finding
active
finding:rlfr-ni-not-inline-achieves-31-4-2-3-overall-reduction-with-0-in-context-reductionRLFR-NI (not inline) achieves 31.4%±2.3% overall reduction with 0% in-context reduction
Ablation removing inline interventions.
Source paper
extracted_from(2026) · Aaditya Vikram Prasad · Connor Watts · Jack Merullo · Dhruvil Gala +3
Neighborhood — ranked by edge-count
Papers (1)
paper
Claims (1)
claim
- Central thesis.
Related by similarity (8)
cosine ≥ 0.65 · no typed edgeEntities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.
- Ablation of BoN.
- SFT on correction+retraction data gives 39.4% inline overall reduction and 9.6% not-inline, well below RLFRfinding0.826SFT baseline comparison.
- Decomposition component.
- Topline result.
- Even stylistic distribution.
- RLFR policy matches base on standard benchmarks (e.g., MMLU 67.2 vs 69.2, GSM8K 73.0 vs 72.3)finding0.753No capability degradation.
- Comparable to RLFR-NI.
- Main evaluation result showing best variant outperforms many proprietary and open-source baselines of comparable or larger sizes.