BOUND refines LLMs' package-validity boundary via targeted editing to cut package hallucination rates by 79.9% on edit prompts and 65.4% on unseen prompts in recommendation tasks while generalizing to code generation.
hub
A Comprehensive Study of Knowledge Editing for Large Language Models
30 Pith papers cite this work, alongside 20 external citations. Polarity classification is still indexing.
30
Pith papers citing it
20
external citations · external index
hub tools
citation-role summary
background 4
citation-polarity summary
roles
background 4polarities
background 4representative citing papers
Introduces Latent Adversarial Robustification and Rank-Constrained Subspace Learning to enable robust generalization in multimodal knowledge editing through adversarial subspace alignment.
M-ORE decouples text and visual update statistics in MLLMs and applies recursive low-rank edits in an orthogonal subspace to reduce cross-modal conflict and long-horizon interference.
EditPropBench evaluates LLM editors on propagating factual edits to dependent claims in synthetic scientific manuscripts, showing that even the strongest systems miss roughly 30% of required updates on hard cases.
Graph Memory Transformer replaces FFN sublayers with a graph memory cell using 128 centroids and transition matrices per block, yielding stable training at 82.2M parameters but higher validation loss than a 103M dense baseline.
MisEdu-RAG builds concept and instance hypergraphs for two-stage retrieval of pedagogical knowledge and student errors, improving feedback quality on the MisstepMath benchmark by 10.95% token-F1 and up to 15.3% on response dimensions.
MetaKE unifies knowledge editing stages via bi-level optimization and a structural gradient proxy to improve the accuracy-editability trade-off over prior methods.
Presents CRAFT dataset and KEDAS paradigm for real-time knowledge editing, claiming better balanced performance on dynamic and static benchmarks than prior methods.
ScopeEdit decomposes MLLM edits into modality-local and evidence-gated shared branches using orthogonal low-rank spaces and recursive updates to improve scoped cross-modal transfer while preserving locality and efficiency.
Knowledge editing methods redistribute and suppress rather than overwrite facts in LLMs, creating narrow vulnerable regions in representation space that adversarial prompts can exploit.
LOKI enables memory-free lifelong knowledge editing via HSIC-based dynamic layer selection and null-space constrained updates, reporting up to 14% higher average accuracy than prior methods.
Introduces a benchmark using logical rules from knowledge graphs to generate multi-hop questions that evaluate whether knowledge edits in LLMs propagate to entailed facts, finding up to 24% performance gaps for methods like ROME and FT.
The paper presents the FOE benchmark (261 figures, 19 categories, 2178 records) showing current LLM opinion editing is inconsistent with evidence and introduces a self-generated evidence alignment method to address it.
Parameter-based knowledge editing in LLMs induces reasoning collapse via dimensional collapse and is consistently outperformed by a retrieval baseline across varied edit counts, knowledge complexity, and evaluation metrics.
LDKE framework localizes fact-specific layers and disentangles inputs to improve generalization and locality in multimodal knowledge editing for MLLMs.
The paper proposes CODE for causal knowledge editing in LLMs via on-policy self-distillation, reducing self-refutation to 1.8% and achieving up to 83.5% multi-hop accuracy.
Theoretical analysis of continual factual knowledge acquisition shows data replay stabilizes pretrained knowledge by shifting convergence dynamics while regularization only slows forgetting, leading to the STOC method for attention-based replay selection.
EditRisk-Bench demonstrates that malicious knowledge editing reliably induces incorrect or unsafe reasoning in LLMs while largely preserving general capabilities.
Proposes forward replay of target hidden states from the first editing layer instead of backward spreading, claiming equivalent complexity but higher accuracy for LLM parameter editing.
LLMs prioritize task-appropriate reasoning over conflicting instructions, but reasoning types are linearly encoded in middle-to-late layers, allowing activation steering to raise instruction compliance by up to 29%.
EVOREC integrates locate-then-edit model editing with FA-constrained decoding to improve LLM-based service recommendation under evolution, reporting 25.9% average relative gain in Recall@5 over baselines and 22.3% over fine-tuning in dynamic scenarios.
Fixed golden layers for knowledge editing in LLMs can be identified via gradient attribution and generalize across queries and datasets.
CrispEdit edits LLMs via low-curvature projections using Bregman divergence and K-FAC approximations, achieving high edit success with under 1% average capability degradation.
The survey organizes RAG methods via a taxonomy of query-based, logits-based, latent, and parametric fusion with comparisons on accessibility, efficiency, applications, and challenges.
citing papers explorer
-
Mitigating Package Hallucinations in Large Language Models via Model Editing
BOUND refines LLMs' package-validity boundary via targeted editing to cut package hallucination rates by 79.9% on edit prompts and 65.4% on unseen prompts in recommendation tasks while generalizing to code generation.
-
Beyond Binary Edits Robust Multimodal Knowledge Editing with Adversarial Subspace Alignment
Introduces Latent Adversarial Robustification and Rank-Constrained Subspace Learning to enable robust generalization in multimodal knowledge editing through adversarial subspace alignment.
-
Modality-Decoupled Online Recursive Editing
M-ORE decouples text and visual update statistics in MLLMs and applies recursive low-rank edits in an orthogonal subspace to reduce cross-modal conflict and long-horizon interference.
-
EditPropBench: Measuring Factual Edit Propagation in Scientific Manuscripts
EditPropBench evaluates LLM editors on propagating factual edits to dependent claims in synthetic scientific manuscripts, showing that even the strongest systems miss roughly 30% of required updates on hard cases.
-
Graph Memory Transformer (GMT)
Graph Memory Transformer replaces FFN sublayers with a graph memory cell using 128 centroids and transition matrices per block, yielding stable training at 82.2M parameters but higher validation loss than a 103M dense baseline.
-
MisEdu-RAG: A Misconception-Aware Dual-Hypergraph RAG for Novice Math Teachers
MisEdu-RAG builds concept and instance hypergraphs for two-stage retrieval of pedagogical knowledge and student errors, improving feedback quality on the MisstepMath benchmark by 10.95% token-F1 and up to 15.3% on response dimensions.
-
MetaKE: Meta-Learning for Knowledge Editing Toward a Better Accuracy-Editability Trade-off
MetaKE unifies knowledge editing stages via bi-level optimization and a structural gradient proxy to improve the accuracy-editability trade-off over prior methods.
-
Aligning Language Models with Real-time Knowledge Editing
Presents CRAFT dataset and KEDAS paradigm for real-time knowledge editing, claiming better balanced performance on dynamic and static benchmarks than prior methods.
-
Multimodal Knowledge Edit-Scoped Generalization for Online Recursive MLLM Editing
ScopeEdit decomposes MLLM edits into modality-local and evidence-gated shared branches using orthogonal low-rank spaces and recursive updates to improve scoped cross-modal transfer while preserving locality and efficiency.
-
Exposing the Illusion of Erasure in Knowledge Editing for LLMs
Knowledge editing methods redistribute and suppress rather than overwrite facts in LLMs, creating narrow vulnerable regions in representation space that adversarial prompts can exploit.
-
LOKI: Memory-Free Null-Space Constrained Lifelong Knowledge Editing
LOKI enables memory-free lifelong knowledge editing via HSIC-based dynamic layer selection and null-space constrained updates, reporting up to 14% higher average accuracy than prior methods.
-
Benchmarking Knowledge Editing using Logical Rules
Introduces a benchmark using logical rules from knowledge graphs to generate multi-hop questions that evaluate whether knowledge edits in LLMs propagate to entailed facts, finding up to 24% performance gaps for methods like ROME and FT.
-
Can Factual Opinions Be Edited (Manipulated) in Large Language Models?
The paper presents the FOE benchmark (261 figures, 19 categories, 2178 records) showing current LLM opinion editing is inconsistent with evidence and introduces a self-generated evidence alignment method to address it.
-
Revisiting Parameter-Based Knowledge Editing in Large Language Models: Theoretical Limits and Empirical Evidence
Parameter-based knowledge editing in LLMs induces reasoning collapse via dimensional collapse and is consistently outperformed by a retrieval baseline across varied edit counts, knowledge complexity, and evaluation metrics.
-
Towards Localized and Disentangled Knowledge Editing for Multimodal Large Language Models
LDKE framework localizes fact-specific layers and disentangles inputs to improve generalization and locality in multimodal knowledge editing for MLLMs.
-
From Fact Overwriting to Knowledge Evolution: Causal Editing via On-Policy Self-Distillation
The paper proposes CODE for causal knowledge editing in LLMs via on-policy self-distillation, reducing self-refutation to 1.8% and achieving up to 83.5% multi-hop accuracy.
-
Towards Understanding Continual Factual Knowledge Acquisition of Language Models: From Theory to Algorithm
Theoretical analysis of continual factual knowledge acquisition shows data replay stabilizes pretrained knowledge by shifting convergence dynamics while regularization only slows forgetting, leading to the STOC method for attention-based replay selection.
-
Benchmarking Safety Risks of Knowledge-Intensive Reasoning under Malicious Knowledge Editing
EditRisk-Bench demonstrates that malicious knowledge editing reliably induces incorrect or unsafe reasoning in LLMs while largely preserving general capabilities.
-
From Backward Spreading to Forward Replay: Revisiting Target Construction in LLM Parameter Editing
Proposes forward replay of target hidden states from the first editing layer instead of backward spreading, claiming equivalent complexity but higher accuracy for LLM parameter editing.
-
Compliance versus Sensibility: On the Reasoning Controllability in Large Language Models
LLMs prioritize task-appropriate reasoning over conflicting instructions, but reasoning types are linearly encoded in middle-to-late layers, allowing activation steering to raise instruction compliance by up to 29%.
-
When Model Editing Meets Service Evolution: A Knowledge-Update Perspective for Service Recommendation
EVOREC integrates locate-then-edit model editing with FA-constrained decoding to improve LLM-based service recommendation under evolution, reporting 25.9% average relative gain in Recall@5 over baselines and 22.3% over fine-tuning in dynamic scenarios.
-
Golden Layers and Where to Find Them: Improved Knowledge Editing for Large Language Models Via Layer Gradient Analysis
Fixed golden layers for knowledge editing in LLMs can be identified via gradient attribution and generalize across queries and datasets.
-
CrispEdit: Low-Curvature Projections for Scalable Non-Destructive LLM Editing
CrispEdit edits LLMs via low-curvature projections using Bregman divergence and K-FAC approximations, achieving high edit success with under 1% average capability degradation.
-
Retrieval-Augmented Generation for Natural Language Processing: A Survey
The survey organizes RAG methods via a taxonomy of query-based, logits-based, latent, and parametric fusion with comparisons on accessibility, efficiency, applications, and challenges.
-
HoReN: Normalized Hopfield Retrieval for Large-Scale Sequential Model Editing
HoReN is a parameter-preserving editor that wraps an MLP with a Hopfield codebook memory and scales to 50K sequential edits on ZsRE while maintaining performance above 0.93.
-
Towards Scalable Lifelong Knowledge Editing with Selective Knowledge Suppression
LightEdit enables scalable lifelong knowledge editing in LLMs via selective knowledge retrieval and probability suppression during decoding, outperforming prior methods on ZSRE, Counterfact, and RIPE while reducing training costs.
-
Mechanistic Circuit-Based Knowledge Editing in Large Language Models
MCircKE maps causal circuits for specific reasoning tasks in LLMs and surgically updates parameters within those circuits to enable effective multi-hop knowledge editing, as shown on the MQuAKE-3K benchmark.
-
MemOS: A Memory OS for AI System
MemOS introduces a unified memory management framework for LLMs using MemCubes to handle and evolve different memory types for improved controllability and evolvability.
-
Revisiting Ripple Effects in Knowledge Editing through Pressure-Aware Joint Neighborhood Optimization
JNO uses Pressure-Aware Coordination to jointly optimize neighborhood target representations under coupled constraints, improving propagation and preservation by at least 7% on RippleEdits while maintaining stability.
-
A Survey on the Memory Mechanism of Large Language Model based Agents
A systematic review of memory designs, evaluation methods, applications, limitations, and future directions for LLM-based agents.