论文检索

Deep Learning · Large Language Models

Gül Sena Altıntaş, Malikeh Ehghaghi, Brian Lester, Fengyuan Liu, Wanru Zhao, Marco Ciccone, Colin Raffel

Tokenizers provide the fundamental basis through which text is represented and processed by language models (LMs). Despite the importance of tokenization, its role in LM performance and behavior is poorly understood due to the challenge of measuring the impact of tokenization in isolation. To address this need, we present TokSuite, a collection of models and a benchmark that supports research into tokenization's influence on LMs. Specifically, we release fourteen pre-trained models that use different tokenizers but are otherwise identical, using the same architecture, dataset, training budget, and initialization. We also release a multilingual robustness benchmark that measures model performance under real-world perturbations in English, Chinese, Farsi, Italian, and Turkish, curated by native annotators. Together, TokSuite allows robust decoupling of the influence of a model's tokenizer, supporting a series of novel findings that elucidate the respective benefits and shortcomings of a wide range of popular tokenizers.

Applications · Neuroscience, Cognitive Science

Sicheng Shen, Mingyang Lv, Bing Han, Dongcheng Zhao, Guobin Shen, Feifei Zhao, Yi Zeng

In recent years, Spiking Neural Networks (SNNs) have achieved remarkable progress, with Spiking Transformers emerging as a promising architecture for energy-efficient sequence modeling. However, existing Spiking Transformers still lack a principled mechanism for effective temporal fusion, limiting their ability to fully exploit spatiotemporal dependencies. Inspired by feedforward–feedback modulation in the human visual pathway, we propose **TEFormer**, the first Spiking Transformer framework that achieves bidirectional temporal fusion by decoupling temporal modeling across its core components. Specifically, TEFormer employs a lightweight and hyperparameter-free **forward temporal fusion mechanism in the attention module**, enabling fully parallel computation, while incorporating a **backward gated recurrent structure in the MLP** to aggregate temporal information in reverse order and reinforce temporal consistency. Extensive experiments across a wide range of benchmarks demonstrate that TEFormer consistently and significantly outperforms strong SNN and Spiking Transformer baselines under diverse datasets. Moreover, through the first systematic evaluation of Spiking Transformers under different neural encoding schemes, we show that the performance gains of TEFormer remain stable across encoding choices, indicating that the improved temporal modeling directly translates into reliable accuracy improvements across varied spiking representations. These results collectively establish TEFormer as an effective and general framework for temporal modeling in Spiking Transformers. Code: [https://anonymous.4open.science/r/TEFormer-6EB7](https://anonymous.4open.science/r/TEFormer-6EB7)

Reinforcement Learning · Batch/Offline

Jiayu Chen, Le Xu, Aravind Venugopal, Jeff Schneider

Offline reinforcement learning (RL) offers a powerful paradigm for data-driven control. Compared to model-free approaches, offline model-based RL (MBRL) explicitly learns a world model from a static dataset and uses it as a surrogate simulator, improving data efficiency and enabling potential generalization beyond the dataset support. However, most existing offline MBRL methods follow a two-stage training procedure: first learning a world model by maximizing the likelihood of the observed transitions, then optimizing a policy to maximize its expected return under the learned model. This objective mismatch results in a world model that is not necessarily optimized for effective policy learning. Moreover, we observe that policies learned via offline MBRL often lack robustness during deployment, and small adversarial noise in the environment can lead to significant performance degradation. To address these, we propose a framework that dynamically adapts the world model alongside the policy under a unified learning objective aimed at improving robustness. At the core of our method is a maximin optimization problem, which we solve by innovatively utilizing Stackelberg learning dynamics. We provide theoretical analysis to support our design and introduce computationally efficient implementations. We benchmark our algorithm on twelve noisy D4RL MuJoCo tasks and three stochastic Tokamak Control tasks, demonstrating its state-of-the-art performance.

General Machine Learning · Evaluation

Maya Varma, Jean-Benoit Delbrouck, Sophie Ostmeier, Akshay Chaudhari, Curtis Langlotz

Multimodal large language models (MLLMs) often introduce errors when generating image captions, resulting in misaligned image-text pairs. Our work focuses on a class of captioning errors that we refer to as systematic misalignments, where a recurring error in MLLM-generated captions is closely associated with the presence of a specific visual feature in the paired image. Given a vision-language dataset with MLLM-generated captions, our aim in this work is to detect such errors, a task we refer to as systematic misalignment detection. As our first key contribution, we present Symbal, which utilizes a structured, dual-stage setup with off-the-shelf foundation models to identify systematic misalignments and summarize results in natural language. As our second key contribution, we introduce SymbalBench, a benchmark designed to evaluate automated methods on our proposed task. SymbalBench consists of 420 vision-language datasets from two domains (natural images and medical images) with annotated systematic misalignments. Symbal exhibits strong performance on this benchmark, correctly identifying systematic misalignments in 63.8% of datasets, a nearly 4x improvement over the closest baseline. We supplement our evaluations on SymbalBench with real-world evaluations, showing that (1) Symbal can accurately surface systematic misalignments in captions generated by four MLLMs and (2) Symbal is a powerful tool for auditing off-the-shelf image-caption datasets. Ultimately, our novel task, method, and benchmark can aid users with auditing MLLM-generated captions and identifying critical errors, without requiring access to the underlying MLLM.

Applications · Computer Vision

Rui Chen, Dongdong Li, Yan Fan, Yan Liu, Yangliu Kuai, Pengfei Zhu

Recently, the rapid development of low-altitude aerial applications has driven the need for drone-based unified detectors. In contrast to task-specific detectors that suffer from poor scalability across diverse scenarios, existing unified detectors leverage the Mixture-of-Experts (MoE) architecture to learn task-aware features from diverse datasets. However, the imbalanced multi-task data distribution leads to over-activation of experts for dominant tasks and under-activation for others. To enable balanced feature learning, this paper combines three detection paradigms (RGB, IR, and RGB-IR) into a unified framework termed DroneDINO. DroneDINO extends DINO by introducing heterogeneous routed MoEs that organize experts into three functional groups: shared, task-specific, and dynamic. Unlike conventional dynamic experts where the top-$k$ experts are activated for each input, the shared expert is activated for all inputs, while each task-specific expert is activated exclusively for the matching task. To ensure inputs are routed to appropriate experts and yield task-discriminative features, we propose a task-recognition auxiliary training strategy to penalize features with low task-discriminability. Experiments demonstrate the effectiveness and generalizability of DroneDINO, which consistently outperforms state-of-the-art unified and task-specific detectors across multiple drone-based detection benchmarks.

Optimization · Everything Else

Gal Lifshitz, Shahar Zuler, Ori Fouks, Dan Raviv

End-to-end deep learning has achieved impressive results but often relies on large labeled datasets, exhibits limited generalization to unseen scenarios, and incurs substantial computational cost. Classical optimization methods, in contrast, are data-efficient and lightweight but frequently suffer from slow or unstable convergence. Learned optimizers aim to bridge this gap, yet existing approaches predominantly focus on first-order methods, leaving learned second-order optimization largely unexplored. We introduce L-SR1, a novel learned second-order optimizer that augments the classical Symmetric Rank-One (SR1) method with a lightweight, trainable preconditioning unit. This unit generates data-driven rank-one updates that are explicitly aligned with the secant condition via a learned projection mechanism, ensuring stable and consistent curvature estimation. Through controlled analytic benchmarks, we systematically analyze the stability, generalization across problem dimensions, and the quality of the resulting search directions. We further evaluate L-SR1 on the real-world task of Monocular Human Mesh Recovery (HMR), where it outperforms existing optimization-based and learned-optimization baselines. With a compact model and no reliance on task-specific fine-tuning or annotated data, L-SR1 demonstrates strong generalization and provides an effective drop-in optimizer for a wide range of iterative optimization problems.

Deep Learning · Large Language Models

Ahsan Bilal, Muhammad Ahmed Mohsin, Muhammad Umer, Ali Subhan, Hassan Rizwan, Ayesha Mohsin, Dean Hougen

Test-time compute scaling allocates inference computation uniformly, uses fixed sampling strategies, and applies verification only for reranking. In contrast, we propose a verifier-guided adaptive framework treating reasoning as iterative trajectory generation and selection. For each problem, the agent runs multiple inference iterations. In each iteration, it optionally produces a high-level plan, selects a set of reasoning tools and a compute strategy together with an exploration parameter, and then generates a candidate reasoning trajectory. A process reward model (PRM) serves as a unified control signal: within each iteration, step-level PRM scores are aggregated to guide pruning and expansion during generation, and across iterations, aggregated trajectory rewards are used to select the final response. Across datasets, our dynamic, PRM-guided approach consistently outperforms direct test-time scaling, yielding large gains on MATH-500 and several-fold improvements on harder benchmarks such as AIME24 and AMO-Bench. We characterize efficiency using theoretical FLOPs and a compute intensity metric penalizing wasted generation and tool overhead, demonstrating that verification-guided allocation concentrates computation on high-utility reasoning paths.

Applications · Energy

Chao Shen, Zihan Guo, Xu Wan, Zhenghao Yang, Yifan Zhang, Wenqi Huang, Jie Song, Zongyan Zhang, Mingyang Sun

Growing renewable penetration introduces substantial uncertainty into power system operations, necessitating frequent adaptation of dispatch objectives and constraints and challenging expertise-intensive, near-real-time modeling workflows. Large Language Models (LLMs) provide a promising avenue for automating this process by translating natural-language (NL) operational requirements into executable optimization models via semantic reasoning and code synthesis. Yet existing LLM datasets and benchmarks for optimization modeling primarily target coarse-grained cross-domain generalization, offering limited, rigorous evaluation in powersystem settings, particularly for Optimal Power Flow (OPF). We therefore introduce ProOPFD and ProOPF-B, a dataset and benchmark for professional-grade OPF modeling: ProOPF-D contains 12K instances pairing NL requests with parameter adjustments and structural extensions to a canonical OPF, together with executable implementations; ProOPF-B provides 121 expertannotated test cases with ground-truth code, enabling end-to-end evaluation under both concrete and abstract OPF modeling regimes.

Deep Learning · Foundation Models

Xueying Ding, Haomin Wen, Simon Klüttermann, Leman Akoglu

Outlier detection (OD) is widely used in practice; but its effective deployment on new tasks is hindered by lack of labeled outliers, which makes algorithm and hyperparameter selection notoriously hard. Foundation models (FMs) have transformed ML, and OD is no exception: Shen et al. (2025) introduced FOMO-0D, the first FM for OD, achieving remarkable performance against numerous baselines. This work introduces OUTFORMER, which advances FOMO-0D with (1) a mixture of synthetic priors and (2) self-evolving curriculum training. OUTFORMER is pretrained solely on synthetic labeled datasets and infers test labels of a new task by using its training data as in-context input. Inference is fast and zero-shot, requiring merely forward pass and no labeled outliers. Thanks to in-context learning, it requires zero additional work—no OD model training or bespoke model selection—enabling truly plug-and-play deployment. OUTFORMER achieves state-of-the-art performance on the prominent ADBench, as well as two new large-scale OD benchmarks that we introduce, comprising over 1,500 datasets, while maintaining speedy inference.

Applications · Computer Vision

Bo Zhao, Yihang Liu, Chenfeng Zhang, Huan Yang, Kun Gai, Wei Ji

Text-guided texture editing aims to modify object appearance while preserving the underlying geometric structure. However, our empirical analysis reveals that even SOTA editing models frequently struggle to maintain structural consistency during texture editing, despite the intended changes being purely appearance-related. Motivated by this observation, we jointly enhance structure preservation from both data and training perspectives, and build TexEditor, a dedicated texture editing model based on Qwen-Image-Edit-2509. Firstly, we construct BlenderTex, a high-quality SFT dataset generated with Blender, which provides strong structural priors for a cold start. Secondly, we introduce StructureNFT, a RL–based approach that integrates structure-preserving losses to transfer the structural priors learned during SFT to real-world scenes. Moreover, due to the limited realism and evaluation coverage of existing benchmarks, we introduce TexBench, a general-purpose real-world benchmark for text-guided texture editing. Extensive experiments on existing Blender-based texture benchmarks and our TexBench show that TexEditor consistently outperforms strong baselines such as Nano Banana Pro. In addition, we assess TexEditor on the general-purpose benchmark ImgEdit to validate its generalization.

Applications · Everything Else

Pawan Sasanka Ammanamanchi, Siddharth Bhat, Stella Biderman

Benchmarks for LLM-assisted theorem proving in Lean are often treated as intrinsically reliable because every solved instance comes with a machine-checked proof. However, the kernel only checks that a proof establishes a \emph{formal} statement; it does not verify that the statement faithfully encodes the intended informal problem, nor that evaluation harnesses are robust to trivial or adversarial solutions. We audit widely used Lean theorem-proving benchmarks and find recurring defects in every dataset we examined, including missing hypotheses, problem simplification, incomplete or incorrect translations, and Lean-specific specification hazards. Beyond dataset construction, we survey and identify evaluation-time failure modes that can inflate reported success without demonstrating meaningful proof capability. We propose a fault taxonomy, a suite of automated checkers and prompts, and release standards to guide the creation of formal math datasets and make evaluation more reproducible and trustworthy.

Applications · Health / Medicine

Bonjae Ku, Seeun Kim, Yubeen Kim, Hahnbeom Park, Chaok Seok

Proteins are inherently dynamic, with biological functions often emerging from transitions between multiple conformational states. While recent breakthroughs have largely addressed the static structure prediction problem, a systematic benchmark is absent to demonstrate how well current models capture functionally relevant dynamics. We introduce ProMiSE, the first benchmark that provides both a dataset and evaluation scheme, based on native biological assemblies and integrating major conformational change mechanisms—intrinsic, ligand-induced, and protein-induced—within a single curated dataset. We conducted a comprehensive evaluation of state-of-the-art structure prediction models, including AlphaFold3 and recent generative approaches. Our findings reveal that current models exhibit a limited ability to sample intrinsic dynamics and are often insensitive to biological context in induced scenarios. We further investigate whether these multi-state prediction biases are associated with multiple sequence alignment (MSA) signals or training data distributions, while analyzing internal model representations throughout the model to identify where these biases arise. Ultimately, ProMiSE benchmarks limitations in conformational diversity and biological relevance, enabling improved multi-state and dynamics-aware modeling.

Applications · Time Series

Linxiao Yang, Xue Jiang, Gezheng Xu, Tian Zhou, Min Yang, Zhaoyang Zhu, Linyuan Geng, Zhipeng Zeng, Qiming Chen, Xinyue Gu 等

Transformers enable in-context learning (ICL) for rapid, gradient-free adaptation in time series forecasting, yet most ICL-style approaches rely on tabularized, hand-crafted features, while end-to-end sequence models lack inference-time adaptation. We bridge this gap with a unified framework, Baguan-TS, which integrates the raw-sequence representation learning with ICL, instantiated by a 3D Transformer that attends jointly over temporal, variable, and context axes. To make this high-capacity model practical, we tackle two key hurdles: (i) calibration and training stability, improved with a feature-agnostic, target-space retrieval-based local calibration; and (ii) output oversmoothing, mitigated via context-overfitting strategy. On public benchmark with covariates, Baguan-TS consistently outperforms established baselines, achieving the highest win rate and significant reductions in both point and probabilistic forecasting metrics. Further evaluations across diverse real-world energy datasets demonstrate its robustness, yielding substantial improvements.

Applications · Chemistry, Physics, and Earth Sciences

Matteo Rossi, Ryan Pederson, Miles Wang-Henderson, Benjamin Kaufman, Edward Williams, Carl Underkoffler, Owen Howell, Adrian Layer, Stephan Thaler, Narbe Mardirossian 等

We present CoarseBind, a foundation model for protein-ligand structure and binding affinity prediction that achieves 26$\times$ faster inference than state-of-the-art methods while improving affinity prediction accuracy by up to 20\%. Current deep learning approaches to structure-based drug design rely on expensive all-atom diffusion to generate 3D coordinates, creating inference bottlenecks that render large-scale compound screening computationally intractable. We challenge this paradigm with the hypothesis: full all-atom resolution is unnecessary for accurate small molecule pose and binding affinity prediction. CoarseBind tests this hypothesis through a coarse pocket-level representation (protein C$_\beta$ atoms and ligand heavy atoms only) within a multimodal architecture combining pretrained molecular encoders and ESM-2 protein embeddings that learns rich structural representations, which are used in a diffusion-free optimization module for pose generation and a binding affinity likelihood prediction module. On structure prediction benchmarks, CoarseBind matches diffusion-based baselines in ligand pose accuracy. For binding affinity, CoarseBind outperforms Boltz-2 by 16-20\% in Pearson correlation on both a public benchmark (CASP16) and a diverse private dataset (18 assays). The affinity module also provides well-calibrated uncertainty estimates, addressing a critical gap in compound prioritization for drug discovery. Furthermore, this module enables a continual learning framework and a hedged batch selection strategy that, in simulated drug discovery cycles, achieves 6$\times$ greater affinity improvement over greedy approaches.

Applications · Computer Vision

Ghadi Nehme, Yanxia Zhang, Dule Shu, Matthew Klenk, Faez Ahmed

Generating high-fidelity 3D geometries that satisfy specific parameter constraints has broad applications in design and engineering. However, current methods typically rely on large training datasets and struggle with controllability and generalization beyond the training distributions. To overcome these limitations, we introduce LAMP (Linear Affine Mixing of Parametric shapes), a data-efficient framework for controllable and interpretable 3D generation. LAMP first aligns signed distance function (SDF) decoders by overfitting each exemplar from a shared initialization, then synthesizes new geometries by solving a parameter-constrained mixing problem in the aligned weight space. To ensure robustness, we further propose a safety metric that detects geometry validity via linearity mismatch. We evaluate LAMP on two 3D parametric benchmarks: DrivAerNet++ and BlendedNet. We found that LAMP enables (i) controlled interpolation within bounds with as few as 100 samples, (ii) safe extrapolation by up to 100\% parameter difference beyond training ranges, (iii) physics performance-guided optimization under fixed parameters. LAMP significantly outperforms conditional autoencoder and Deep Network Interpolation (DNI) baselines in both extrapolation and data efficiency. Our results demonstrate that LAMP advances controllable, data-efficient, and safe 3D generation for design exploration, dataset generation, and performance-driven optimization.

Deep Learning · Everything Else

Songsong Ouyang, Le Wu, Yingying Zhu

Cross-view geo-localization (CVGL) aims to retrieve the corresponding satellite image given a street query and is critical for autonomous navigation. Although recent methods perform well on benchmarks, they often fail to generalize to unseen environments. A key limitation is the use of contrastive learning, which assigns equal labels to all negative samples and induces similarity-amplified repulsion. But should all negatives be treated equally? In CVGL, semi-positive samples that are geographically proximate to the positive often share important semantic cues. Treating them as ordinary negatives forces the model to overfit noise, leading to a collapse in generalization. To address this issue, we propose an uncertainty-aware framework grounded in Deep Evidential Regression (DER), modeling the Normal-Inverse-Gamma (NIG) distribution as a conjugate prior to quantify environmental complexity $u$ in a single forward pass. The estimated $u$ adaptively softens labels for hard negatives in Soft InfoNCE, mitigating excessive repulsion on semi-positive samples. An Uncertainty Head with cls-to-spatial cross-attention and attention statistics is designed to accurately fit the NIG distribution. Extensive experiments demonstrate state-of-the-art performance, including an average 18\% R@1 improvement in zero-shot cross-dataset transfer, filling the critical gap between laboratory benchmarks and robust real-world deployment.

Deep Learning · Large Language Models

Azim Ospanov, Zijin Feng, Jiacheng Sun, Haoli Bai, SHEN XIN, Farzan Farnia

Informal mathematics has been central to modern large language model (LLM) reasoning, offering flexibility and efficient construction of arguments. However, purely informal reasoning is prone to logical gaps and subtle errors that are difficult to detect and correct. In contrast, formal theorem proving provides rigorous, verifiable mathematical reasoning, where each inference step is checked by a trusted compiler, but lacks the exploratory freedom of informal problem-solving. This mismatch leaves current LLM-based math agents without a principled way to combine the strengths of both paradigms. In this work, we introduce Hermes, the first tool-assisted agent that explicitly interleaves informal reasoning with formally verified proofs in Lean. The framework performs intermediate formal checking to prevent reasoning drift and a memory module for proof continuity across multi-step reasoning chains, enabling both exploration and verification. We evaluate Hermes on four challenging mathematical reasoning benchmarks using LLMs of varying parameter scales, from small models to state-of-the-art systems. Across all settings, Hermes reliably improves the reasoning accuracy of base models while substantially reducing reasoning token usage and computational cost compared to reward-based approaches. On difficult datasets such as AIME and HARDMath2, Hermes@1 achieves up to a 40% accuracy improvement while using 80% fewer total inference FLOPs. When scaled at test time, Hermes@5 boosts accuracy further by 20%.

General Machine Learning · Supervised Learning

Zikun Jin, Yuhua Qian, Xinyan Liang, Jiaqian Zhang, Haijun Geng

Robust signal enhancement at extremely low SNR is fundamentally challenging because noise becomes strongly entangled with the signal and corrupts local time–frequency (TF) evidence. In this regime, fixed resolution short-time Fourier transform (STFT) enhancement with purely data driven convolutional biases can become overconfident in unreliable TF regions, causing unstable suppression or residual artifacts. We propose FracKGMF, which couples Fractional Distance Decay Convolution (FracConv) with Knowledge Guided Multi-view Fusion (KGMF) for expressive TF modeling and reliability aware decisions under heavy corruption. FracConv introduces a lightweight fractional distance decay family that reshapes local interactions into long tailed receptive patterns, enabling aggregation of weak but globally consistent cues when per-bin observations are ambiguous. KGMF further injects a Wiener inspired reliability view derived from noise statistics to calibrate multi-view fusion, avoiding over-suppression in uncertain regions while exploiting confident structure for effective denoising. Across speech and electromagnetic (EM) benchmarks, FracKGMF improves perceptual quality and intelligibility over state-of-the-art baselines, with especially robust gains at extremely low SNR; on EM dataset at -20 dB, it achieves an average improvement of 33 dB where conventional TF methods performed poorly. The code will be released upon acceptance.

Applications · Computer Vision

Ghadi Nehme, Eamon Whalen, Faez Ahmed

Despite recent progress, recovering parametric CAD construction sequences from geometric input, such as meshes or point clouds, is a key challenge for design and manufacturing, as existing CAD reconstruction and generation methods are largely restricted to difficult-to-edit formats like meshes or Breps or editable simple sketch-and-extrude pipelines and low-complexity datasets. We introduce CADFit, a hybrid optimization-based CAD reconstruction framework that recovers complex, editable CAD construction sequences from meshes by incrementally fitting and validating parametric operations using geometric feedback. Our approach is distinguished by formulating reconstruction as an IoU-driven optimization over structured CAD programs and supporting a rich set of operations, including extrusions, revolutions, fillets, and chamfers. Experiments on multiple CAD benchmarks show that CADFit outperforms state-of-the-art mesh-to-CAD methods in volumetric Intersection-over-Union and Chamfer Distance, while substantially reducing the Invalid Ratio of reconstructed CAD programs, particularly for complex designs. We further present a multimodal pipeline that enables end-to-end reconstruction of CAD construction sequences from images by combining image-based geometry reconstruction with CADFit. By enabling accurate reconstruction of higher-complexity CAD models, CADFit provides a practical foundation for generating richer datasets and advancing future learning-based approaches to CAD reverse engineering.

Social Aspects · Alignment

Aakash Sen Sharma, Debdeep Sanyal, Manodeep Ray, Vivek Srivastava, Shirish Karande, Murari Mandal

Post-training alignment of large language models (LLMs) relies on large-scale human annotations guided by policy specifications that change over time. Cultural shifts, value reinterpretations, and regulatory or industrial updates make static alignment increasingly brittle. As policies evolve, deployed models can diverge from current alignment objectives, creating an Alignment–Reality Gap that is difficult to audit or correct. Existing remediation typically requires re-annotation under revised guidelines, which introduces systematic challenges, including guideline ambiguity, annotator interpretation drift, and reduced consistency at scale. We introduce TRACE (Triage and Re-align by Alignment Conflict Evaluation), a framework that transforms re-alignment into a structured optimization problem over existing data without requiring fresh human annotation. Leveraging a stronger model as a proxy judge, TRACE operates via a three-stage pipeline: (1) triaging preference pairs into inversion, suppression, or retention categories based on alignment conflicts; (2) computing an alignment impact score via bi-level optimization to prioritize high-leverage samples; and (3) executing updates using a hybrid objective that combines relational losses (e.g., IPO) for preference inversion and punitive losses (e.g., NPO) for response suppression. Experiments on Qwen2.5-7B, Gemma-2-9B, and Llama-3.1-8B demonstrate robust re-alignment on synthetic benchmarks and the PKU-SafeRLHF dataset without degrading general utility. This work provides a scalable approach for LLM realignment under evolving data annotation policies and alignment guidelines.