cs.AIJul 27, 2026

Similar Models Learn Differently: Final-Window Pretraining Shapes Post-Training Beyond SFT

Authors: Cen Lu, Yung-Chen Tang, Andrea Cavallaro

Organizations: 1EPFL · 2Idiap Research Institute

Abstract

Developers judge a model checkpoint by how it behaves. After supervised fine-tuning (SFT), two checkpoints that perform about the same across relevant benchmarks are treated as interchangeable, equally ready for the next alignment stage, typically preference optimization. We ask whether this judgment misses a pretraining imprint: a difference that no post-SFT benchmark reveals, yet that decides how each checkpoint responds to further training. To find out, we run a controlled experiment on the final window of pretraining, the last data trained on before instruction tuning. Six branches fork from one partially pretrained checkpoint and differ only in this window: 500 million tokens, 0.1% to 1% of the tokens that precede it. Each branch trains its window on a single data source: generic web text, filtered web text, normative discourse, safety text, mathematical text, or synthetic educational text. SFT and post-training are then identical. After SFT the branches behave near-identically, within about one point on instruction following, refusal, and capability, yet the same post-training carries them to very different endpoints, under both a direct preference optimization update and a reinforcement learning update with a verifiable reward. We measure this deviation through refusal of harmful requests: when post-training begins the safety text branch refuses no more than the web text branch, yet by the end it has lost far less of its refusal. The other four branches gain little or no protection, so the effect is selective to what the window contained. The protection requires the safety text to arrive last rather than earlier in pretraining, and it reproduces on a second model family. What a model is pretrained on last shapes how it reacts to alignment. Therefore, a checkpoint should not be evaluated by its post-SFT behavior alone, and what it was trained on last should be reported with it.

Explore similar work

CardsList
Sep 8, 2026cs.AI

Good Pretraining, Bad SFT: Checkpoint Quality Across the Training Stack

Language-model checkpoints are commonly selected by pretraining loss or benchmark scores, assuming that the highest-scoring checkpoint will remain the best starting point for subsequent training. We show that this assumption can fail in a full 30B mixture-of-experts training pipeline. The checkpoints that perform better after the full downstream training stack also have higher solution density, i.e., retain downstream performance under local weight perturbations.
Sohir Maskey, Philipp Scholl, Jonas Knupp +2
Model CheckpointsModel PretrainingDownstream Fine-TuningDownstream Reasoning
AskPDF
May 8, 2026cs.LG

The Convergence Gap: Instruction-Tuned Language Models Stabilize Later in the Forward Pass

Final outputs hide when a checkpoint commits to its next-token prediction. We introduce the convergence gap, a model-diffing diagnostic that decodes each layer's next-token distribution and measures its distance to the model's own final distribution. Across six paired pretrained and instruction-tuned checkpoints in native prompting regimes, instruction-tuned checkpoints remain farther from their final predictions later into the stack. The effect persists under endpoint-matched raw and tuned readouts, endpoint-free same-history checks, and fixed-history template replay. Matched-prefix interventions identify late MLP windows as the largest tested leverage point: late IT grafts into PT hosts increase late KL by +0.34 nats, while PT-late swaps into IT hosts reduce it by -0.51 nats; matched random late perturbations give only +0.003 versus +0.327 for the true late graft. A preselected Gemma case study provides behavior-facing plausibility for the same late swap, without serving as a benchmark claim. These results identify a robust predictiondynamics signature of post-training: released instruction-following checkpoints tend to settle later, and late MLP computation is the strongest tested bidirectional handle on that delay under matched histories.
Yifan Zhou
Instruction TuningIntermediate CheckpointsNext-Token PredictionSingle Forward PassMultilayer PerceptronsOptimization Convergence Analysis+1
AskPDF
Sep 3, 2026cs.CL

Beyond Shallow Alignment: How Post-Training Methods Determine Refusal Circuits And Steering Robustness

How do the methods used to train language models to refuse harmful requests shape how that refusal actually works inside the model? We compare three post-training methods - supervised fine-tuning, reasoning-augmented fine-tuning (training on reasoning chains that justify a safety decision), and preference optimization (ORPO) - across three architecturally distinct models (Llama-3.1-8B, Gemma-2-9B, Qwen3-8B). We find that training method, not just data, reshapes how refusal is computed internally: reasoning-augmented training consistently produces a distinct kind of refusal computation, visible across all three models, while architecture independently shapes internal structure and how reliably refusal can be steered. Most importantly, no method we study achieves all three properties we would want from safe alignment at once: refusal that isn't concentrated in a few fragile components, safety gains that don't cost general capability, and safety behavior correctable through small, targeted edits. We caution against treating current post-training methods as a solved, reliable defense, especially for security-critical use. Code and models are available in https://github.com/hoangcuongnguyen2001/Beyond-Shallow-Alignment.
Hoang Cuong Nguyen, Mark Dras, Usman Naseem
RefusalsLarge Language Model AlignmentPost-TrainingAI Safety AlignmentSteering
AskPDF