Bayesian concept bottleneck models with llm priors

[Free GPT-4]
[PDF] arxiv.org

Interpretable Language Modeling via Induction-head Ngram Models

E Kim, S Mantena, W Yang, C Singh, S Yoon… - arxiv preprint arxiv …, 2024 - arxiv.org
Recent large language models (LLMs) have excelled across a wide range of tasks, but their
use in high-stakes and compute-limited settings has intensified the demand for …
Save Cite Related articles All 3 versionsFree GPT-4 View as HTML