Dynamic Retriever for In-Context Knowledge Editing via Policy Optimization

• URL: http://arxiv.org/abs/2510.21059v2
• Date: Mon, 27 Oct 2025 00:25:35 GMT
• Title: Dynamic Retriever for In-Context Knowledge Editing via Policy Optimization
• Authors: Mahmud Wasif Nafee, Maiqi Jiang, Haipeng Chen, Yanfu Zhang,
• Abstract summary: We propose Dynamic Retriever for In-Context Knowledge Editing (DR-IKE)<n>DR-IKE is a lightweight framework that trains a BERT retriever with REINFORCE to rank demonstrations by editing reward.<n>It improves edit success by up to 17.1%, reduces latency by 41.6%, and preserves accuracy on unrelated queries.
• Score: 11.338802325779866
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large language models (LLMs) excel at factual recall yet still propagate stale or incorrect knowledge. In-context knowledge editing offers a gradient-free remedy suitable for black-box APIs, but current editors rely on static demonstration sets chosen by surface-level similarity, leading to two persistent obstacles: (i) a quantity-quality trade-off, and (ii) lack of adaptivity to task difficulty. We address these issues by dynamically selecting supporting demonstrations according to their utility for the edit. We propose Dynamic Retriever for In-Context Knowledge Editing (DR-IKE), a lightweight framework that (1) trains a BERT retriever with REINFORCE to rank demonstrations by editing reward, and (2) employs a learnable threshold to prune low-value examples, shortening the prompt when the edit is easy and expanding it when the task is hard. DR-IKE performs editing without modifying model weights, relying solely on forward passes for compatibility with black-box LLMs. On the COUNTERFACT benchmark, it improves edit success by up to 17.1%, reduces latency by 41.6%, and preserves accuracy on unrelated queries, demonstrating scalable and adaptive knowledge editing. The code is available at https://github.com/mwnafee/DR-IKE .

Related papers

• Consistency-Aware Editing for Entity-level Unlearning in Language Models [53.522931419965424]
  We introduce a novel consistency-aware editing (CAE) framework for entity-level unlearning.<n>CAE aggregates a diverse set of prompts related to a target entity, including its attributes, relations, and adversarial paraphrases.<n>It then jointly learns a low-rank update guided by a consistency regularizer that aligns the editing directions across prompts.
  arXiv  Detail & Related papers  (2025-12-19T15:18:07Z)
• EvoEdit: Lifelong Free-Text Knowledge Editing through Latent Perturbation Augmentation and Knowledge-driven Parameter Fusion [31.09201415423854]
  We propose Lifelong Free-text Knowledge Editing (LF-Edit)<n>It enables models to incorporate updates expressed in natural language and supports continual editing over time.<n>Despite its promise, LF-Edit faces the dual challenge of integrating new knowledge while mitigating the forgetting of prior information.
  arXiv  Detail & Related papers  (2025-12-04T07:55:36Z)
• Aligning Language Models with Real-time Knowledge Editing [11.503574001763246]
  We introduce CRAFT, an ever-evolving real-world benchmark for knowledge editing.<n>It features well-designed paired edits for composite reasoning, and evaluates models on alias portability and temporal and common-sense locality.<n> Towards flexible real-time editing, we propose KEDAS, a novel paradigm of knowledge editing alignment featuring diverse edit augmentation and self-adaptive post-alignment inference.
  arXiv  Detail & Related papers  (2025-08-02T10:25:36Z)
• InComeS: Integrating Compression and Selection Mechanisms into LLMs for Efficient Model Editing [86.17245523439514]
  In-context learning is a promising editing method by comprehending edit information through context encoding.<n>This method is constrained by the limited context window of large language models.<n>We propose InComeS, a flexible framework that enhances LLMs' ability to process editing contexts.
  arXiv  Detail & Related papers  (2025-05-28T09:20:18Z)
• Keys to Robust Edits: from Theoretical Insights to Practical Advances [20.10464264597003]
  Large language models (LLMs) struggle with maintaining accurate knowledge due to conflicting/outdated parametric memories.<n>Our solution introduces textitRobust Edit Pathway (REP), a plug-and-play module that disentangles editing keys from native model representations.
  arXiv  Detail & Related papers  (2024-10-12T02:54:12Z)
• ELDER: Enhancing Lifelong Model Editing with Mixture-of-LoRA [55.697627106315004]
  Large language models (LLMs) require model editing to efficiently update specific knowledge within them and avoid factual errors.<n>Previous approaches manage sequential edits by freezing original parameters and discretely allocating new parameters for each knowledge update.<n>We propose ELDER, a novel approach to create a continuous association between data and adapters.
  arXiv  Detail & Related papers  (2024-08-19T02:27:00Z)
• Time Sensitive Knowledge Editing through Efficient Finetuning [35.79991957163508]
  Large Language Models (LLMs) have demonstrated impressive capability in different tasks and are bringing transformative changes to many domains. Keeping the knowledge in LLMs up-to-date remains a challenge once pretraining is complete. Existing locate-and-edit knowledge editing (KE) method suffers from two limitations.
  arXiv  Detail & Related papers  (2024-06-06T20:41:36Z)
• Lifelong Knowledge Editing for LLMs with Retrieval-Augmented Continuous Prompt Learning [30.554641380670315]
  We introduce RECIPE, a ContInuous Prompt lEarning method to boost editing efficacy and inference efficiency in lifelong learning.<n> RECIPE first converts knowledge statements into short and informative continuous prompts, prefixed to the LLM's input query embedding.<n>It further integrates the Knowledge Sentinel (KS) that acts as an intermediary to calculate a dynamic threshold.<n>Our retriever and prompt encoder are jointly trained to achieve editing properties, i.e. reliability, generality, and locality.
  arXiv  Detail & Related papers  (2024-05-06T08:52:11Z)
• Robust and Scalable Model Editing for Large Language Models [75.95623066605259]
  We propose EREN (Edit models by REading Notes) to improve the scalability and robustness of LLM editing. Unlike existing techniques, it can integrate knowledge from multiple edits, and correctly respond to syntactically similar but semantically unrelated inputs.
  arXiv  Detail & Related papers  (2024-03-26T06:57:23Z)
• Learning to Edit: Aligning LLMs with Knowledge Editing [101.96620267293731]
  We propose a Learning to Edit (LTE) framework, focusing on teaching large language models to apply updated knowledge into input questions. LTE features a two-phase process: (i) the Alignment Phase, which fine-tunes LLMs on a meticulously curated parallel dataset to make reliable, in-scope edits. We demonstrate LTE's superiority in knowledge editing performance, robustness in both batch and sequential editing, minimal interference on general tasks, and rapid editing speeds.
  arXiv  Detail & Related papers  (2024-02-19T07:45:17Z)
• EVEDIT: Event-based Knowledge Editing with Deductive Editing Boundaries [69.72012539060731]
  We introduce a theoretical framework for efficient knowledge editing (KE) in large language models (LLMs) We propose a novel task of event-based knowledge editing that pairs facts with event descriptions. We empirically demonstrate the superiority of event-based editing over the existing setting on resolving uncertainty in edited models.
  arXiv  Detail & Related papers  (2024-02-17T16:34:50Z)
• Knowledge Editing on Black-box Large Language Models [37.17131278142237]
  Knowledge editing aims to efficiently and precisely modify the behavior of large language models (LLMs) to update specific knowledge. Current research primarily focuses on white-box LLMs editing, overlooking an important scenario: black-box LLMs editing. We introduce KE on black-box LLMs and then propose a comprehensive evaluation framework to overcome the limitations of existing evaluations. Experiments and analysis on two benchmarks demonstrate that postEdit outperforms all baselines and achieves strong generalization.
  arXiv  Detail & Related papers  (2024-02-13T17:59:34Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.