James Wexler
4 papers · 2018–2024 · 4 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+1 more ↓ Show less ↑
🌍 Conference Polyglot (4) 🏃 Academic Marathon (6) 🌉 Interdisciplinary Bridge 🧭 Keyword Pioneer 🐣 Hot Topic Early Bird
🐝
Cross-Pollinator
(15)
Conferences
ACL (1)
EMNLP (1)
ICML (1)
NIPS (1)
Top co-authors
Keywords
image classification
(1)
concept-based explanation
(1)
feature importance
(1)
neural network interpretability
(1)
model interpretability
(1)
visual concept
(1)
local explanation
(1)
parameter-efficient fine-tuning
(1)
mixture of expert
(1)
prompt optimization
(1)
counterfactual generation
(1)
nlp model
(1)
neural network
(1)
concept activation vector
(1)
testing with cav
(1)
semantic routing
(1)
constitutional principle
(1)
principle-based prompt
(1)
aggregate analysis
(1)
Papers
ConstitutionalExperts: Training a Mixture of Principle-based Prompts
ACL 2024
The Language Interpretability Tool: Extensible, Interactive Visualizations and Analysis for NLP Models
EMNLP 2020
Towards Automatic Concept-based Explanations
NIPS 2019
Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)
ICML 2018