Mengdi Li
8 papers · 2021–2025 · 7 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+2 more ↓ Show less ↑
π Interdisciplinary Bridge π Conference Polyglot (7) π Renaissance Researcher (7) π Cross-Pollinator (12) πΊοΈ Taxonomy Completionist (22)
π§
Keyword Pioneer
β
The Questioner
Conferences
ACL (2)
AAAI (1)
CLEAR (1)
COLING (1)
EMNLP (1)
ICCV (1)
ICML (1)
Top co-authors
Keywords
large language model
(4)
distant supervision
(2)
commonsense knowledge
(2)
adversarial robustness
(1)
feature extraction
(1)
multi-instance learning
(1)
chain-of-thought reasoning
(1)
text generation
(1)
policy learning
(1)
scene graph generation
(1)
mental health detection
(1)
evaluation framework
(1)
reward function
(1)
fraud detection
(1)
vision-language model
(1)
training stability
(1)
mechanistic interpretability
(1)
sparse autoencoder
(1)
activation manipulation
(1)
knowledge acquisition
(1)
Papers
Can Large Language Models Identify Implicit Suicidal Ideation? An Empirical Evaluation
EMNLP 2025
Fraud-R1 : A Multi-Round Benchmark for Assessing the Robustness of LLM Against Augmented Fraud and Phishing Inducements
ACL 2025
Understanding the Repeat Curse in Large Language Models from a Feature Perspective
ACL 2025
Causal State Distillation for Explainable Reinforcement Learning
CLEAR 2024
Enhancing Zero-Shot Chain-of-Thought Reasoning in Large Language Models through Logic
COLING 2024
Internally Rewarded Reinforcement Learning
ICML 2023
Visually Grounded Commonsense Knowledge Acquisition
AAAI 2023
Visual Distant Supervision for Scene Graph Generation
ICCV 2021