It is shown that imbalanced learning of two conflicting copy tasks promotes in-context learning and improves the selectivity of refusal fine-tuning, suggesting that imbalanced pretraining curricula may be an important tool for promoting disentangled representations, with direct consequences for the precision and reliability of safety fine-tuning.
Abstract
Transformers follow implicit curricula whereby some tasks are learned before others. However, how explicit pretraining curricula influence learning, generalization, and the selectivity of fine-tuning is unclear. This is important for AI safety, where fine-tuning is used to selectively suppress misaligned behaviors. Here, we compare curricula that pretrain tasks in a balanced (sampled uniformly) or an imbalanced (one task early, the other late) fashion. We show that imbalanced learning of two conflicting copy tasks promotes in-context learning and improves the selectivity of refusal fine-tuning. Ablations and activation patching show that this occurs because imbalanced pretraining encourages tasks to be disentangled in separable neural circuits, whereas balanced training routes both tasks through a common pathway. We extend these findings to a synthetic language learning task involving rule-consistent and rule-violating data, where imbalanced curricula similarly lead to more localized, less entangled rule representations, resulting in more robust rule-following behavior. Together, these results suggest that imbalanced pretraining curricula may be an important tool for promoting disentangled representations, with direct consequences for the precision and reliability of safety fine-tuning.
TAILS resolves cross-task ambiguity at the representation level, while leaving the original PTM, method-specific modules, and classifier unchanged, and can improve classification and task-inference performance with modest parameter overhead and negligible inference cost.
Zhiming Xu, Huiyu Yi, Zhenghe Xie et al.· 0 citations
Task Specialization Fine-Tuning (TSFT), an online framework that predicts fine-tuning performance with a simple parametric model and exactly solves the resulting discrete budget allocation problem via integer linear programming, is proposed.
Jianan Zhou, Jung-Hoon Cho, Tianyue Zhou et al.· 0 citations
It is found that narrow fine-tuning recruits a persona structure that is present in the model before the fine-tune exists, and that broad misalignment on questions unrelated to the training data is more broad than mechanical weight superposition and matched diversity jointly account for.
Large language model (LLM) post-training is essential for improving reasoning, adaptation, and alignment. Existing methods mainly follow two paradigms: reinforcement learning (RL) and on-policy distillation (OPD). However, RL relies on coarse-grained outcome supervision, resulting in difficult credit assignment and limited capability to acquire new knowledge. OPD, meanwhile, unconditionally matches teacher logits through KL divergence, which creates a dilemma: similar teachers provide little new knowledge, while substantially different teachers often yield ineffective guidance, largely restricting OPD to within-family distillation. We propose Distilled Reinforcement Learning (Distilled RL), which integrates teacher supervision into the RL objective to provide fine-grained guidance, selectively transfer new knowledge and avoid unconditional imitation. Distilled RL contains three components: reverse importance sampling with clipping, negative sample reset, and sequence-level geometric normalization. Through a concise and interpretable case study, we demonstrate that Distilled RL can effectively transfer previously unavailable knowledge from a teacher model to a student model. Extensive experiments across both within-family and cross-family distillation settings show that Distilled RL substantially outperforms standard RL and OPD in terms of both pass@1 and pass@k. Our code is available at https://github.com/597358816/Distilled-RL.
Chen Wang, Zhaochun Li, Jionghao Bai et al.· 2 citations
Reinforcement learning post-training drives reasoning and agentic capabilities in modern AI systems, yet a growing body of work shows that it is most effective when used to fine-tune an already capable base model. We question whether existing pipelines yield models that are most suitable for reinforcement learning. Building on prior work highlighting the role of coverage and pass@K as predictors of post-RL performance, we design a simple modification to supervised fine-tuning, TailSFT, which filters out already fit sequences during training, thereby focusing learning on under-modeled regions, or the tail, of the data distribution. We justify and validate the design choices in TailSFT, particularly the specific filtering criteria, through a combination of controlled experiments and theoretical analysis. On OLMo-3 7B, TailSFT often improves pass@16 performance on math and coding evaluations, with gains up to 17% absolute, while incurring minimal computational overhead. These higher-coverage checkpoints consistently translate to up to 4% absolute pass@1 gains in subsequent GRPO runs, demonstrating that TailSFT checkpoints serve as better initializations for RL. We further introduce a lightweight diagnostic for identifying settings where TailSFT is most likely to help. More broadly, our results motivate a principled, stage-aware approach to model development, in which intermediate checkpoints are judged by how effectively they support subsequent training.
Sadhika Malladi, Samy Jelassi, Dylan J. Foster et al.· 0 citations
Continual learning commonly relies on post-hoc mechanisms such as replay, elastic regularization, or distillation. This work argues that forgetting should instead be modeled directly as interference between tasks. In the frozen-feature regime, forgetting from learning a new task is exactly the interference energy induced on the old task. In deep networks, the same quantity is recovered through path-averaged curvature with minimal additional forward passes. When task supports are disjoint, forgetting can be eliminated structurally and when task supports overlap in conflicting directions, a non-zero distortion floor is unavoidable. The same geometry optimally merges models through task-aware orthogonalization. From this analysis we derive Interference-Gated Functional Allocation (IGFA), a replay-free, Fisher-free method that shares directions when tasks align and protects them when they conflict. Across benchmarks, IGFA achieves lossless retention when tasks are structurally separable and moves unavoidable cost from irreversible forgetting into deferred but recoverable plasticity when they are not. It matches the strongest replay-free structural baselines on dissimilar-task streams and improves on unconditional projection when similarity makes transfer worth preserving.