Skip to content
AI News HubLIVE
Original source2 min read

Capacity Allocation at the Source: Sparse Target Optimization for LLM Knowledge Editing

Summary

A new arXiv paper introduces Sparse Target Optimization for knowledge editing in large language models. It shows that interference between target hidden states correlates with parameter-space interference. By applying ℓ1 regularization to prune unnecessary components of knowledge vectors, the method reduces edit-induced interference and improves knowledge coexistence.

SourcearXiv Computational LinguisticsAuthor: Dongyao Chen, Jiayun Lei, Zhiyuan Ji, Zhiying Deng, Wei Liu, Xiaobo Sun
Capacity Allocation at the Source: Sparse Target Optimization for LLM Knowledge Editing
Report an error

The correction channel is not available yet. You can copy the article reference below for later.

Correction instructions
Read article

[Submitted on 8 Nov 2026]

Title:Capacity Allocation at the Source: Sparse Target Optimization for LLM Knowledge Editing

View a PDF of the paper titled Capacity Allocation at the Source: Sparse Target Optimization for LLM Knowledge Editing, by Dongyao Chen and 5 other authors

View PDF HTML (experimental)

Abstract:Knowledge editing has emerged as a promising approach for efficiently updating embedded knowledge in large language models (LLMs). It first computes an ideal target hidden state that steers the LLM toward the new output, and then edits the model parameters so that the original hidden state is mapped to this target. While most existing methods focus on the second stage of parameter editing in preserving other knowledge, we find that the upstream construction of the target hidden state also plays an important role in allocating the model's limited capacity space. We first establish a theoretical connection between interference in the parameter space and interference between target hidden states, showing that the two are positively correlated. Building on this insight, we propose a simple yet effective $\ell_1$ regularization method that prunes away unnecessary ``tentacles'' of each knowledge vector, retaining only the essential components. With fewer extraneous tentacles, each edit affects less other knowledge, enabling better coexistence. Extensive experiments across multiple LLMs and benchmark datasets verify the effectiveness of our method. Code: this https URL.

Comments: neurips2026

Subjects:

Computation and Language (cs.CL)

Cite as: arXiv:2611.12995 [cs.CL]

(or arXiv:2611.12995v1 [cs.CL] for this version)

https://doi.org/10.48550/arXiv.2611.12995

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Lei Jiayun [view email] [v1] Sun, 8 Nov 2026 13:28:43 UTC (260 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled Capacity Allocation at the Source: Sparse Target Optimization for LLM Knowledge Editing, by Dongyao Chen and 5 other authors

View PDF

HTML (experimental)

TeX Source

view license

Additional Features

Audio Summary

Current browse context:

cs.CL

new | recent | 2026-11

Change to browse by:

cs

References & Citations

SciX

Google Scholar

Semantic Scholar

Loading...

Data provided by:

Bibliographic Tools

Bibliographic and Citation Tools

Bibliographic Explorer Toggle

Bibliographic Explorer (What is the Explorer?)

Connected Papers Toggle

Connected Papers (What is Connected Papers?)

Litmaps Toggle

Litmaps (What is Litmaps?)

scite.ai Toggle

scite Smart Citations (What are Smart Citations?)

Code, Data, Media

Code, Data and Media Associated with this Article

alphaXiv Toggle

alphaXiv (What is alphaXiv?)

Links to Code Toggle

CatalyzeX Code Finder for Papers (What is CatalyzeX?)

DagsHub Toggle

DagsHub (What is DagsHub?)

GotitPub Toggle

Gotit.pub (What is GotitPub?)

Huggingface Toggle

Hugging Face (What is Huggingface?)

ScienceCast Toggle

ScienceCast (What is ScienceCast?)

Demos

Demos

Replicate Toggle

Replicate (What is Replicate?)

Spaces Toggle

Hugging Face Spaces (What is Spaces?)

Spaces Toggle

TXYZ.AI (What is TXYZ.AI?)

Related Papers

Recommenders and Search Tools

Link to Influence Flower

Influence Flower (What are Influence Flowers?)

Core recommender toggle

CORE Recommender (What is CORE?)

Author

Venue

Institution

Topic

About arXivLabs

arXivLabs: experimental projects with community collaborators

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)

Key points and analysis

Article intelligence

EngineersAdvanced

Key points

  • Establishes a theoretical link between parameter interference and target hidden state interference.
  • Proposes an ℓ1 regularization method that prunes redundant 'tentacles' from knowledge vectors.
  • Experiments across multiple LLMs and benchmarks verify effectiveness.

Highlights and analysis are generated automatically and may contain errors. Check the original source.