natolambert's picture
update
9ceb843
raw history blame
No virus
3.05 kB
ABOUT_TEXT = """
We compute the win percentage for a reward model on hand curated chosen-rejected pairs for each prompt.
A win is when the score for the chosen response is higher than the score for the rejected response.
### Subset summary
| Subset | Num. Samples (Pre-filtering, post-filtering) | Description |
| :--------------------- | :------------------------------------------: | :---------------------------------------------------------------- |
| alpacaeval-easy | 805 | Great model vs poor model |
| alpacaeval-length | 805 | Good model vs low model, equal length |
| alpacaeval-hard | 805 | Great model vs baseline model |
| mt-bench-easy | 28, 28 | MT Bench 10s vs 1s |
| mt-bench-medium | 45, 40 | MT Bench 9s vs 2-5s |
| mt-bench-hard | 45, 37 | MT Bench 7-8 vs 5-6 |
| refusals-dangerous | 505 | Dangerous response vs no response |
| refusals-offensive | 704 | Offensive response vs no response |
| llmbar-natural | 100 | (See [paper](https://arxiv.org/abs/2310.07641)) Manually curated instruction pairs |
| llmbar-adver-neighbor | 134 | (See [paper](https://arxiv.org/abs/2310.07641)) Instruction response vs. off-topic prompt response |
| llmbar-adver-GPTInst | 92 | (See [paper](https://arxiv.org/abs/2310.07641)) Instruction response vs. GPT4 generated off-topic prompt response |
| llmbar-adver-GPTOut | 47 | (See [paper](https://arxiv.org/abs/2310.07641)) Instruction response vs. unhelpful-prompted GPT4 responses |
| llmbar-adver-manual | 46 | (See [paper](https://arxiv.org/abs/2310.07641)) Challenge set chosen vs. rejected |
| XSTest | 450 | TODO curate |
| (?) repetitiveness | | |
| (?) grammar | | |
For more details, see the [dataset](https://huggingface.co/datasets/ai2-rlhf-collab/rm-benchmark-dev).
"""