Songlin Hu
- Papers
- 13
Cite
Notes
Only stored in your browser.
Authored papers
13NExtLong: Toward Effective Long-Context Training without Long Documents
arXiv 2025
Paper Summary Attack: Jailbreaking LLMs through LLM Safety Papers
arXiv 2025
AgentAlign: Navigating Safety Alignment in the Shift from Informative to Agentic Large Language Models
arXiv 2025
LightRetriever: A LLM-based Hybrid Retrieval Architecture with 1000x Faster Query Inference
arXiv 2025
Fine-Grained Behavior Simulation with Role-Playing Large Language Model on Social Media
arXiv 2024
Task-level Distributionally Robust Optimization for Large Language Model-based Dense Retrieval
arXiv 2024
CartesianMoE: Boosting Knowledge Sharing among Experts via Cartesian Product Routing in Mixture-of-Experts
arXiv 2024
MaskMoE: Boosting Token-Level Learning via Routing Mask in Mixture-of-Experts
arXiv 2024
Drop your Decoder: Pre-training with Bag-of-Word Prediction for Dense Passage Retrieval
arXiv 2024
HC3 Plus: A Semantic-Invariant Human ChatGPT Comparison Corpus
arXiv 2023
Supervised Prototypical Contrastive Learning for Emotion Recognition in Conversation
arXiv 2022
Query-as-context Pre-training for Dense Passage Retrieval
arXiv 2022
ESimCSE: Enhanced Sample Building Method for Contrastive Learning of Unsupervised Sentence Embedding
COLING 2022 10
Affiliations
Frequent co-authors
10from 13 papers