Benchmarks › BBQ

BBQ

Benchmark measures social biases against people belonging to protected classes along nine social dimensions relevant for U.S. English-speaking contexts.

Full title

BBQ: A Hand-Built Bias Benchmark for Question Answering

Tag

bbq (use this to limit an assistant's search to this benchmark)

Reference

arxiv.org/abs/2110.08193

BenchRisk

Scored 2025-04-01 · 41 mitigations adopted, 145 absent · score page · source entry

Documents available to assistants

Summary from the reference

It is well documented that NLP models learn social biases, but little work has been done on how these biases manifest in model outputs for applied tasks like question answering (QA). We introduce the Bias Benchmark for QA (BBQ), a dataset of question sets constructed by the authors that highlight attested social biases against people belonging to protected classes along nine social dimensions relevant for U.S. English-speaking contexts. Our task evaluates model responses at two levels: (i) given an under-informative context, we test how strongly responses reflect social biases, and (ii) given an adequately informative context, we test whether the model's biases override a correct answer choice. We find that models often rely on stereotypes when the context is under-informative, meaning the model's outputs consistently reproduce harmful biases in this setting. Though models are more accurate when the context provides an informative answer, they still rely on stereotypes and average up to 3.4 percentage points higher accuracy when the correct answer aligns with a social bias than when it conflicts, with this difference widening to over 5 points on examples targeting gender for most models tested.

Ask an assistant about it

Once your assistant is connected, try a question such as “Using the benchmark sources, how is BBQ scored?”

Developers can restrict a search to this benchmark with the filter {"benchmark": "bbq"} on the MCP endpoint https://ns-f1fc49e3-9bca-4aa2-b5a1-ef5dbc18588f.search.ai.cloudflare.com/mcp.