Menu

Less Is Suddenly Enough — Sparse Edits and Synthetic Data Start Beating Full-Scale Post-Training
📰

Less Is Suddenly Enough — Sparse Edits and Synthetic Data Start Beating Full-Scale Post-Training

DEV Community: machinelearning·Felipe 0liveira·3 days ago
#8DPvdDxA
Reading 0:00
15s threshold

This digest covers post-training and fine-tuning developments from 2026-11-06 to 2026-11-13, across arXiv, the Hugging Face blog, Together AI, Interconnects, and Latent Space.

🔥 Highlights

Human or Synthetic? What a Fixed Budget Buys for Post-Training — synthetic preference data wins hard at low budgets.

The Surprising Effectiveness of Deleting Weights in LLM Post-Training — zeroing 0.05% of weights matches full fine-tuning.

Rethinking "RL Generalizes, SFT Memorizes": The Role of SFT Data — data mix, not algorithm, drives generalization.

SafetyPulse: Catching Safety Drift During Fine-Tuning by Reading the Model's Refusal Circuit — a live monitor for alignment decay.

A Theory of Policy Optimization in Post-Training: Coverage Collapse and Reference Resets — a theoretical fix for stalled RLHF/GRPO runs.

arXiv (cs.CL / cs.LG)

PORT: Preference Optimization via Robust Token-Level Reweighting — 2026-11-09.…

Continue reading — create a free account

Join HashtagPLUS to read full articles, follow hashtags, vote, and join the conversation.