ACI-Bench: Clinical Dialogue to Structured Note Conversion Benchmark

ACI-Bench-MedARC evaluates model performance in converting clinical dialogue into structured clinical notes. The dataset includes the benchmark and data from ablation studies testing different transcription methods. It was uploaded by mkieffer to HuggingFace and last updated on 2026-01-18.

Use Cases

• Benchmarking model performance on clinical note generation based on dialogue transcripts.
• Ablation studies on the impact of different transcription methods (e.g., ASR vs. corrected ASR) on downstream note quality.
• Training models for automated clinical documentation from doctor-patient conversations.

Strengths

• Includes ablation study data comparing different transcription versions, such as 'asr' and 'asrcorr'.
• Provides structured splits for training, validation, and multiple test sets (test1, test2, test3).

Limitations

• Column-level documentation is absent; field semantics must be inferred after download.
• Row count is unknown, which may limit suitability assessment.
• Last updated 2026-01-18 06:18:20; freshness should be verified.

Provenance

Source

mkieffer (uploader) on HuggingFace; original authors unspecified.

Collection Method

Likely derived from clinical dialogues and structured note annotations for benchmark evaluation.

Freshness

Last updated 2026-01-18 06:18:20.