conftrace_

prediction robustness

3 papers

Explore in graph

Co-occurring keywords · papers mentioning both

attention stability (1) token-level modeling (1) concept reasoning (1) concept-aware llm (1) conceptual reasoning (1) large language model (1) model stability (1) stochastic neural network (1) faithful explanation (1) gradient variance (1)

Papers

SEAT: Stable and Explainable Attention AAAI 2023 Towards Concept-Aware Large Language Models EMNLP 2023 How Sampling Impacts the Robustness of Stochastic Neural Networks NeurIPS 2022