Human Feedback Types
strongCritique Edit
Directly usable for protocol triage.
"International Classification of Diseases (ICD) coding assigns diagnosis codes to clinical documents and is essential for healthcare billing and clinical analysis."
HFEPX · Eval paper review
From Documents to Spans: Scalable Supervision for Evidence-Based ICD Coding with LLMs
Xu Zhang, Wenxin Ma, Chenxu Wu, Rongsheng Wang +4 more
Published
Mar 16, 2026
Citations
0
Trust level
Moderate
Usefulness score
65/100 (Medium)
Extraction confidence
70% (Moderate)
Derived from extracted protocol signals and abstract evidence.
Rater population
Not reported
Signals refreshed
May 7, 2026
Should you rely on this paper?
This paper has useful evaluation signal, but protocol completeness is partial; pair it with related papers before deciding implementation strategy.
Use this for comparison and orientation, not as your only source.
Best use
Secondary protocol comparison source
Use if you need
A secondary eval reference to pair with stronger protocol papers.
What to verify
Validate the evaluation procedure and quality controls in the full paper before operational use.
Main weakness
No major weakness surfaced.
Human feedback signal
Detected
From extracted signals
Evaluation signal
Detected
Eval setup described
Usefulness for eval research
65/100
Moderate-confidence candidate
Useful as a secondary reference; validate protocol details against neighboring papers.
If you are doing eval pipeline work, start here
Abstract
International Classification of Diseases (ICD) coding assigns diagnosis codes to clinical documents and is essential for healthcare billing and clinical analysis. Reliable coding requires that each predicted code be supported by explicit textual evidence. However, existing public datasets provide only code labels, without evidence annotations, limiting models' ability to learn evidence-grounded predictions. In this work, we argue that dense, document-level evidence annotation is not always necessary for learning evidence-based coding. Instead, models can learn code-specific evidence patterns from local spans and use these patterns to support document-level evidence-based coding. Based on this insight, we propose Span-Centric Learning (SCL), a training framework that strengthens LLMs' coding ability at the span level and transfers this capability to full clinical documents. Specifically, we use a small set of annotated documents to supervise evidence recognition, aggregation, and code assignment, while leveraging a large collection of lightweight evidence spans to reinforce span-level reasoning. Due to their compactness, span annotations are scalable and can be further augmented through synthesis. Under the same Llama3.1-8B backbone, our approach achieves an 8.2-point improvement in macro-F1 at only 20% of the training cost of standard SFT, and provides explicit supporting evidence for each predicted code, enabling human auditing and revision.
What we could verify
These are the protocol signals we could actually recover from the available paper metadata. Use them to decide whether this paper is worth deeper reading.
Evaluation Modes
strongAutomatic Metrics
Includes extracted eval setup.
"International Classification of Diseases (ICD) coding assigns diagnosis codes to clinical documents and is essential for healthcare billing and clinical analysis."
Quality Controls
missingNot reported
No explicit QC controls found.
"International Classification of Diseases (ICD) coding assigns diagnosis codes to clinical documents and is essential for healthcare billing and clinical analysis."
Benchmarks / Datasets
missingNot extracted
No benchmark anchors detected.
"International Classification of Diseases (ICD) coding assigns diagnosis codes to clinical documents and is essential for healthcare billing and clinical analysis."
Reported Metrics
strongF1, F1 macro
Useful for evaluation criteria comparison.
"International Classification of Diseases (ICD) coding assigns diagnosis codes to clinical documents and is essential for healthcare billing and clinical analysis."
Benchmarks and datasets
No benchmark or dataset names were extracted from the available abstract.
Reported metrics
f1f1 macro
Human feedback details
- Uses human feedback
- Yes
- Feedback types
- Critique Edit
- Rater population
- Not reported
- Expertise required
- Medicine, Coding
Evaluation details
- Evaluation modes
- Automatic Metrics
- Agentic eval
- None
- Quality controls
- Not reported
- Evidence quality
- Moderate
- Use this page as
- Secondary protocol comparison source
Research brief
Metadata summary
International Classification of Diseases (ICD) coding assigns diagnosis codes to clinical documents and is essential for healthcare billing and clinical analysis.
Based on abstract + metadata only. Check the source paper before making high-confidence protocol decisions.
Key takeaways
- International Classification of Diseases (ICD) coding assigns diagnosis codes to clinical documents and is essential for healthcare billing and clinical analysis.
- Reliable coding requires that each predicted code be supported by explicit textual evidence.
- However, existing public datasets provide only code labels, without evidence annotations, limiting models' ability to learn evidence-grounded predictions.
Researcher actions
- Compare this paper against nearby papers in the same arXiv category before using it for protocol decisions.
- Validate inferred eval signals (Automatic metrics) against the full paper.
- Use related-paper links to find stronger protocol-specific references.
Caveats
- Generated from abstract + metadata only; no PDF parsing.
- Signals below are heuristic and may miss details reported outside the abstract.
Recommended queries
Contribution summary
- Based on this insight, we propose Span-Centric Learning (SCL), a training framework that strengthens LLMs' coding ability at the span level and transfers this capability to full clinical documents.
- Under the same Llama3.1-8B backbone, our approach achieves an 8.2-point improvement in macro-F1 at only 20% of the training cost of standard SFT, and provides explicit supporting evidence for each predicted code, enabling human auditing and…
Why it matters for eval
- Under the same Llama3.1-8B backbone, our approach achieves an 8.2-point improvement in macro-F1 at only 20% of the training cost of standard SFT, and provides explicit supporting evidence for each predicted code, enabling human auditing and…
Researcher checklist
-
Human feedback protocol is explicit
Detected: Critique Edit
-
Evaluation mode is explicit
Detected: Automatic Metrics
-
Quality control reporting appears
No calibration/adjudication/IAA control explicitly detected.
-
Benchmark or dataset anchors are present
No benchmark/dataset anchor extracted from abstract.
-
Metric reporting is present
Detected: f1, f1 macro