MentalHealth (MedHELM)

MedHELM's private counseling task: generate the next English counselor turn from dialogue history and score it with an LLM jury.

Also known as: MedHELM MentalHealth, mental_health_accuracy

unassessed

This page is a discovery lead. Nobody has yet assessed it against the catalogue contract, so it carries no disposition. Absence of evidence here is not evidence of staleness.
Categorydomain
Subcategorycounseling-response generation (LLM jury)
Page statusactive
Metricmental_health_accuracy (HELM LLM-jury average of accuracy, completeness, clarity, each 1-5)
Directionhigher_is_better
Unitpoints
PublisherStanford CRFM and collaborators (MedHELM)

What it measures

This id is HELM's mental_health scenario in MedHELM, not a public therapy dataset and not a psychiatric diagnostic exam. The model reads an English conversation history labelled with counselor and client turns, plus topic and dialogue-type fields, and must write the next counselor response. HELM scores that text with an LLM jury on accuracy, completeness and clarity. Inputs and outputs are English text.

Task format

Generation. Instruction: "Given a mental health conversation history, generate an empathetic and appropriate counselor response." Output noun Counselor response. max_tokens 512 in the run spec; some MedHELM private entries raise num_output_tokens to 4000. The scenario emits only TEST_SPLIT. get_generation_adapter_spec defaults to five train instances, but no train split exists, so the protocol is effectively zero-shot.

Models reporting this benchmark

No model card in ModelSpec reports this benchmark yet.

Data

This page as JSON · Edit on GitHub