What it measures

Taxonomy-driven benchmark separating extrinsic factual hallucination (entities, citations, nonexistent concepts) from intrinsic context contradiction.

Reading the measurement

Accuracy is only part of the picture. Inspect unsupported answers, abstentions, language coverage and the evidence available to the model. A confident response can still be wrong, and a broad average can hide a specialist gap.

Published evaluation

PreciseWikiQA correct answers; HalluLens · three-trial mean. The source’s task split, model configuration and scoring units are retained.

Where this fits in an evaluation suite

Read accuracy together with error and abstention rates. Domain averages can hide language gaps, specialist failures, and poorly calibrated confidence.

Start with a capability hypothesis, then choose a second test with a different failure mode. Keep the checkpoint, reasoning effort, agent tools, sampling policy, and scoring procedure fixed when measuring a training intervention. Record failures and missing outputs in the denominator.

A reproducible comparison

PreciseWikiQA correct answers; HalluLens · three-trial mean. The source’s task split, model configuration and scoring units are retained.

Publish the exact run configuration, item coverage, score units, and available uncertainty. If a source supplies only an aggregate or a single run, preserve that limit. A new model name or a rounded score alone does not establish a capability improvement.

PRIMARY EVIDENCE & FURTHER READING

  1. HalluLens: LLM Hallucination Benchmark — published result table ↗

    Yejin Bang, Ziwei Ji, Alan Schelten, Anthony Hartshorn, Tara Fowler, Cheng Zhang et al. · 2025

    All 8 authors

    Yejin Bang, Ziwei Ji, Alan Schelten, Anthony Hartshorn, Tara Fowler, Cheng Zhang, Nicola Cancedda, Pascale Fung

Reviewed 2026-10-26. Explanation and interpretation by RLTasks. Benchmark ownership remains with its original authors.