Pith. sign in

REVIEW 2 cited by

ECBD: Evidence-Centered Benchmark Design for NLP

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2406.08723 v1 pith:7WOHODA7 submitted 2024-06-13 cs.CL

classification cs.CL
keywords benchmarkdesignecbdcapabilitiesevidence-centeredbenchmarksdecisionsevidence
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Benchmarking is seen as critical to assessing progress in NLP. However, creating a benchmark involves many design decisions (e.g., which datasets to include, which metrics to use) that often rely on tacit, untested assumptions about what the benchmark is intended to measure or is actually measuring. There is currently no principled way of analyzing these decisions and how they impact the validity of the benchmark's measurements. To address this gap, we draw on evidence-centered design in educational assessments and propose Evidence-Centered Benchmark Design (ECBD), a framework which formalizes the benchmark design process into five modules. ECBD specifies the role each module plays in helping practitioners collect evidence about capabilities of interest. Specifically, each module requires benchmark designers to describe, justify, and support benchmark design choices -- e.g., clearly specifying the capabilities the benchmark aims to measure or how evidence about those capabilities is collected from model responses. To demonstrate the use of ECBD, we conduct case studies with three benchmarks: BoolQ, SuperGLUE, and HELM. Our analysis reveals common trends in benchmark design and documentation that could threaten the validity of benchmarks' measurements.

Discussion (0). Sign in to comment.

Forward citations

Cited by 2 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Toward Valid Measurement Of (Un)fairness For Generative AI: A Proposal For Systematization Through The Lens Of Fair Equality of Chances

    cs.CY 2025-07 accept novelty 6.0 of 10

    A Fair Equality of Chances-based framework decomposes GenAI unfairness into harms/benefits, morally arbitrary factors, and morally decisive factors to improve measurement validity.

  2. Measurement as Bricolage: Examining How Data Scientists Construct Target Variables for Predictive Modeling Tasks

    cs.HC 2025-07 conditional novelty 6.0 of 10

    Data scientists construct prediction targets through bricolage, applying five reformulation strategies (piggybacking, composing, swapping, bridging, refining) to balance five criteria: validity, simplicity, predictabi...

Pith tools