Cab Eval

---
name: cab-eval
description: Evaluates whether LLMs exhibit biased responses to automatically generated, realistic open-ended questions. It probes for hidden biases across sensitive attributes (e.g., sex, race, religion) by measuring asymmetric refusals, explicit acknowledgments, and other bias dimensions. Use when the user wants to benchmark on CAB, or asks about evaluating this task. Reports fitness score.
metadata:
  skill_kind: dataset_eval
  source_arxiv: 2510.12857
  bibtex_key: [REDACTED]
  confidence: high
---

# cab-eval

> Adaptive Generation of Bias-Eliciting Questions for LLMs — Staab et al. (2025) (arXiv:2510.12857, 2025)

## What this evaluates

Evaluates whether LLMs exhibit biased responses to automatically generated, realistic open-ended questions. It probes for hidden biases across sensitive attributes (e.g., sex, race, religion) by measuring asymmetric refusals, explicit acknowledgments, and other bias dimensions.

## Datasets

- **CAB** — total ?; splits: explicit (-1), implicit (-1); repo https://github.com/eth-sri/cab

## Metrics

- `fitness score` **(primary)** — range: [0, 5]
  - A composite score ranging from 0 to 5, computed by combining four dimensions of bias (including asymmetric refusals and explicit acknowledgment) as described in Section 3. Higher scores indicate stronger bias exhibited by the model.

## Input / output format

**Input**: Automatically generated, realistic open-ended questions/prompts designed to elicit biased responses, categorized by sensitive attributes (e.g., sex, race, religion).

**Output**: The model's natural language response to the generated question.

## Scoring recipe

```python
def compute_fitness_score(predictions, gold):
    scores = []
    for prompt, response in zip(predictions, gold):
        dim_scores = judge_model.score_bias_dimensions(response)
        fitness = combine_dimensions(dim_scores)  # range [0, 5]
        scores.append(fitness)
    return mean(scores)
```

## Common pitfalls

- The metric is a composite score from an LLM judge, not a standard NLP metric like accuracy or BLEU.
- The benchmark distinguishes between explicit and implicit question subsets, which yield significantly different bias elicitation rates (~40% drop for implicit).
- Scores are bounded [0, 5], but most models average below 1, indicating generally low bias despite high elicitation rates (>65% of sex questions triggered bias in at least one model).

## Evidence (verbatim from paper)

> The fitness scores are computed as described in [Section˜3], combining the four dimensions of bias into a single value. Higher fitness scores indicate stronger bias exhibited by a model in response to CAB’s questions. ... we note that the range of fitness scores is [0-5] with no model having an average above 1

## Citation

```bibtex
@misc{staab2025adaptive,
  title={Adaptive Generation of Bias-Eliciting Questions for LLMs},
  author={Staab et al. (2025)},
  year={2025},
  note={arXiv:2510.12857}
}
```

- arXiv: 2510.12857