56,886 responses from 57 respondents to 998 items.
One of 21 tables from the same source; this one is the bbq_helm table. The others are listed under Related tables.
| Description | AI models as respondents: 57 large language models scored on 998 items of BBQ (HELM subset), multiple-choice questions about people in ambiguous or disambiguated contexts, a 1,000-question HELM sample scored for a different set of models from jiang_2026_openeval_bbq (falcon-40b-instruct, falcon-7b-instruct and one item are left out: OpenEval stores them twice with conflicting scores). resp is 1 if the model's answer matched the reference (quasi exact match). From the OpenEval archive (Hugging Face Open-Eval-Commons/OpenEval, revision 23a1ded9), scores only, one run per model x item. id = model name, verbatim (aliases and case variants not merged). Respondents are not independent: many models share base weights, decoding temperature varies across models (cov_temperature), and items may appear in training data. |
|---|---|
| Reference | Jiang, H., Zhang, S., Zhu, D., Bai, Y., Truong, S. T., Yi, X., Koyejo, S., Xie, X., & Xiao, Z. (2026). AI Evaluation Should Require Standardized Item-Level Data Releases. arXiv:2604.03244 (v2). Benchmark: Parrish, A., et al. (2022). BBQ: A Hand-Built Bias Benchmark for Question Answering. Findings of ACL 2022. https://aclanthology.org/2022.findings-acl.165/ |
| DOI | 10.48550/arXiv.2604.03244 |
| Licence | CC BY-NC 4.0 |
| Source data | https://huggingface.co/datasets/Open-Eval-Commons/OpenEval/tree/23a1ded985b3c2cdaaddb27581a35bfabe0ad7e7 |
| Responses | 56,886 |
|---|---|
| Respondents | 57 |
| Items | 998 |
| Response categories | 2 |
| Responses per respondent | 998 |
| Responses per item | 57 |
| Density | 1 |
| Longitudinal | FALSE |
| age range | Not applicable (non-person) |
|---|---|
| sample | AI/model |
| construct type | Cognitive/educational, Opinion/attitude |
| measurement tool | Test |
| item format | Likert Scale/selected response |
| primary language(s) | eng |
| construct name | BBQ social bias in question answering |
This codebook is reconstructed by the IRW from the IRW data standard and the script that built it, jiang_2026_openeval.py. It is our best reading, not the source’s own codebook, and it may contain mistakes. Where the two disagree, the source data are the authority. If you find an error, please tell us.
| Column | What it is | Source column |
|---|---|---|
| IRW standard columns | ||
id | IRW standard Identifier for the focal unit being measured — typically a person, but sometimes another entity (e.g., a word in a lexical task). | made in the build script |
item | IRW standard Item identifier. | made in the build script |
resp | IRW standard Response value. | made in the build script |
| Respondent covariates | ||
cov_model_size | Covariate | made in the build script |
cov_temperature | Covariate | made in the build script |
What item codes and covariate values stand for is in the codebook released with the source data.
Licence: CC BY-NC 4.0 — non-commercial use only.
Or load it directly in R or Python (both need a free Redivis account; the first call opens a browser to sign in):
# R
install.packages("remotes")
remotes::install_github("itemresponsewarehouse/Rpkg")
library(irw)
df <- irw_fetch("jiang_2026_openeval_bbq_helm")
# Python
pip install irw
import irw
df = irw.fetch("jiang_2026_openeval_bbq_helm")
@misc{https://doi.org/10.48550/arxiv.2604.03244,
doi = {10.48550/ARXIV.2604.03244},
url = {https://arxiv.org/abs/2604.03244},
author = {Jiang, Han and Zhang, Susu and Zhu, Dongyao and Bai, Yuzhuo and Truong, Sang T. and Yi, Xiaoyuan and Koyejo, Sanmi and Xie, Xing and Xiao, Ziang},
keywords = {Artificial Intelligence (cs.AI), Computers and Society (cs.CY), Databases (cs.DB), FOS: Computer and information sciences, FOS: Computer and information sciences},
title = {AI Evaluation Should Require Standardized Item-Level Data Releases},
publisher = {arXiv},
year = {2026},
copyright = {Creative Commons Attribution 4.0 International}
}
| IRW version | v584 |
|---|---|
| Redivis dataset | item_response_warehouse_6 v5.11 |
| Redivis dataset DOI | 10.57761/qahq-j855 |
| Manifest pin for this IRW version | v5.11 |
| Metadata source | irw_meta v44.0 |