BenchDrift拆評測水分

Computer Science > Computation and Language arXiv:2608.

11694 (cs) [Submitted on 12 Aug 2026] Title:The Wording Effect: Quantifying Two-Way Drift in LLM Benchmark Performance Authors:Shailja Thakur, Sungeun An, Chad DeLuca, Hima Patel View a PDF of the paper titled The Wording Effect: Quantifying Two-Way Drift in LLM Benchmark Performance, by Shailja Thakur and 3 other authors View PDF HTML (experimental) Abstract:A benchmark score comes from a single phrasing of each problem.

That single phrasing is treated as if it stood for the whole space of ways the same problem could be asked, but it does not.

We show that rephrasing a problem while keeping its meaning and answer fixed routinely flips a model's answer in both directions, so some failures become successes and some successes become failures.We call this drift.

BenchDrift generates meaning-preserving variations of benchmark problems along four axes, namely linguistic, referential, pragmatic, and structural, and measures how often, and why, correctness flips under each.

Across eight models and three benchmarks (GSM8K, MMLU, MATH-Hard), we observe that drift is large in both directions.Two findings stand out.First, phrasing sensitivity does not fade as models get better.Instead, it changes sign.

Weak models gain more from rephrasing than they lose, while strong models lose far more than they gain.We find that the best models on a benchmark are therefore the ones whose scores depend most on the wording they happened to be given.

Second, the models largely agree on which rephrasings cost the most correct answers even though they differ in how much they drift, so fragility belongs to the rephrasing and not to the model.

Furthermore, rephrasing breaks answers a model was confident about, whether the problem is made shorter or longer.Code and Data: this https URL Subjects: Computation and Language (cs.CL); Artificial Intelligence (cs.AI) Cite as: arXiv:2608.11694 [cs.CL] (or arXiv:2608.11694v1 [cs.

CL] for this version) https://doi.org/10.48550/arXiv.2608.

11694 Focus to learn more arXiv-issued DOI via DataCite (pending registration) Submission history From: Shailja Thakur [view email] [v1] Wed, 12 Aug 2026 06:05:47 UTC (1,955 KB) Full-text links: Access Paper: View a PDF of the paper titled The Wording Effect: Quantifying Two-Way Drift in LLM Benchmark Performance, by Shailja Thakur and 3 other authorsView PDFHTML (experimental)TeX Source view license Current browse context: cs.

CL < prev | next > new | recent | 2026-08 Change to browse by: cs cs.AI References & Citations NASA ADSGoogle Scholar Semantic Scholar export BibTeX citation Loading...BibTeX formatted citation × loading...

Data provided by: Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.

ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv (What is alphaXiv?) Links to Code Toggle CatalyzeX Code Finder for Papers (What is CatalyzeX?) DagsHub Toggle DagsHub (What is DagsHub?

) GotitPub Toggle Gotit.pub (What is GotitPub?) Huggingface Toggle Hugging Face (What is Huggingface?) ScienceCast Toggle ScienceCast (What is ScienceCast?) Demos Demos Replicate Toggle Replicate (What is Replicate?) Spaces Toggle Hugging Face Spaces (What is Spaces?) Spaces Toggle TXYZ.

AI (What is TXYZ.AI?) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower (What are Influence Flowers?) Core recommender toggle CORE Recommender (What is CORE?

) Author Venue Institution Topic About arXivLabs arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy.arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community?Learn more about arXivLabs.Which authors of this paper are endorsers?| Disable MathJax (What is MathJax?)