AI Paper Atlas

Research map / Large language models / Retrieval and knowledge

DynEdit: Dynamic Entropy-Guided Sequential Editing for Large Language Models

Jinhu Fu, Yan Bai, Yihang Lou, Li Sun, Jiahong Wu, Xiangxiang Chu, Sen Su

NeurIPS 2026 · Large language models › Retrieval and knowledge · approach: Knowledge editing in LLMs · 0 citations (OpenAlex)

Read the paper

AI-extracted summary. Written by AI from the paper's full text. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Proposes DynEdit, a knowledge-editing method for LLMs that uses dynamic entropy-guided segmentation to sequentially edit long-sequence knowledge targets instead of fixed chunks.

Problem

Parameter-based knowledge editing struggles with long-sequence targets: single-point editors give insufficient coverage, while fixed chunk-based editors spread effort uniformly and fail to focus on difficult, information-dense tokens.

Approach

Uses token-level entropy to dynamically partition long editing targets into variable-length windows so that editing effort concentrates on high-entropy, information-dense spans, applied sequentially.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add entropy-guided sliding and token weighting to AnyEdit (MEMIT)AnyEdit · UnKE benchmark Paraphrase (Llama-3-8B)BLEU: 66.29 -> 80.3Improved
add entropy-guided sliding and token weighting to AnyEdit (MEMIT)AnyEdit · UnKE benchmark Original (Llama-3-8B)BLEU: 77.91 -> 91.6Improved
add entropy-guided editing to UnKE-based AnyEdit*AnyEdit* · UnKE benchmark Paraphrase (Qwen-2.5-7B)BLEU: 47.17 -> 66.13Improved
add entropy-guided editing to UnKE-based AnyEdit*AnyEdit* · UnKE benchmark Original (Llama-3-8B)BLEU: 99.54 -> 99.19No clear effect
add entropy-guided editing to UnKE-based AnyEdit*AnyEdit* · CounterFact Original (Llama-3-8B)BLEU: 99.93 -> 98.26Hurt
add entropy-guided editing to MEMIT-based AnyEditAnyEdit · MQuAKE Original (Llama-3-8B)Rouge-L: 94.28 -> 93.11Hurt
add entropy-guided editing to AlphaEdit+AnyEditAlphaEdit+AnyEdit · UnKEBench Original (Qwen3-8B)BLEU: 40.88 -> 68.16Improved
add entropy-guided editing to MEMIT+AnyEditMEMIT+AnyEdit · UnKEBench Original (Qwen3-8B)BLEU: 31.29 -> 44.52Improved
add entropy-guided editing to AnyEditAnyEdit · EditEverything math (Llama-3-8B)Rouge-L: 70.73 -> 97.76Improved
add dynamic entropy-guided sliding strategy (ablation)DynEdit · UnKE, CounterFact, MQuAKE BLEUBLEUImproved
add entropy-guided token weighting (ablation)DynEdit · UnKE, CounterFact, MQuAKE BLEUBLEUImproved
use entropy-guided editing instead of fixed chunks on MMLU and IFEvalAnyEdit · MMLU, IFEvalaccuracyNo clear effect

Experimental setup

Baselines: single-point editors fixed chunk-based editors

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy