Knowledge Editing refers to techniques for precisely modifying specific facts or behaviors encoded in a trained language model without retraining the full model or degrading unrelated capabilities. Methods include locate-and-edit approaches that directly alter model weights, adapter-based memory modules that route queries to updated knowledge, and representation-space interventions. Research challenges include achieving edit locality to prevent unintended changes, maintaining generalization across paraphrases, and scaling to large numbers of edits in lifelong settings.

Posts

Representation Interventions Enable Lifelong Knowledge Memory Control in LLMs

/0 Comments/in /by

Large language models (LLMs) often produce incorrect or outdated content after being employed. Efficient and accurate knowledge up-dates without costly retraining are a major challenge. This problem is particularly challenging in lifelong settings, where complex, unstructured knowledge must coexist without interference. We introduce RILKE (Representation Intervention for Lifelong KnowledgE Control), a robust and scalable method that treats knowledge control as interventions within the model’s representation space. Leveraging representation-space expressiveness, we identify two key properties enabling RILKE to achieve fine-grained control over complex, un-structured knowledge while maintaining general utility with frozen base weights. During training, RILKE learns paraphrase-robust and edit-localized modules that limit each update to a low-dimensional subspace to minimize cross-edit interference. At inference, a query-adaptive router selects the appropriate module to guide the model’s generation. Across LLaMA and Qwen models, RILKE scales effectively to large-scale benchmarks, demonstrating high edit success and strong paraphrase generalization while preserving general utility with modest memory overhead. These results show RILKE is an effective and scalable solution for lifelong knowledge control in LLMs.

Read more

LOKA: Conflict-Aware LLM Knowledge Update with Adaptive Knowledge Memory

/0 Comments/in /by

Large Language Models (LLMs) have achieved remarkable success in natural language processing by encoding extensive knowledge, but their utility relies on timely updates as human knowledge keeps evolving. In this paper, we investigate the problem of LLM knowledge updates, which requires simultaneously unlearning un-wanted information and learning new knowledge. Existing approaches that tackle unlearning and learning separately encounter task conflicts and knowledge management issues when applied to comprehensive knowledge updates. In this paper, we validate our findings with theoretical analysis and empirical evidence, and propose LOKA, a conflict-aware framework for Large language mOdel Knowledge updAtes. During training, LOKA introduces an adaptive knowledge memory approach in which updated knowledge is allocated across multiple memory units. During inference, LOKA retrieves the most relevant memory unit from the knowledge memory and integrates it with the original LLM to apply updated knowledge, while a learning-based router controls the activation of the knowledge memory to improve knowledge utilization. Extensive experiments demonstrate the efficacy of LOKA in achieving accurate, flexible, and conflict-aware knowledge updates.

Read more

Mind the Gap in Cultural Alignment: Task-Aware Culture Management for Large Language Models

/0 Comments/in /by

Large language models (LLMs) are increasingly deployed in culturally sensitive real-world tasks. However, existing cultural alignment ap-roaches fail to align LLMs’ broad cultural values with the specific goals of downstream tasks and suffer from cross-culture interference. We propose CultureManager, a novel pipeline for task-specific cultural alignment. CultureManager synthesizes task-aware cultural data in line with target task formats, grounded in culturally relevant web search results. To prevent conflicts between cultural norms, it manages multi-culture knowledge learned in separate adapters with a culture router that selects the appropriate one to apply. Experiments across five national cultures and ten culture-sensitive tasks show consistent improvements over prompt-based and fine-tuning baselines. Our results demonstrate the necessity of task adaptation and modular culture management for effective cultural alignment.

Read more

NEC Labs America Attends ACL 2026 San Diego July 2-7, 2026

/in /by

NEC Laboratories America heads to ACL 2026 in San Diego, California, July 2–7, to present accepted papers spanning knowledge updating and memory control in large language models, task-aware cultural alignment, uncertainty-aware reasoning, and adaptive chain-of-thought optimization, representing some of the most active frontiers in NLP and AI research today.

Read more