Picture for Songlin Hu

Songlin Hu

Enhancing Multi-Hop Fact Verification with Structured Knowledge-Augmented Large Language Models

Add code
Mar 11, 2025
Viaarxiv icon

An Information-theoretic Multi-task Representation Learning Framework for Natural Language Understanding

Add code
Mar 06, 2025
Viaarxiv icon

DSMoE: Matrix-Partitioned Experts with Dynamic Routing for Computation-Efficient Dense LLMs

Add code
Feb 18, 2025
Viaarxiv icon

Fine-Grained Behavior Simulation with Role-Playing Large Language Model on Social Media

Add code
Dec 04, 2024
Figure 1 for Fine-Grained Behavior Simulation with Role-Playing Large Language Model on Social Media
Figure 2 for Fine-Grained Behavior Simulation with Role-Playing Large Language Model on Social Media
Figure 3 for Fine-Grained Behavior Simulation with Role-Playing Large Language Model on Social Media
Figure 4 for Fine-Grained Behavior Simulation with Role-Playing Large Language Model on Social Media
Viaarxiv icon

The Dark Side of Trust: Authority Citation-Driven Jailbreak Attacks on Large Language Models

Add code
Nov 18, 2024
Viaarxiv icon

CartesianMoE: Boosting Knowledge Sharing among Experts via Cartesian Product Routing in Mixture-of-Experts

Add code
Oct 21, 2024
Viaarxiv icon

CodePMP: Scalable Preference Model Pretraining for Large Language Model Reasoning

Add code
Oct 03, 2024
Viaarxiv icon

Holistic Automated Red Teaming for Large Language Models through Top-Down Test Case Generation and Multi-turn Interaction

Add code
Sep 25, 2024
Viaarxiv icon

AdaPPA: Adaptive Position Pre-Fill Jailbreak Attack Approach Targeting LLMs

Add code
Sep 11, 2024
Viaarxiv icon

Task-level Distributionally Robust Optimization for Large Language Model-based Dense Retrieval

Add code
Aug 20, 2024
Viaarxiv icon