Labelled responses from remote datasets can't reach `HumanLabeledDataset`
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 4.5k
- Forks
- 893
- Avg merge
- 3d 50m
- Merged PRs (30d)
- 165
Description
There's no path from the remote dataset loaders to the labelled-data side of scoring.
**What's there now.** `HumanLabeledDataset` is only constructible via `from_csv()`, so scorer evaluation data has to be authored by hand. That's reflected in `datasets/scorer_evals/` — `refusal.csv` is ~105 rows and several of the objective sets are single digits.
**What's being dropped.** `datasets/seed_datasets/remote/` has 61 loaders, and several of the underlying HuggingFace datasets ship human labels alongside model responses. Those are discarded at load time because `SeedDataset` models prompts only. `beaver_tails_dataset.py` states it directly:
> This loader extracts only the prompts (not the responses) and filters to unsafe entries by default.
`aegis_ai_content_safety_dataset.py` is the same shape. `wildguardmix_dataset.py` at least retains its classifier labels in `metadata`, but still produces a `SeedDataset`.
So labelled `(response, score)` pairs are already flowing through the loaders and being dropped, while the one class that needs them can only be fed by hand.
**Proposal.** A second output path off the existing remote loaders producing `HumanLabeledDataset` — reusing the fetch logic and the `HARM_CATEGORY_ALIAS_OVERRIDES` mapping that's already there, but retaining `assistant_response` and the human label.
Suggest starting narrow: Aegis 2.0 only (CC-BY-4.0, so no licence friction for a repo shipping under MIT) and one harm category that maps cleanly, with tests and a generated `scorer_evals` CSV so it's usable on merge.
Happy to build it if the shape is right — is `HumanLabeledDataset` the correct target here, or is there a reason the loaders are prompts-only that I'm missing?
Contributor guide
No contributing guide indexed for this repository
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start with datasets/seed_datasets/remote/aegis_ai_content_safety_dataset.py and the HumanLabeledDataset path, then compare the existing HARM_CATEGORY_ALIAS_OVERRIDES mapping and loader behavior with datasets/scorer_evals/refusal.csv. Add focused tests for the narrow Aegis 2.0 case and generate a usable scorer_evals CSV retaining assistant_response and the selected human label.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- huggingface, python
- Domain
- data, machine-learning, testing-qa
- Issue type
- Feature
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Active
- Clarity
- Mostly clear
- Newbie friendliness
- 48/100