Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models
Paper • 2206.04615 • Published • 6
Chandan Singh
csinva
AI & ML interests
Interpretability
Recent Activity
new activity 43 minutes ago
guidelabs/fineweb-atlas:What do the concept labels represent? liked a dataset about 2 hours ago
guidelabs/fineweb-atlas liked a Space 10 months ago
yzhuang/MixtureOfInputsOrganizations
authored 4
papers about 2 years ago
Emb-GAM: an Interpretable and Efficient Predictor using Pre-trained Language Models
Paper • 2209.11799 • Published
Interpretations are useful: penalizing explanations to align neural networks with prior knowledge
Paper • 1909.13584 • Published
Rethinking Interpretability in the Era of Large Language Models
Paper • 2402.01761 • Published • 23
authored 4
papers over 2 years ago
Tell Your Model Where to Attend: Post-hoc Attention Steering for LLMs
Paper • 2311.02262 • Published • 14
Tree Prompting: Efficient Task Adaptation without Fine-Tuning
Paper • 2310.14034 • Published • 3
Explaining black box text modules in natural language with language models
Paper • 2305.09863 • Published • 3
NL-Augmenter: A Framework for Task-Sensitive Natural Language Augmentation
Paper • 2112.02721 • Published