[1/6][Builtin Judges] Conversational Safety Judge#19106
[1/6][Builtin Judges] Conversational Safety Judge#19106B-Step62 merged 7 commits intomlflow:masterfrom
Conversation
Signed-off-by: joelrobin18 <joelrobin1818@gmail.com>
Signed-off-by: joelrobin18 <joelrobin1818@gmail.com>
|
Documentation preview for 8b309b1 is available at: Changed Pages (1) More info
|
AveshCSingh
left a comment
There was a problem hiding this comment.
Thank you for contributing this PR, @joelrobin18 ! I've let some comments inline.
I've also requested review from Xiang, who has also been implementing new judges recently.
|
Also, can you run some sanity checks on conversations that should and should not be marked as safe, and include these in the PR description? For these, I'd recommend using a modern but low-cost LLM, like gpt-oss-120b or gpt5-mini |
Signed-off-by: joelrobin18 <joelrobin1818@gmail.com>
AveshCSingh
left a comment
There was a problem hiding this comment.
Thanks for addressing my comments Joel. I left two more, and am also going to add Yuki for review, since you'll need a committer's approval to merge the PR
| - Detailed instructions for illegal activities, weapons, or dangerous substances | ||
| - Content that exploits or endangers minors | ||
| - Explicit encouragement of self-harm or harm to others | ||
|
|
There was a problem hiding this comment.
It's strange that these diverge from the Safety guidelines. Could you limit this judge to hate speech, harassment, incitement of violence, and the promotion of illegal or severely harmful acts?
There was a problem hiding this comment.
Can you review if the current prompt is fine for Conversational Safety?
There was a problem hiding this comment.
Looks good --thanks for iterating on this
Signed-off-by: joelrobin18 <joelrobin1818@gmail.com>
| - Detailed instructions for illegal activities, weapons, or dangerous substances | ||
| - Content that exploits or endangers minors | ||
| - Explicit encouragement of self-harm or harm to others | ||
|
|
There was a problem hiding this comment.
Looks good --thanks for iterating on this
Signed-off-by: joelrobin18 <joelrobin1818@gmail.com>
🛠 DevTools 🛠
Install mlflow from this PR
For Databricks, use the following command:
Related Issues/PRs
Towards #19061
What changes are proposed in this pull request?
Conversational Safety Judge.
This PR introduces a new built-in judge and scorer for evaluating the safety of multi-turn conversations. Unlike the existing Safety scorer which evaluates individual responses, this new feature analyzes entire conversations for various safety concerns.
How is this PR tested?
Example
Safe convo:
Result:
Safe convo example 2:
Result:
Unsafe Convo:
Result:
Does this PR require documentation update?
Release Notes
Is this a user-facing change?
This PR introduces a new built-in judge and scorer for evaluating the safety of multi-turn conversations. Unlike the existing Safety scorer which evaluates individual responses, this new feature analyzes entire conversations for various safety concerns.
What component(s), interfaces, languages, and integrations does this PR affect?
Components
area/tracking: Tracking Service, tracking client APIs, autologgingarea/models: MLmodel format, model serialization/deserialization, flavorsarea/model-registry: Model Registry service, APIs, and the fluent client calls for Model Registryarea/scoring: MLflow Model server, model deployment tools, Spark UDFsarea/evaluation: MLflow model evaluation features, evaluation metrics, and evaluation workflowsarea/gateway: MLflow AI Gateway client APIs, server, and third-party integrationsarea/prompts: MLflow prompt engineering features, prompt templates, and prompt managementarea/tracing: MLflow Tracing features, tracing APIs, and LLM tracing functionalityarea/projects: MLproject format, project running backendsarea/uiux: Front-end, user experience, plotting, JavaScript, JavaScript dev serverarea/build: Build and test infrastructure for MLflowarea/docs: MLflow documentation pagesHow should the PR be classified in the release notes? Choose one:
rn/none- No description will be included. The PR will be mentioned only by the PR number in the "Small Bugfixes and Documentation Updates" sectionrn/breaking-change- The PR will be mentioned in the "Breaking Changes" sectionrn/feature- A new user-facing feature worth mentioning in the release notesrn/bug-fix- A user-facing bug fix worth mentioning in the release notesrn/documentation- A user-facing documentation change worth mentioning in the release notesShould this PR be included in the next patch release?
Yesshould be selected for bug fixes, documentation updates, and other small changes.Noshould be selected for new features and larger changes. If you're unsure about the release classification of this PR, leave this unchecked to let the maintainers decide.What is a minor/patch release?
Bug fixes, doc updates and new features usually go into minor releases.
Bug fixes and doc updates usually go into patch releases.