Papers › MMKE-Bench: A Multimodal Editing Benchmark for Diverse Visual Knowledge

MMKE-Bench: A Multimodal Editing Benchmark for Diverse Visual Knowledge

27 Feb 2025arXiv:2502.19870archive 2025-07-28

Yuntao Du, Kailin Jiang, Zhi Gao, Chenrui Shi, Zilong Zheng, Siyuan Qi, Qing Li

Knowledge editing techniques have emerged as essential tools for updating the factual knowledge of large language models (LLMs) and multimodal models (LMMs), allowing them to correct outdated or inaccurate information without retraining from scratch. However, existing benchmarks for multimodal knowledge editing primarily focus on entity-level knowledge represented as simple triplets, which fail to capture the complexity of real-world multimodal information. To address this issue, we introduce MMKE-Bench, a comprehensive MultiModal Knowledge Editing Benchmark, designed to evaluate the ability of LMMs to edit diverse visual knowledge in real-world scenarios. MMKE-Bench addresses these limitations by incorporating three types of editing tasks: visual entity editing, visual semantic editing, and user-specific editing. Besides, MMKE-Bench uses free-form natural language to represent and edit knowledge, offering a more flexible and effective format. The benchmark consists of 2,940 pieces of knowledge and 8,363 images across 33 broad categories, with evaluation questions automatically generated and human-verified. We assess five state-of-the-art knowledge editing methods on three prominent LMMs, revealing that no method excels across all criteria, and that visual and user-specific edits are particularly challenging. MMKE-Bench sets a new standard for evaluating the robustness of multimodal knowledge editing techniques, driving progress in this rapidly evolving field.

PaperPDFCodeCode Syntology ran

In Syntology View this paper on Syntology: its repositories, every harvested function with whether it ran, its licence and the call to fetch it.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2502.19870")

Code

Syntology Ran 8 of 12 code samples harvested from 1 repository linked to this paper; 4 have no recorded run. Of those that ran: 3 ran · our draft was wrong; 1 ran · fixture could not drive it; 4 ran with no contract checked.

By repository: official repository: 12 samples from 1 repository, 8 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

MMKE-Bench-ICLR/MMKE-Bench officialmentioned on GitHubpytorchMIT report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

12 samples harvested; 8 ran; 0 honoured the contract we drafted; 4 have no recorded run. Read from Syntology's graph 2026-09-25; that is when this build read the record, not when the samples ran.

3ran · our draft was wrong
1ran · fixture could not drive it
4ran
4unverified

Licence: 0 of the 12 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from MMKE-Bench-ICLR/MMKE-Bench. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

binary_log_probs MMKE-Bench-ICLR/MMKE-Bench/easyeditor/trainer/losses.py official repository ran · our draft was wrong MIT (permissive) · 27659a9c234ffb11 · report
chunk_it MMKE-Bench-ICLR/MMKE-Bench/KE/src/utils.py official repository ran fingerprinted MIT (permissive) · 3f4963e78e50be03 · report
hierarchical_subsequence MMKE-Bench-ICLR/MMKE-Bench/easyeditor/util/nethook.py official repository ran MIT (permissive) · 920b394e7ad80c53 · report
label_smoothed_nll_loss MMKE-Bench-ICLR/MMKE-Bench/KE/src/utils.py official repository ran · our draft was wrong MIT (permissive) · 96b6713ff1c322ca · report
multiclass_log_probs MMKE-Bench-ICLR/MMKE-Bench/easyeditor/trainer/losses.py official repository ran · fixture could not drive it MIT (permissive) · 4609b1b3a11479ce · report
normalize MMKE-Bench-ICLR/MMKE-Bench/KE/src/utils.py official repository ran fingerprinted MIT (permissive) · 23d3acf0aced66d5 · report
recursive_copy MMKE-Bench-ICLR/MMKE-Bench/easyeditor/util/nethook.py official repository ran · our draft was wrong MIT (permissive) · 70f6ab8bde55420e · report
subsequence MMKE-Bench-ICLR/MMKE-Bench/easyeditor/util/nethook.py official repository ran MIT (permissive) · 440ff98c2b1ae1aa · report
get_model MMKE-Bench-ICLR/MMKE-Bench/easyeditor/trainer/models.py official repository unverified MIT (permissive) · a0e211c2cfa8303a · report
get_model MMKE-Bench-ICLR/MMKE-Bench/KE/src/models/get_models.py official repository unverified MIT (permissive) · 5fd83ef8bc33e7e7 · report
get_tokenizer MMKE-Bench-ICLR/MMKE-Bench/easyeditor/trainer/models.py official repository unverified MIT (permissive) · 77ff1d0bef624163 · report
kl_loc_loss MMKE-Bench-ICLR/MMKE-Bench/easyeditor/trainer/losses.py official repository unverified MIT (permissive) · bcc592aa5c1e2bb3 · report

Tasks

knowledge editing

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Focus

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections