Paper on Predicting Memorization Before Fine-Tuning Accepted to EACL 2027
niloofar_mire · x · 2026-11-14
Jaydeep Borkar announced that "Predicting Memorization Before Fine-Tuning Language Models," co-authored with Niloofar Mireshghallah and David A. Smith, has been accepted to the EACL 2027 Main Conference. The paper addresses predicting memorization behavior before fine-tuning; details are yet to be released.
More from Research
- Yamanaka lab preprint: partial reprogramming outcomes diverge sharply by cell lineage — MaxUnfried · 2026-11-14
- New paper speeds up Delaunay-based nearest neighbor search with grid queries and parallel construction — ssh4net · 2026-11-14
- Runway open-sources Praxis-1: 27B robot model trained on web video, tops RoboLab-120 at 46.2% — iamfakhrealam · 2026-11-14
- Olmo 3 32B uses a 55x compute multiplier on code in its training mix — DZhang50 · 2026-11-14
- HarborRL update adds elastic scaling, SSH-free cluster deployment for agentic RL training — Dear_Treat3688 · 2026-11-14
- q6 vs q8 A/B testing at 300-400k context shows quantization loss amplified — Viktri1 · 2026-11-14