Expert QA Pipeline (EMNLP 2026 Industry, Anonymous)
Collection
Anonymous SFT checkpoint release for EMNLP 2026 Industry submission. • 172 items • Updated
emnlp2026_expertqa_phi4-mini_exp0_finance_seed2
SFT checkpoint from the EMNLP 2026 Industry Track submission A Factorial Ablation of a Speech-to-SFT Pipeline: Differential Effects on Data Quality and Downstream Transfer (anonymous).
| Field | Value |
|---|---|
| Pipeline condition | Exp 0 (baseline (no refinement)) |
| Domain | finance |
| Seed | 2 |
| Base model | microsoft/Phi-4-mini-instruct |
| Training | LoRA (rank 16, α=32, QLoRA 4-bit, lr 2e-4, 3 epochs) |
| Upstream STT | In-house STT (paper main pipeline) |
| License | CC BY-NC 4.0 (research and non-commercial use only) |
Intended use: research and non-commercial use only, matching the consent scope of the source audio.
Companion repository (code, configs, prompts, sample QA): https://anonymous.4open.science/r/anon-emnlp2026-expertqa-7616
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for Korshort/emnlp2026_expertqa_phi4-mini_exp0_finance_seed2
Base model
microsoft/Phi-4-mini-instruct