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

CardsList

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

  1. Representation Interventions Enable Lifelong Knowledge Memory Control in LLMs

    Nov 25, 2025Xuyuan Liu, Shengyu Chen, Xinshuai Dong +6Knowledge EditingContinual Learning for LLMs

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

    Nov 8, 2025Yinjie Cheng, Paul Youssef, Christin Seifert +2Knowledge EditingLLM Fine-Tuning

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

    Sep 3, 2025Daniela Gottesman, Alon Gilae-Dotan, Ido Cohen +4Language Model PretrainingKnowledge Editing

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

    Jul 4, 2025Klim Zaporojets, Daniel Daza, Edoardo Barba +3Knowledge GraphsKnowledge Editing