Knowledge editing has emerged as a lightweight alternative to retraining for correcting or injecting specific facts in large language models (LLMs). Meanwhile, fine-tuning remains the default operation for adapting LLMs to new domains and tasks. Despite their widespread adoption, these two post-training interventions have been studied in isolation, leaving open a crucial question: if we fine-tune an edited model, do the edits survive? This question is motivated by two practical scenarios: removing covert or malicious edits, and preserving beneficial edits. If fine-tuning impairs edits (Fig.1), current KE methods become less useful, as every fine-tuned model would require re-editing, which significantly increases the cost; if edits persist, fine-tuned models risk propagating hidden malicious edits, raising serious safety concerns. To this end, we systematically quantify edit decay after fine-tuning, investigating how fine-tuning affects knowledge editing. Our results show that edits decay after fine-tuning, with survival varying across configurations, e.g., AlphaEdit edits decay more than MEMIT edits. Further, we find that fine-tuning edited layers only can effectively remove edits, though at a slight cost to downstream performance. Surprisingly, fine-tuning non-edited layers impairs more edits than full fine-tuning. Overall, our study establishes empirical baselines and actionable strategies for integrating knowledge editing with fine-tuning, and underscores that evaluating model editing requires considering the full LLM application pipeline.

Large-scale foundation models are often adapted for specific downstream tasks after pre-training.

Parameter-Efficient Fine-Tuning (PEFT) methods are crucial for adapting large pre-trained models. Among these, LoRA is considered a foundational approach. Building on this, the influential DoRA method enhances performance by decomposing weight updates into magnitude and direction. However, its underlying mechanism remains unclear, and it introduces significant computational overhead. In this work, we first identify that DoRA's success stems from its capacity to increase the singular value entropy of the weight update matrix, which promotes a more uniform update distribution akin to full fine-tuning. We then reformulate DoRA into a mathematically equivalent and more efficient matrix form, revealing it as a learnable weight conditioning method. Based on this insight, we propose a unified framework for designing advanced PEFT methods by exploring two orthogonal dimensions: the architectural placement and the transformation type of the conditioning matrix. Within this framework, we introduce two novel methods: (1) \textbf{Pre-Diag}, which applies a diagonal conditioning matrix before the LoRA update to efficiently calibrate the pre-trained weights, thereby enhancing performance while reducing training time; and (2) \textbf{S}kewed \textbf{O}rthogonal \textbf{R}otation \textbf{A}daptation (\textbf{SORA}), which employs a parameter-efficient orthogonal rotation to perform a more powerful, norm-preserving transformation of the feature space. Extensive experiments on natural language understanding and generation tasks demonstrate that our proposed methods achieve superior performance and efficiency compared to both LoRA and DoRA. The code is available at https://github.com/MaeChd/SORA.

Preference alignment methods are increasingly critical for steering large language models (LLMs) to generate outputs consistent with human values. While recent approaches often rely on synthetic data generated by LLMs for scalability and cost-efficiency reasons, this reliance can introduce distribution shifts that undermine the nuanced representation of human preferences needed for desirable outputs. In this paper, we propose a novel distribution-aware optimization framework that improves preference alignment despite such shifts. Our approach first leverages well-learned classifiers to assign a calibration value to each training sample, quantifying its alignment with the target human-preferred distribution. These values are then incorporated into a robust optimization objective that minimizes the worst-case loss over regions of the data space most relevant to human preferences. By explicitly focusing optimization on the target distribution, our approach mitigates the impact of distributional mismatch and improves the generation of responses that better reflect intended values.

Test-Time Scaling (TTS) improves the performance of Large Language Models (LLMs) by using additional inference-time computation to explore multiple reasoning paths through search. Yet how to allocate a fixed rollout budget most effectively during search remains underexplored, often resulting in inefficient use of compute at test time. To bridge this gap, we formulate test-time search as a resource allocation problem and derive the optimal allocation strategy that maximizes the probability of obtaining a correct solution under a fixed rollout budget. Within this formulation, we reveal a core limitation of existing search methods: solution-level allocation tends to favor reasoning directions with more candidates, leading to theoretically suboptimal and inefficient use of compute. To address this, we propose Direction-Oriented Resource Allocation (DORA), a provably optimal method that mitigates this bias by decoupling direction quality from candidate count and allocating resources at the direction level. To demonstrate DORA's effectiveness, we conduct extensive experiments on challenging mathematical reasoning benchmarks including MATH500, AIME2024, and AIME2025. The empirical results show that DORA consistently outperforms strong baselines with comparable computational cost, achieving state-of-the-art accuracy. We hope our findings contribute to a broader understanding of optimal TTS for LLMs.

Large-scale foundation models are often adapted for specific downstream tasks after pre-training.

Parameter-efficient fine-tuning (PEFT) methods have become the standard paradigm for adapting large-scale models. Among these techniques, Weight-Decomposed Low-Rank Adaptation (DoRA) has been shown to improve both the learning capacity and training stability of the vanilla Low-Rank Adaptation (LoRA) method by explicitly decomposing pre-trained weights into magnitude and directional components. In this work, we propose DoRAN, a new variant of DoRA designed to further stabilize training and boost the sample efficiency of DoRA. Our approach includes two key stages: (i) injecting noise into the denominator of DoRA's weight decomposition, which serves as an adaptive regularizer to mitigate instabilities; and (ii) replacing static low-rank matrices with auxiliary networks that generate them dynamically, enabling parameter coupling across layers and yielding better sample efficiency in both theory and practice. Comprehensive experiments on vision and language benchmarks show that DoRAN consistently outperforms LoRA, DoRA, and other PEFT baselines. These results underscore the effectiveness of combining stabilization through noise-based regularization with network-based parameter generation, offering a promising direction for robust and efficient fine-tuning of foundation models.

Large decoder-based language models have become the dominant architecture for reward modeling in reinforcement learning from human feedback (RLHF). However, as reward models are increasingly deployed in test-time strategies, their inference costs become a growing concern. We present TinyRM, a family of small, bidirectional masked language models (MLMs) with as few as 400 million parameters, that rival the capabilities of models over 175 times larger on reasoning and safety preference modeling tasks. TinyRM combines FLAN-style prompting, Directional Low-Rank Adaptation (DoRA), and layer freezing to achieve strong performance on RewardBench, despite using significantly fewer resources. Our experiments suggest that small models benefit from domain-specific tuning strategies, particularly in reasoning, where lightweight finetuning methods are especially effective. While challenges remain in building generalist models and conversational preference modeling, our preliminary results highlight the promise of lightweight bidirectional architectures as efficient, scalable alternatives for preference modeling.