Direction, evidence grade, and study type are AI-generated labels (gpt-5-mini), not human-verified. Syntheses are LLM-written. "Tensions" are machine-detected candidates, not confirmed contradictions. A research-acceleration tool, not peer review.
How this is built →
2Distinct papers
1Unique collaborators
2/2Semantic Scholar citation coverage
Publication span: 2026. Corpus fetch span: 2026.
Identity provenance
Provider IDs
- Semantic Scholar:
2455186055
ORCID evidence
No valid ORCID is stored.
Observed aliases (1)
- Yefei Chen (semantic scholar, provider refresh)
Topics and outcomes in this view
Assessment themes
- Org Design: 2 papers
- Productivity: 2 papers
- Adoption: 1 paper
- Human Ai Collab: 1 paper
- Innovation: 1 paper
Claim outcomes
- Decision Quality: 2 papers
- Organizational Efficiency: 2 papers
- Skill Obsolescence: 1 paper
- Output Quality: 1 paper
- Regulatory Compliance: 1 paper
- Training Effectiveness: 1 paper
Papers in the Semantic Scholar view
Latest stored Semantic Scholar author observations only. Citation counts below are from the same provider and are not combined with other services.
Scroll the table horizontally to see every column.
| Paper | Author evidence | Date | Provider citations |
|---|---|---|---|
| A decision-focused benchmark shows upgrading fine-tuned LLM specialists is context-dependent: freezing often suffices for intent classification over multiple releases, but text-to-SQL specialists can lose most of their edge in a single upgrade, and naive adapter copying fails as pretraining distance grows while label-free refresh can restore parity at lower cost.arxiv | Yefei Chen provider id |
2026-08-21 | 0 |
| Specialist ‘judgelets’ trained from scratch underperform a shared judge: splitting adapter training across rubric families cuts accuracy and safe coverage unless adapters are initialized from a shared trained judge; separately, simple learned risk-routing lets small-to-large cascades beat a single large evaluator in accuracy at lower normalized compute.arxiv | Yefei Chen provider id |
2026-07-30 | 0 |
Citation observation summary
Semantic Scholar supplied counts for 2 of 2 papers in this view; 0 are missing. The observed paper counts sum to 0 cumulative citations. This is a coverage summary, not an author score or h-index.