Multi-IF

IFEval-style verifiable instruction following extended to three-turn conversations in eight languages, 4,501 dialogues.

Also known as: MultiIF, facebook/Multi-IF

unassessed

This page is a discovery lead. Nobody has yet assessed it against the catalogue contract, so it carries no disposition. Absence of evidence here is not evidence of staleness.
Categoryinstruction-following
Subcategorymulti-turn multilingual verifiable instruction following
Page statusactive
Metricmean of prompt-level and instruction-level strict and loose accuracy, per turn and overall
Directionhigher_is_better
Unit%
Dataset size4501
Dataset licenceCC BY-NC 2.0
PublisherMeta (Facebook AI)

What it measures

Multi-IF tests whether a model still obeys mechanically checkable instructions when those constraints span three dialogue turns and eight languages. Each user turn adds or restates IFEval-style rules (length, keywords, format). Scoring uses the same strict and loose program checks as [IFEval](ifeval.md), applied per turn. The English prompts were translated into seven other languages with an LLM, then audited by professional annotators.

Task format

Three-turn chat. The model answers turn 1, then turn 2 given the history, then turn 3. Each turn has an instruction-id list and kwargs for the IFEval checkers. OpenCompass MultiIFDataset builds a six-message dialogue (user/assistant × 3) and scores with MultiIFEvaluator. Official code is facebookresearch/Multi-IF on the `facebook/Multi-IF` CSV.

Models reporting this benchmark

No model card in ModelSpec reports this benchmark yet.

Data

This page as JSON · Edit on GitHub