arXiv:2503.23777v2 Announce Type: replace 
Abstract: Naive joint training of large language models (LLMs) for multilingual preference alignment can suffer from negative interference. This is a known issue in multilingual training, where conflicting objectives degrade overall performance. However, the impact of this phenomenon in the context of multilingual preference alignment remains largely underexplored. To address this issue, we propose CONGRAD, a scalable and effective filtering method that selects high-quality preference samples with minimal gradient conflicts across languages. Our method leverages gradient surgery to retain samples aligned with an aggregated multilingual update direction. Additionally, we incorporate a sublinear gradient compression strategy that reduces memory overhead during gradient accumulation. We integrate CONGRAD into self-rewarding framework and evaluate on LLaMA3-8B and Gemma2-2B across 10 languages. Results show that CONGRAD consistently outperforms strong baselines in both seen and unseen languages, with minimal alignment tax.

تم اقتراح طريقة جديدة تُدعى CONGRAD لمعالجة التداخل السلبي في محاذاة التفضيلات متعددة اللغات أثناء تدريب نماذج اللغة الكبيرة (LLMs). تقوم هذه الطريقة بترشيح عينات تفضيل عالية الجودة لتقليل الصراعات في التدرجات عبر اللغات. تم تقييمها على نماذج LLaMA3-8B وGemma2-2B عبر 10 لغات، وقد أظهرت CONGRAD تحسينات مستمرة في الأداء مقارنة بالأسس الحالية، مما يجعلها تقدمًا مهمًا في التدريب متعدد اللغات.

Se ha propuesto un nuevo método llamado CONGRAD para abordar la interferencia negativa en la alineación de preferencias multilingües durante el entrenamiento de grandes modelos de lenguaje (LLMs). Este método filtra muestras de preferencias de alta calidad para minimizar los conflictos de gradiente entre idiomas. Evaluado en los modelos LLaMA3-8B y Gemma2-2B en 10 idiomas, CONGRAD ha mostrado mejoras de rendimiento constantes sobre las bases existentes, lo que representa un avance significativo en el entrenamiento multilingüe.

Une nouvelle méthode appelée CONGRAD a été proposée pour résoudre les interférences négatives dans l'alignement des préférences multilingues lors de l'entraînement de grands modèles de langage (LLMs). Cette méthode filtre des échantillons de préférences de haute qualité pour minimiser les conflits de gradient entre les langues. Évaluée sur les modèles LLaMA3-8B et Gemma2-2B dans 10 langues, CONGRAD a montré des améliorations de performance constantes par rapport aux bases existantes, ce qui en fait une avancée significative dans l'entraînement multilingue.

A new method called CONGRAD has been proposed to address negative interference in multilingual preference alignment during the training of large language models (LLMs). This method filters high-quality preference samples to minimize gradient conflicts across languages. Evaluated on models LLaMA3-8B and Gemma2-2B across 10 languages, CONGRAD has shown consistent performance improvements over existing baselines, making it a significant advancement in multilingual training.

CONGRAD:Conflicting Gradient Filtering for Multilingual Preference Alignment

Here's everything you need to know about the latest smart ring by Oura, based on a wearable expert's real-world usage.

Is the $500 Oura Ring 4 Ceramic worth it? I wore one for a month, and here's my advice

Samsung's QN90F QLED delivers great streaming and gaming performance, making it a strong holiday value.

Why I recommend this Samsung QLED TV over pricier OLED models in 2025 - and don't regret it

<h1>
 
 
 AI Amnesia: Erasing Knowledge Without a Trace
</h1>

Imagine your AI model accidentally learned something it shouldn't have – sensitive customer data, for example. Current methods for deleting this information often require retraining the entire model, an expensive and time-consuming process. What if we could surgically remove that knowledge without starting from scratch?

The key lies in a novel approach: creating artificial "forgetting cues." We're teaching the model to unlearn specific data patterns by exposing it to carefully crafted synthetic examples. These examples are designed to strongly contradict the information we want the model to forget, effectively overwriting the problematic associations in its memory. This works even if you don’t have access to the original data you need to erase.

Think of it like this: you're trying to forget a bad song stuck in your head. Instead of trying to actively suppress it (which rarely works), you blast an even more catchy song. The new song overwrites the old one, effectively erasing it from your mental playlist.

Benefits of Selective Forgetting:

<ul>
<li> Enhanced Data Privacy: Remove sensitive data without compromising the overall model's performance.</li>
<li> Reduced Retraining Costs: Avoid full model retraining, saving significant time and resources.</li>
<li> Improved Model Security: Eliminate vulnerabilities introduced by unintentionally learned patterns.</li>
<li> Adaptable Learning: Enables continuous refinement of AI models based on evolving data landscapes.</li>
<li> Compliance Ready: Supports compliance with data privacy regulations like GDPR.</li>
<li> Scalable Solutions: Works efficiently even with limited access to training data.</li>
</ul>

Practical Tip: One challenge is ensuring the synthetic data accurately targets the information you want to remove without negatively impacting the model's ability to generalize. Rigorous testing and validation with holdout datasets are crucial.

The promise of AI that can truly 'forget' opens exciting possibilities for responsible AI development. By enabling precise data deletion, we pave the way for more secure, compliant, and adaptable machine learning systems. Imagine AI models that can adapt to changing ethical guidelines or quickly unlearn incorrect information, all without massive retraining efforts. This is a crucial step towards trustworthy and responsible AI that respects data privacy and aligns with societal values. Future exploration could include extending this to different data modalities and model architectures.

Related Keywords: machine unlearning, data privacy, few-shot learning, zero-shot learning, synthetic data, model editing, catastrophic forgetting, incremental learning, continual learning, deep learning, neural networks, data security, algorithmic fairness, responsible ai, ethical ai, federated unlearning, privacy-preserving ai, model retraining, AI governance, data deletion, GDPR compliance

يتناول المقال نهجًا جديدًا لمعالجة مشكلة نسيان الذكاء الاصطناعي، حيث قد تحتفظ نماذج الذكاء الاصطناعي عن غير قصد بمعلومات حساسة. تتطلب الطرق التقليدية لحذف هذه البيانات غالبًا إعادة تدريب كاملة للنموذج، وهو ما يعد مكلفًا ويستغرق وقتًا. تتضمن التقنية الجديدة إنشاء 'إشارات نسيان' اصطناعية تساعد النموذج على نسيان أنماط بيانات معينة من خلال تعريضه لأمثلة صناعية تتناقض مع المعلومات غير المرغوب فيها، مما يسمح بإزالة المعرفة المستهدفة دون الحاجة للوصول إلى البيانات الأصلية.

El artículo aborda un nuevo enfoque para tratar el problema de la amnesia de la IA, donde los modelos de IA pueden retener inadvertidamente información sensible. Los métodos tradicionales para eliminar estos datos a menudo requieren un reentrenamiento completo del modelo, lo que es costoso y lleva tiempo. La nueva técnica implica crear 'señales de olvido' artificiales que ayudan al modelo a desaprender patrones de datos específicos al exponerlo a ejemplos sintéticos que contradicen la información no deseada, permitiendo así la eliminación selectiva de conocimientos sin necesidad de acceder a l…

L'article traite d'une nouvelle approche pour résoudre le problème de l'amnésie de l'IA, où les modèles d'IA peuvent involontairement conserver des informations sensibles. Les méthodes traditionnelles pour supprimer ces données nécessitent souvent un réentraînement complet du modèle, ce qui est coûteux et long. La nouvelle technique consiste à créer des 'cues d'oubli' artificiels qui aident le modèle à désapprendre des schémas de données spécifiques en lui présentant des exemples synthétiques qui contredisent les informations indésirables, permettant ainsi une suppression ciblée des connaissan…

The article discusses a novel approach to address the issue of AI amnesia, where AI models may inadvertently retain sensitive information. Traditional methods for deleting such data often require complete retraining of the model, which is costly and time-consuming. The new technique involves creating artificial 'forgetting cues' that help the model unlearn specific data patterns by presenting it with synthetic examples that contradict the unwanted information, allowing for targeted knowledge removal without needing access to the original data.

AI Amnesia: Erasing Knowledge Without a Trace

Baseus' Enercore CG11 travel adapter is one of the better designed ones I've tested, although its best feature isn't immediately apparent.

Traveling soon? Why this one charger is the only one you'll ever need to pack

Turning materials like wood chips, crop residues and municipal solid waste into fuels and chemicals is important for our country's energy independence.

طور الباحثون نماذج حاسوبية متقدمة تهدف إلى تحسين التنبؤات لعمليات طحن الكتلة الحيوية. تركز هذه الابتكارات على تحويل مواد مثل رقائق الخشب، بقايا المحاصيل، والنفايات الصلبة البلدية إلى وقود ومواد كيميائية قيمة، وهو أمر مهم لتعزيز استقلالية الطاقة في البلاد. من المتوقع أن تعمل النماذج على تحسين كفاءة معالجة الكتلة الحيوية، مما يساهم في حلول الطاقة المستدامة.

Investigadores han desarrollado modelos informáticos avanzados destinados a mejorar las predicciones para los procesos de molienda de biomasa. Esta innovación se centra en convertir materiales como astillas de madera, residuos de cultivos y residuos sólidos municipales en combustibles y productos químicos valiosos, lo que es crucial para mejorar la independencia energética del país. Se espera que los modelos optimicen la eficiencia del procesamiento de biomasa, contribuyendo así a soluciones energéticas sostenibles.

Des chercheurs ont développé des modèles informatiques avancés visant à améliorer les prévisions pour les processus de broyage de la biomasse. Cette innovation se concentre sur la conversion de matériaux tels que les copeaux de bois, les résidus de culture et les déchets solides municipaux en combustibles et produits chimiques précieux, ce qui est crucial pour renforcer l'indépendance énergétique du pays. Les modèles devraient optimiser l'efficacité du traitement de la biomasse, contribuant ainsi à des solutions énergétiques durables.

Researchers have developed advanced computer models aimed at improving predictions for biomass milling processes. This innovation focuses on converting materials such as wood chips, crop residues, and municipal solid waste into valuable fuels and chemicals, which is crucial for enhancing energy independence in the country. The models are expected to optimize the efficiency of biomass processing, thereby contributing to sustainable energy solutions.

Researchers develop computer models for better biomass milling predictions

The most interesting aspect of the latest Even Realities glasses may be their limitations.

I've tried several AI smart glasses (including Meta Ray-Bans) in 2025 - these are the most comfortable

arXiv:2511.11518v1 Announce Type: new 
Abstract: Large Language Models (LLMs) demonstrate impressive capabilities, yet their outputs often suffer from misalignment with human preferences due to the inadequacy of weak supervision and a lack of fine-grained control. Training-time alignment methods like Reinforcement Learning from Human Feedback (RLHF) face prohibitive costs in expert supervision and inherent scalability limitations, offering limited dynamic control during inference. Consequently, there is an urgent need for scalable and adaptable alignment mechanisms. To address this, we propose W2S-AlignTree, a pioneering plug-and-play inference-time alignment framework that synergistically combines Monte Carlo Tree Search (MCTS) with the Weak-to-Strong Generalization paradigm for the first time. W2S-AlignTree formulates LLM alignment as an optimal heuristic search problem within a generative search tree. By leveraging weak model's real-time, step-level signals as alignment proxies and introducing an Entropy-Aware exploration mechanism, W2S-AlignTree enables fine-grained guidance during strong model's generation without modifying its parameters. The approach dynamically balances exploration and exploitation in high-dimensional generation search trees. Experiments across controlled sentiment generation, summarization, and instruction-following show that W2S-AlignTree consistently outperforms strong baselines. Notably, W2S-AlignTree raises the performance of Llama3-8B from 1.89 to 2.19, a relative improvement of 15.9 on the summarization task.

تقدم الورقة المعنونة 'W2S-AlignTree: Weak-to-Strong Inference-Time Alignment for Large Language Models via Monte Carlo Tree Search' إطارًا جديدًا يهدف إلى تحسين توافق نماذج اللغة الكبيرة مع تفضيلات البشر. يجمع الإطار المقترح W2S-AlignTree بين بحث شجرة مونت كارلو ونموذج التعميم من الضعيف إلى القوي، مما يعالج قيود طرق التوافق الحالية في وقت التدريب. تهدف هذه الطريقة إلى توفير حل قابل للتوسع وقابل للتكيف لتحسين أداء نماذج اللغة الكبيرة أثناء الاستدلال.

El artículo titulado 'W2S-AlignTree: Weak-to-Strong Inference-Time Alignment for Large Language Models via Monte Carlo Tree Search' presenta un nuevo marco destinado a mejorar la alineación de los grandes modelos de lenguaje (LLMs) con las preferencias humanas. El marco propuesto, W2S-AlignTree, combina la búsqueda de árboles de Monte Carlo con el paradigma de generalización débil a fuerte, abordando las limitaciones de los métodos de alineación en tiempo de entrenamiento existentes. Este enfoque busca proporcionar una solución escalable y adaptable para mejorar el rendimiento de los LLM duran…

L'article intitulé 'W2S-AlignTree: Weak-to-Strong Inference-Time Alignment for Large Language Models via Monte Carlo Tree Search' présente un nouveau cadre visant à améliorer l'alignement des grands modèles de langage (LLMs) avec les préférences humaines. Le cadre proposé, W2S-AlignTree, intègre la recherche d'arbres de Monte Carlo avec le paradigme de généralisation faible à forte, abordant les limitations des méthodes d'alignement en temps d'entraînement existantes. Cette approche vise à fournir une solution évolutive et adaptable pour améliorer les performances des LLM lors de l'inférence.

The paper titled 'W2S-AlignTree: Weak-to-Strong Inference-Time Alignment for Large Language Models via Monte Carlo Tree Search' introduces a novel framework aimed at improving the alignment of large language models (LLMs) with human preferences. The proposed W2S-AlignTree framework integrates Monte Carlo Tree Search with the Weak-to-Strong Generalization paradigm, addressing the limitations of existing training-time alignment methods. This approach seeks to provide a scalable and adaptable solution for enhancing LLM performance during inference.

W2S-AlignTree: Weak-to-Strong Inference-Time Alignment for Large Language Models via Monte Carlo Tree Search

arXiv:2510.24021v2 Announce Type: replace 
Abstract: Knowledge distillation (KD) is a standard route to compress Large Language Models (LLMs) into compact students, yet most pipelines uniformly apply token-wise loss regardless of teacher confidence. This indiscriminate supervision amplifies noisy, high-entropy signals and is especially harmful under large teacher-student capacity gaps. We introduce SelecTKD, a plug-and-play Selective Token-Weighted distillation framework that shifts the focus from "how to measure divergence" to "where to apply learning". At each step, the student proposes tokens that are verified by the teacher through a robust propose-and-verify procedure with two variants: greedy Top-k and non-greedy Spec-k. Accepted tokens receive full loss, while rejected tokens are masked or down-weighted. This objective-agnostic design works with on- and off-policy data, induces an implicit curriculum quantified by Token Acceptance Rate (TAR), and stabilizes optimization. Across instruction following, mathematical reasoning, code generation, and a VLM setting, SelecTKD consistently improves strong baselines and achieves state-of-the-art results for small models without architectural changes or extra reference models.

SelecTKD: Selective Token-Weighted Knowledge Distillation for LLMs

arXiv:2511.13368v1 Announce Type: new 
Abstract: Large language models (LLMs) perform strongly across tasks and languages, yet how improvements in one task or language affect other tasks and languages and their combinations remains poorly understood. We conduct a controlled PEFT/LoRA study across multiple open-weight LLM families and sizes, treating task and language as transfer axes while conditioning on model family and size; we fine-tune each model on a single task-language source and measure transfer as the percentage-point change versus its baseline score when evaluated on all other task-language target pairs. We decompose transfer into (i) Matched-Task (Cross-Language), (ii) Matched-Language (Cross-Task), and (iii) Cross-Task (Cross-Language) regimes. We uncover two consistent general patterns. First, a pronounced on-task vs. off-task asymmetry: Matched-Task (Cross-Language) transfer is reliably positive, whereas off-task transfer often incurs collateral degradation. Second, a stable donor-recipient structure across languages and tasks (hub donors vs. brittle recipients). We outline implications for risk-aware fine-tuning and model specialisation.

Donors and Recipients: On Asymmetric Transfer Across Tasks and Languages with Parameter-Efficient Fine-Tuning

arXiv:2511.11878v1 Announce Type: new 
Abstract: While large language models (LLMs) show transformative potential in healthcare, their development remains focused on high-resource languages, creating a critical barrier for others as simple translation fails to capture unique clinical and cultural nuances, such as endemic diseases. To address this, we introduce MedPT, the first large-scale, real-world corpus for Brazilian Portuguese, comprising 384,095 authentic question-answer pairs from patient-doctor interactions. The dataset underwent a meticulous multi-stage curation protocol, using a hybrid quantitative-qualitative analysis to filter noise and contextually enrich thousands of ambiguous queries. We further augmented the corpus via LLM-driven annotation, classifying questions into seven semantic types to capture user intent. Our analysis reveals its thematic breadth (3,200 topics) and unique linguistic properties, like the natural asymmetry in patient-doctor communication. To validate its utility, we benchmark a medical specialty routing task: fine-tuning a 1.7B parameter model achieves an outstanding 94\% F1-score on a 20-class setup. Furthermore, our qualitative error analysis shows misclassifications are not random but reflect genuine clinical ambiguities (e.g., between comorbid conditions), proving the dataset's deep semantic richness. We publicly release MedPT to foster the development of more equitable, accurate, and culturally-aware medical technologies for the Portuguese-speaking world.

CONGRAD:Conflicting Gradient Filtering for Multilingual Preference Alignment

Was this article worth reading? Share it