Overview

Knowledge editing aims to correct or add information in a model without retraining it from scratch, so models can adapt to new facts, rules, and user-specific information. Approaches include targeted weight updates, low-rank adapters and null-space constraints, as well as external memories and retrieval systems that supply updates at inference time. Researchers test whether edits work across paraphrases, related questions, and multi-hop reasoning while measuring locality, capability retention, and stability over long sequences of updates. A central tension is that strong performance on direct edit queries may reflect surface compliance rather than changed internal knowledge, and edits can interfere with other facts, reasoning, or safety behavior over time.

Latest papers

95 papers15 papers in the last four weeks, up 36% on the four weeks before. 0.1% of all new papers.

Feb 2, 2026

Edit Knowledge, Not Just Facts via Multi-Step Reasoning over Background Stories

Enabling artificial intelligence systems, particularly large language models, to update knowledge and flexibly apply it during reasoning remains a central challenge. Existing knowledge editing approaches emphasize atomic facts, improving factual recall but often failing to integrate updated information into a coherent framework usable across contexts. In this work, we argue that knowledge update is fundamentally a reasoning problem rather than a memorization problem. Consequently, a model should be trained in situations where the new information is instrumental to solving a task, combined with pre-existing knowledge, and exercised through multi-step reasoning. Based on this insight, we propose a training strategy based on three principles. First, new knowledge is introduced as a coherent background story that contextualizes novel facts and explains their relation to existing knowledge. Second, models are trained using self-generated multi-hop questions that require multi-step reasoning involving the new information. Third, training is done using knowledge distillation, forcing a student model to internalize the teacher's reasoning behavior without access to the novel information. Experiments show that models trained with this strategy effectively leverage newly acquired knowledge during reasoning and achieve remarkable performance on challenging questions that require combining multiple new facts.
Nov 25, 2025

Representation Interventions Enable Lifelong Knowledge Memory Control in LLMs

Large language models (LLMs) often produce incorrect or outdated content after being employed. Efficient and accurate knowledge updates 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, unstructured 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.
Nov 8, 2025

Can Fine-Tuning Erase Your Edits? On the Fragile Coexistence of Knowledge Editing and Adaptation

Knowledge editing (KE) offers a lightweight alternative to retraining for updating 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 practical objectives: removing covert or malicious edits, and preserving beneficial edits. If fine-tuning impairs edits (Fig.1), current KE methods become less efficient, as a newly fine-tuned model requires re-editing; 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 across 254 experimental configurations. Our results show that in general, edits decay substantially after subsequent fine-tuning. AlphaEdit exhibits the greatest decay on the zsRE benchmark when applied to GPT-J, where 25.27% of previously successful edits become unsuccessful after fine-tuning. We further find that fine-tuning only the edited layers is sufficient to effectively remove edits, while incurring only modest degradation in downstream performance. Surprisingly, fine-tuning non-edited layers leads to greater edit decay than all-layer fine-tuning. Besides, our activation space analysis reveals that fine-tuning produces a larger and more coherent representational shift, both in magnitude and direction, than KE. Overall, our study underscores the necessity of evaluating KE within the broader LLM application pipeline.
Sep 3, 2025

LMEnt: A Suite for Analyzing Knowledge in Language Models from Pretraining Data to Representations

Language models (LMs) increasingly drive real-world applications that require world knowledge. However, the internal processes through which models turn data into representations of knowledge and beliefs about the world are poorly understood. To facilitate such studies, we present LMEnt, a suite including (1) a knowledge-rich pretraining corpus, fully annotated with entity mentions based on Wikipedia, (2) an entity-based retrieval method over pretraining data that outperforms existing tools by as much as 80.4%, and (3) 12 pretrained LMs with up to 1B parameters and 4K intermediate checkpoints, with comparable performance to popular open-source models on knowledge tasks. Together, these resources provide a controlled environment for analyzing connections between entity mentions in pretraining data and downstream performance. We show the utility of LMEnt by studying knowledge acquisition over training, finding that entity co-occurrence and mention forms-which are difficult to study with existing tools-affect learning trends. Moreover, as LMs form stronger associations between entities, their facts are harder to edit in-context, whereas inconsistencies in model predictions over training are indicative of editing success. We release LMEnt to support studies of knowledge in LMs, including knowledge representations, plasticity, editing, attribution, hallucinations, and learning dynamics.
Jul 4, 2025

EMERGE: A Benchmark for Updating Knowledge Graphs with Emerging Textual Knowledge

Knowledge Graphs (KGs) are structured knowledge repositories containing entities and relations between them. In this paper, we study the problem of automatically updating KGs over time in response to evolving knowledge in unstructured textual sources. Addressing this problem requires identifying a wide range of update operations based on the state of an existing KG at a given time and the information extracted from text. This contrasts with traditional information extraction pipelines, which extract knowledge from text independently of the current state of a KG. To address this challenge, we propose a generic and extensible pipeline that pairs textual passages with the KG edit operations they induce on a given KG snapshot. We instantiate this pipeline on the Wikidata knowledge graph and the English Wikipedia corpus to create EMERGE, a dataset of 233K Wikipedia passages associated with a total of 1.19 million KG edits across seven yearly Wikidata snapshots from 2019 to 2025. Our experimental results highlight key challenges in updating KG snapshots based on emerging textual knowledge, particularly in integrating knowledge expressed in text with the existing KG structure. We further show that KG access substantially improves executable updates and enables triple deprecation. These findings position EMERGE as a benchmark for developing methods that keep KGs up to date with emerging textual knowledge. The dataset (https://huggingface.co/datasets/klimzaporojets/emerge-benchmark) and code (https://github.com/klimzaporojets/emerge) are publicly available.