Datasets › AdversarialQA

AdversarialQA

Introduced by Max Bartolo et al. in Beat the AI: Investigating Adversarial Human Annotation for Reading Comprehension2 Feb 2020 archive 2025-07-28

We have created three new Reading Comprehension datasets constructed using an adversarial model-in-the-loop.

We use three different models; BiDAF (Seo et al., 2016), BERTLarge (Devlin et al., 2018), and RoBERTaLarge (Liu et al., 2019) in the annotation loop and construct three datasets; D(BiDAF), D(BERT), and D(RoBERTa), each with 10,000 training examples, 1,000 validation, and 1,000 test examples.

The adversarial human annotation paradigm ensures that these datasets consist of questions that current state-of-the-art models (at least the ones used as adversaries in the annotation loop) find challenging. The three AdversarialQA round 1 datasets provide a training and evaluation resource for such methods.

Benchmarks archive 2025-07-28

All 2 leaderboards whose dataset resolves to this page shown (sort by any header). "First row" is the archive's own first row at snapshot, in the archive's row order; nothing here re-ranks and metric direction is not asserted.

First row (archive order)PaperCode
Reading Comprehension AdversarialQA RoBERTa-Large Overall: F1 64.4 Beat the AI: Investigating Adversarial Human Annotation... maxbartolo/adversarialQA 3 Compare
Question Answering adversarial_qa no rows — — 0 Compare

Papers archive 2025-07-28

papers with a benchmark row: 1 · with a code link: 1 · where Syntology ran a sample: 0 (0 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument) Syntology

Show: all papers with a benchmark rowonly where code ran: none of the 1 papers with a benchmark row has a Syntology run on record

Page 1 of 1: paper 1 of 1 with a leaderboard row on this dataset's benchmarks, newest first by the archive's date (ties by slug; undated papers last).

The archive's own "papers using this dataset" list was never published, so this is the benchmark-backed subset, not that list; the archive's count for this dataset is 26. The Syntology column is from Syntology's graph, stated per sample; it is not part of any archive number. A line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified” (C is a part of N, never taken away from it); the figure “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced. When the archive marks a repository official for the paper, the cell starts with that repository's state (the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record.

PaperCodeResultsDateSamples run Syntology
Beat the AI: Investigating Adversarial Human Annotation for Reading Comprehension 1 3 2 Feb 2020 not harvested

Dataset loaders archive 2025-07-28

2 loaders as listed in the archive; links are outbound and not re-checked here.

Tasks archive 2025-07-28

License archive 2025-07-28

CC BY-SA 3.0

Modalities archive 2025-07-28

Languages archive 2025-07-28

Variants archive 2025-07-28

  • AdversarialQA
  • adversarial_qa

2 variant names, as the archive lists them.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections