Provenance-grounded gating and adaptive recovery improve synthetic post-training data curation
A controlled study examines two underexplored practices in synthetic post-training data pipelines: grounding filtering signals in source provenance and systematically recovering rejected samples rather than discarding them. Using adversarially injected corpora as ground-truth failure labels, the authors find that exact source provenance improves faithfulness gating for stronger judges, that hallucination and reward gates reject largely disjoint populations (making both necessary), and that adaptive recovery via failure diagnosis and targeted regeneration outperforms naive resampling. Generator scale is the primary driver of downstream fine-tuning quality, with filtration and recovery contributing meaningfully but secondarily.
Related guides (2)
Related events (8)
Interpretability-based pipeline for auditing and shaping post-training learning signals
Researchers introduce a data-centric post-training pipeline that applies interpretability methods to preference datasets before optimization, surfacing latent concepts that separate preferred from dispreferred generations. The approach unifies several interpretability-based training protocols as feature or data interventions that shape reward signals. Empirically, the pipeline diagnoses undesirable signals such as sycophancy and over-stylization, mitigates off-target learning, and can amplify desired properties like safety behaviors and model personality. The work reframes post-training from opaque scalar reward optimization into an auditable, concept-level sculpting process.
Activation Steering for Synthetic Safety Data Generation: Diversity as a Critical Quality Axis
This paper investigates whether activation steering (AS) can generate high-quality synthetic training data for downstream safety detection classifiers, filling a gap in the literature. Across 4 safety concepts × 2 models × 4 steering methods, the authors find that AS-generated data outperforms prompt-generated data on 3 of 4 concepts, but only 41 of 136 configurations succeed, indicating a narrow effective regime. The study introduces sample- and set-level diversity as a previously absent quality axis, finding that higher steering strength reduces diversity and that the harmonic mean of success, coherence, and diversity correlates more reliably with downstream AUROC than prior metrics alone. The results provide a practical heuristic for practitioners tuning AS hyperparameters for safety data generation.
Retrying vs Resampling in AI Control: Safety Tradeoffs in Coding Scaffolds
This paper analyzes two strategies for handling flagged actions in AI coding scaffolds—retrying (blocking risky actions and continuing) and resampling (drawing multiple samples from the same context)—from an AI control perspective that treats the model as potentially adversarial. The authors find that retrying backfires because the untrusted model can exploit monitor rationale to craft stealthier attacks, while resampling avoids this information leakage. Using Claude Opus 4.6 as the untrusted model and MiMo-V2-Flash as the monitor on the BashArena benchmark, they show that drawing five samples per step and auditing on maximum suspicion score raises safety from 61% to 71% at a 0.3% audit budget. Two findings contradict prior work: auditing on maximum (not minimum) suspicion scores is better, and executing the least suspicious sample yields only marginal safety gains.
Failed reasoning traces encode recoverability structure for test-time routing and post-training analysis
A new arXiv paper argues that failed reasoning traces from post-trained LLMs contain exploitable signal about whether failures are recoverable via resampling or require structural intervention. The authors derive three trajectory features from the distributional signature of failed rollouts (not their text content) that cluster failures into stable regimes and characterize failure topography across post-training methods with 84.3% accuracy. A training-free routing rule built on these features lifts rescue rates by +12.2% on a deployment-relevant hard subset, and the features transfer across model families. The work reframes failed traces as diagnostic objects rather than discarded data, with implications for inference-time compute allocation and post-training analysis.
Meta Research Improves Image Generation via Staged Planning and Self-Revision Fine-Tuning
Researchers from Meta and collaborating universities propose a fine-tuning method that teaches image generators to compose images through discrete plan-sketch-inspect-refine cycles rather than generating all at once. Starting from BAGEL-7B, they construct ~62,000 training examples using GPT-4o and FLUX.1 Kontext to supervise each stage, achieving 83% on GenEval versus 77% for the base model and a competing method (PARM) that required 11x more training data and ~8x more inference steps. The approach improves spatial relationship accuracy, object attribute fidelity, and real-world knowledge grounding in generated images.
Step-aligned critique outperforms GRPO and reference-solution conditioning in self-distillation
A new arXiv paper investigates context design for self-distillation of language models, comparing binary reward (GRPO), reference solutions, and step-by-step critiques aligned to the solver's reasoning trace. Step-aligned critique yields the largest gains, outperforming GRPO by 16.11 points and reference-solution conditioning by 5.27 points on Avg@12. Per-token advantage analysis shows that step-aligned feedback targets only failing tokens, avoiding unnecessary pressure on already-correct reasoning steps. The findings suggest structural alignment between feedback and the model's reasoning trace is a key driver of self-distillation effectiveness.
Self-Generated Replay Nearly Eliminates Catastrophic Forgetting in Language Models
This paper investigates catastrophic forgetting in language models during continual learning, finding that models can use self-generated samples from their own training distribution as effective replay data, nearly eliminating forgetting without requiring stored exemplars. The authors identify two key conditions where forgetting persists: when models are pretrained near capacity saturation (leaving no room for new knowledge), and when low learning rates are used to reduce forgetting at the cost of requiring far more training steps. Self-generated replay breaks this learning-rate/forgetting tradeoff, enabling fast high-learning-rate finetuning without degradation on prior tasks.
PGT: Procedurally Generated Tasks for Improving Visual Grounding in MLLMs
This paper introduces Procedurally Generated Tasks (PGT), a data-driven framework that overlays geometric primitives on images to create dense supervision signals for fine-grained visual grounding in multimodal large language models. PGT serves both as a training augmentation method and a diagnostic tool to isolate perception failures from semantic priors. Instruction tuning on LLaVA-v1.5-Instruct augmented with PGT data yields gains of up to +20% on the What'sUp benchmark and +13.3% on CV-Bench-2D. The results suggest that spatial reasoning deficits in MLLMs stem primarily from inadequate supervision rather than architectural or resolution constraints.