Papers › Benchmarking Robustness of Machine Reading Comprehension Models

Benchmarking Robustness of Machine Reading Comprehension Models

29 Apr 2020Findings (ACL) 2021 8arXiv:2004.14004archive 2025-07-28

Chenglei Si, Ziqing Yang, Yiming Cui, Wentao Ma, Ting Liu, Shijin Wang

Machine Reading Comprehension (MRC) is an important testbed for evaluating models' natural language understanding (NLU) ability. There has been rapid progress in this area, with new models achieving impressive performance on various benchmarks. However, existing benchmarks only evaluate models on in-domain test sets without considering their robustness under test-time perturbations or adversarial attacks. To fill this important gap, we construct AdvRACE (Adversarial RACE), a new model-agnostic benchmark for evaluating the robustness of MRC models under four different types of adversarial attacks, including our novel distractor extraction and generation attacks. We show that state-of-the-art (SOTA) models are vulnerable to all of these attacks. We conclude that there is substantial room for building more robust MRC models and our benchmark can help motivate and measure progress in this area. We release our data and code at https://github.com/NoviScl/AdvRACE .

PaperPDFConference PDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

NoviScl/AdvRACE officialmentioned in papermentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

BenchmarkingMachine Reading ComprehensionNatural Language UnderstandingReading Comprehension

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

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