Picture for Shumin Deng

Shumin Deng

ZJUKLAB at SemEval-2025 Task 4: Unlearning via Model Merging

Add code
Mar 27, 2025
Viaarxiv icon

CaKE: Circuit-aware Editing Enables Generalizable Knowledge Learners

Add code
Mar 20, 2025
Viaarxiv icon

Exploring Model Kinship for Merging Large Language Models

Add code
Oct 16, 2024
Figure 1 for Exploring Model Kinship for Merging Large Language Models
Figure 2 for Exploring Model Kinship for Merging Large Language Models
Figure 3 for Exploring Model Kinship for Merging Large Language Models
Figure 4 for Exploring Model Kinship for Merging Large Language Models
Viaarxiv icon

MLLM can see? Dynamic Correction Decoding for Hallucination Mitigation

Add code
Oct 15, 2024
Figure 1 for MLLM can see? Dynamic Correction Decoding for Hallucination Mitigation
Figure 2 for MLLM can see? Dynamic Correction Decoding for Hallucination Mitigation
Figure 3 for MLLM can see? Dynamic Correction Decoding for Hallucination Mitigation
Figure 4 for MLLM can see? Dynamic Correction Decoding for Hallucination Mitigation
Viaarxiv icon

FlipAttack: Jailbreak LLMs via Flipping

Add code
Oct 02, 2024
Figure 1 for FlipAttack: Jailbreak LLMs via Flipping
Figure 2 for FlipAttack: Jailbreak LLMs via Flipping
Figure 3 for FlipAttack: Jailbreak LLMs via Flipping
Figure 4 for FlipAttack: Jailbreak LLMs via Flipping
Viaarxiv icon

OneEdit: A Neural-Symbolic Collaboratively Knowledge Editing System

Add code
Sep 09, 2024
Figure 1 for OneEdit: A Neural-Symbolic Collaboratively Knowledge Editing System
Figure 2 for OneEdit: A Neural-Symbolic Collaboratively Knowledge Editing System
Figure 3 for OneEdit: A Neural-Symbolic Collaboratively Knowledge Editing System
Figure 4 for OneEdit: A Neural-Symbolic Collaboratively Knowledge Editing System
Viaarxiv icon

Knowledge Mechanisms in Large Language Models: A Survey and Perspective

Add code
Jul 22, 2024
Figure 1 for Knowledge Mechanisms in Large Language Models: A Survey and Perspective
Figure 2 for Knowledge Mechanisms in Large Language Models: A Survey and Perspective
Figure 3 for Knowledge Mechanisms in Large Language Models: A Survey and Perspective
Figure 4 for Knowledge Mechanisms in Large Language Models: A Survey and Perspective
Viaarxiv icon

Knowledge Circuits in Pretrained Transformers

Add code
May 28, 2024
Figure 1 for Knowledge Circuits in Pretrained Transformers
Figure 2 for Knowledge Circuits in Pretrained Transformers
Figure 3 for Knowledge Circuits in Pretrained Transformers
Figure 4 for Knowledge Circuits in Pretrained Transformers
Viaarxiv icon

Decompose and Aggregate: A Step-by-Step Interpretable Evaluation Framework

Add code
May 24, 2024
Figure 1 for Decompose and Aggregate: A Step-by-Step Interpretable Evaluation Framework
Figure 2 for Decompose and Aggregate: A Step-by-Step Interpretable Evaluation Framework
Figure 3 for Decompose and Aggregate: A Step-by-Step Interpretable Evaluation Framework
Figure 4 for Decompose and Aggregate: A Step-by-Step Interpretable Evaluation Framework
Viaarxiv icon

Agent Planning with World Knowledge Model

Add code
May 23, 2024
Viaarxiv icon