@inproceedings{simon-ewetz-2026-beyond,
title = "Beyond Single Edits: Rethinking Knowledge Editing Evaluation with Multi-Edit Entities and Undirected Probing",
author = "Simon, Dominic and
Ewetz, Rickard",
editor = "Lee, Hung-Yi and
Dev, Sunipa and
Li, Jessy and
Elliott, Desmond",
booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {EMNLP} 2026",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.findings-emnlp.43/",
pages = "868--888",
ISBN = "979-8-89176-462-0",
abstract = "Large Language Models (LLMs) acquire extensive factual knowledge during computationally expensive pretraining. Knowledge editing aims to efficiently update specific facts in a trained model without retraining the entire network. While many editing methods have recently been proposed and show strong performance on existing benchmarks, these benchmarks exhibit several limitations. In particular, they allow only a single edit per entity, rely on highly templated prompts, and evaluate edits using relative probability changes rather than ground-truth correctness. As a result, the capabilities and limitations of current knowledge editing methods remain insufficiently understood. In this work, we introduce the Subject-centric Entity Editing Dataset (SEED), a dataset and evaluation framework designed to address these limitations. SEED organizes edits into sets of related and unrelated facts rather than isolated instances, enabling evaluation when multiple facts about the same subject entity are updated. It also introduces undirected knowledge probes that test whether edited facts can be recalled in general contexts, and ground-truth evaluation metrics that directly measure whether the edited fact appears in the model{'}s output. Using SEED, we test 9 state-of-the-art knowledge editing methods over 10 metrics. These studies find that editing performance decreases by up to 36.9{\%} as the number of edits per entity increases and edit recall decreases by 36.6{\%} with prompts that increase token-wise distance between the edit subject and relation."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="simon-ewetz-2026-beyond">
<titleInfo>
<title>Beyond Single Edits: Rethinking Knowledge Editing Evaluation with Multi-Edit Entities and Undirected Probing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dominic</namePart>
<namePart type="family">Simon</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rickard</namePart>
<namePart type="family">Ewetz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hung-Yi</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sunipa</namePart>
<namePart type="family">Dev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jessy</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Desmond</namePart>
<namePart type="family">Elliott</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Budapest, Hungary</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-462-0</identifier>
</relatedItem>
<abstract>Large Language Models (LLMs) acquire extensive factual knowledge during computationally expensive pretraining. Knowledge editing aims to efficiently update specific facts in a trained model without retraining the entire network. While many editing methods have recently been proposed and show strong performance on existing benchmarks, these benchmarks exhibit several limitations. In particular, they allow only a single edit per entity, rely on highly templated prompts, and evaluate edits using relative probability changes rather than ground-truth correctness. As a result, the capabilities and limitations of current knowledge editing methods remain insufficiently understood. In this work, we introduce the Subject-centric Entity Editing Dataset (SEED), a dataset and evaluation framework designed to address these limitations. SEED organizes edits into sets of related and unrelated facts rather than isolated instances, enabling evaluation when multiple facts about the same subject entity are updated. It also introduces undirected knowledge probes that test whether edited facts can be recalled in general contexts, and ground-truth evaluation metrics that directly measure whether the edited fact appears in the model’s output. Using SEED, we test 9 state-of-the-art knowledge editing methods over 10 metrics. These studies find that editing performance decreases by up to 36.9% as the number of edits per entity increases and edit recall decreases by 36.6% with prompts that increase token-wise distance between the edit subject and relation.</abstract>
<identifier type="citekey">simon-ewetz-2026-beyond</identifier>
<location>
<url>https://aclanthology.org/2026.findings-emnlp.43/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>868</start>
<end>888</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Beyond Single Edits: Rethinking Knowledge Editing Evaluation with Multi-Edit Entities and Undirected Probing
%A Simon, Dominic
%A Ewetz, Rickard
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Findings of the Association for Computational Linguistics: EMNLP 2026
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-462-0
%F simon-ewetz-2026-beyond
%X Large Language Models (LLMs) acquire extensive factual knowledge during computationally expensive pretraining. Knowledge editing aims to efficiently update specific facts in a trained model without retraining the entire network. While many editing methods have recently been proposed and show strong performance on existing benchmarks, these benchmarks exhibit several limitations. In particular, they allow only a single edit per entity, rely on highly templated prompts, and evaluate edits using relative probability changes rather than ground-truth correctness. As a result, the capabilities and limitations of current knowledge editing methods remain insufficiently understood. In this work, we introduce the Subject-centric Entity Editing Dataset (SEED), a dataset and evaluation framework designed to address these limitations. SEED organizes edits into sets of related and unrelated facts rather than isolated instances, enabling evaluation when multiple facts about the same subject entity are updated. It also introduces undirected knowledge probes that test whether edited facts can be recalled in general contexts, and ground-truth evaluation metrics that directly measure whether the edited fact appears in the model’s output. Using SEED, we test 9 state-of-the-art knowledge editing methods over 10 metrics. These studies find that editing performance decreases by up to 36.9% as the number of edits per entity increases and edit recall decreases by 36.6% with prompts that increase token-wise distance between the edit subject and relation.
%U https://aclanthology.org/2026.findings-emnlp.43/
%P 868-888
Markdown (Informal)
[Beyond Single Edits: Rethinking Knowledge Editing Evaluation with Multi-Edit Entities and Undirected Probing](https://aclanthology.org/2026.findings-emnlp.43/) (Simon & Ewetz, Findings 2026)
ACL