Bbh Prompting Eval

---
name: bbh-prompting-eval
description: Tests the impact of prompt structure and logical validity on language model reasoning performance. Specifically, it compares answer-only, standard chain-of-thought, and logically invalid chain-of-thought prompting strategies on complex reasoning tasks. Use when the user wants to benchmark on BIG-Bench Hard, or asks about evaluating this task. Reports accuracy.
metadata:
  skill_kind: dataset_eval
  source_arxiv: 2307.10573
  bibtex_key: schaeffer2023invalidlogic
  confidence: high
---

# bbh-prompting-eval

> Invalid Logic, Equivalent Gains: The Bizarreness of Reasoning in Language Model Prompting — Schaeffer et al. (2023) (arXiv:2307.10573, 2023)

## What this evaluates

Tests the impact of prompt structure and logical validity on language model reasoning performance. Specifically, it compares answer-only, standard chain-of-thought, and logically invalid chain-of-thought prompting strategies on complex reasoning tasks.

## Datasets

- **BIG-Bench Hard** — total ?; splits: test (-1)

## Metrics

- `accuracy` **(primary)** — range: [0, 1]
  - Standard classification accuracy: the proportion of correctly predicted answers out of the total number of questions.

## Input / output format

**Input**: Task description, few-shot examples, and a target question formatted according to one of three prompt types: Answer Only (AO), Chain-of-Thought (CoT), or Logically Invalid Chain-of-Thought (CoT Invalid).

**Output**: A single predicted answer (e.g., a number, word, or multiple-choice option) corresponding to the target question.

## Scoring recipe

```python
correct = 0
for pred, gold in zip(predictions, gold_labels):
    if pred == gold:
        correct += 1
accuracy = correct / len(gold_labels)
```

## Common pitfalls

- Assuming logically invalid CoT prompts are ineffective; the study shows they often achieve performance gains comparable to logically valid CoT prompts.
- Overlooking that some previously published 'valid' CoT prompts already contain logical errors, which confounds claims that performance gains stem from genuine reasoning.

## Evidence (verbatim from paper)

> The Accuracy of Codex on each of the BIG-Bench Hard (BBH) tasks under each of the three prompt types (Answer Only, Chain-of-Thought, Logically Invalid Chain-of-Thought) is displayed in Fig. 3. We found that Chain-of-Thought prompting beats Answer Only prompting, but Logically Invalid Chain-of-Thought is close behind Chain-of-Thought and better than Answer Only (Fig. 4 top).

## Citation

```bibtex
@misc{schaeffer2023invalidlogic,
  title={Invalid Logic, Equivalent Gains: The Bizarreness of Reasoning in Language Model Prompting},
  author={Schaeffer et al. (2023)},
  year={2023},
  note={arXiv:2307.10573}
}
```

- arXiv: 2307.10573