk contradicts one or more claims in the output
  3. unrelatedThe chunk neither supports nor contradicts the output
c2choice · one of n

How does `context[2]` relate to the claims made in `output`? Judge this chunk on its own.

  1. supportsThe chunk contains evidence that supports one or more claims in the output
  2. contradictsThe chunk contradicts one or more claims in the output
  3. unrelatedThe chunk neither supports nor contradicts the output
when to use it

Reach for it when

  • Explaining a low faithfulness score: which chunk disagrees?
  • Building citation UIs: show the chunks that support each answer.
  • Detecting conflicting sources in the retrieved set.

Not the right tool when

  • No context (this is a RAG evaluator).

Watch out for

  • Unrelated chunks are not a failure here; use chunk_relevance for noise.
inputs and example

What to send

required fields
outputcontext
optional fields
input
in suites
GroundingRAGEverything
result shape

score mapped from the chosen option, label = option key, confidence, a probability per option, passed by option. Plus a details array with one row per chunk.

POST /api/v1/evaluateopen in console
{
  "evaluators": [
    "chunk_support"
  ],
  "output": "Jev is billed per input token at $0.042 per million; output tokens are free.",
  "context": [
    "Price: $42 per billion input tokens. Output tokens are free.",
    "Founded in 2024.",
    "Output billed at $8/M on the legacy v0 endpoint."
  ]
}
expected

Chunk 1 supports, chunk 2 unrelated, chunk 3 contradicts (legacy billing).

rolling it up

Aggregate with

One result per item is a fact; a dataset of them is a metric. These are the aggregations that fit this evaluator's output shape.

related evaluators
questions people ask
What does a contradicting chunk mean?
The retrieved set disagrees with the answer somewhere. Either the answer is wrong or the corpus has conflicting documents; either way you know which chunk to read.