Skip to content
conftrace_

Knowledge Editing

200 papers

1
1
4
1
4
14
13
67
71
24
'20
'25

Papers

Spectral Editing of Activations for Large Language Model Alignment NeurIPS 2024 Stealth edits to large language models NeurIPS 2024 Steering Llama 2 via Contrastive Activation Addition ACL 2024 Synthetic Knowledge Ingestion: Towards Knowledge Refinement and Injection for Enhancing Large Language Models EMNLP 2024 The Butterfly Effect of Model Editing: Few Edits Can Trigger Large Language Models Collapse ACL 2024 The Empirical Impact of Neural Parameter Symmetries, or Lack Thereof NeurIPS 2024 Time Sensitive Knowledge Editing through Efficient Finetuning ACL 2024 TruthX: Alleviating Hallucinations by Editing Large Language Models in Truthful Space ACL 2024 Understanding Information Storage and Transfer in Multi-Modal Large Language Models NeurIPS 2024 Updating Large Language Models’ Memories with Time Constraints EMNLP 2024 Why Does New Knowledge Create Messy Ripple Effects in LLMs? EMNLP 2024 WISE: Rethinking the Knowledge Memory for Lifelong Model Editing of Large Language Models NeurIPS 2024 Aging with GRACE: Lifelong Model Editing with Discrete Key-Value Adaptors NeurIPS 2023 Commonsense Knowledge Transfer for Pre-trained Language Models ACL 2023 Decouple knowledge from paramters for plug-and-play language modeling ACL 2023 Detecting Edit Failures In Large Language Models: An Improved Specificity Benchmark ACL 2023 DT-Solver: Automated Theorem Proving with Dynamic-Tree Sampling Guided by Proof-level Value Function ACL 2023 DUnE: Dataset for Unified Editing EMNLP 2023 Emptying the Ocean with a Spoon: Should We Edit Models? EMNLP 2023 Evaluating Dependencies in Fact Editing for Language Models: Specificity and Implication Awareness EMNLP 2023 Improving Sequential Model Editing with Fact Retrieval EMNLP 2023 Propagating Knowledge Updates to LMs Through Distillation NeurIPS 2023 Robust Concept Erasure via Kernelized Rate-Distortion Maximization NeurIPS 2023 Seeking Clozure: Robust Hypernym extraction from BERT with Anchored Prompts ACL 2023 Transformer-Patcher: One Mistake Worth One Neuron ICLR 2023