Deep Learning
Automating Dataset Updates Towards Reliable and Timely Evaluation of Large Language Models
There are two updating strategies: 1) mimicking strategy to generate similar samples based on original data, preserving stylistic and contextual essence, and 2) extending strategy that further expands existing samples at varying cognitive levels by adapting Bloom's taxonomy of educational objectives.
NaturalBench: Evaluating Vision-Language Models on Natural Adversarial Samples
However, are these models truly effective?
A Scalable Module for Solving Top-k Problems
The cost of ranking becomes significant in the new stage of deep learning.
Loki: Low-rank Keys for Efficient Sparse Attention
In particular, the self-attention mechanism used in LLM inference contributes significantly to these costs, which has sparked an interest in approximating the self-attention computation to reduce such costs.
Implicit Regularization of Decentralized Gradient Descent for Decentralized Sparse Regression
We consider learning a sparse model from linear measurements taken by a network of agents.
On the Noise Robustness of In-Context Learning for Text Generation
Large language models (LLMs) have shown impressive performance on downstream tasks by in-context learning (ICL), which heavily relies on the quality of demonstrations selected from a large set of annotated examples.