Mengnan Du
- Papers
- 11
Cite
Notes
Only stored in your browser.
Authored papers
11Massive Values in Self-Attention Modules are the Key to Contextual Knowledge Understanding
arXiv 2025
When AI Meets Finance (StockAgent): Large Language Model-based Stock Trading in Simulated Real-world Environments
arXiv 2024
From Commands to Prompts: LLM-based Semantic File System for AIOS
arXiv 2024
The Impact of Reasoning Step Length on Large Language Models
arXiv 2024
What if LLMs Have Different World Views: Simulating Alien Civilizations with LLM-based Agents
arXiv 2024
Exploring Concept Depth: How Large Language Models Acquire Knowledge at Different Layers?
arXiv 2024
Usable XAI: 10 Strategies Towards Exploiting Explainability in the LLM Era
arXiv 2024
Explaining Time Series via Contrastive and Locally Sparse Perturbations
arXiv 2024
Language Ranker: A Metric for Quantifying LLM Performance Across High and Low-Resource Languages
arXiv 2024
Mitigating Gender Bias in Captioning Systems
arXiv 2020
Score-CAM: Score-Weighted Visual Explanations for Convolutional Neural Networks
arXiv 2019
Affiliations
Frequent co-authors
10from 11 papers