paper-with-me

Papers

AutoEval Done Right: Using Synthetic Data for Model Evaluation

2024-03-09 · Pierre Boyeau, Anastasios N. Angelopoulos, Nir Yosef, Jitendra Malik, Michael I. Jordan

The evaluation of machine learning models using human-labeled validation data can be expensive and time-consuming. AI-labeled synthetic data can be used to decrease the number of human annotations required for this purpose in a process called autoevaluation. We suggest efficient and statistically principled algorithms for this purpose that improve sample efficiency while remaining unbiased. These algorithms increase the effective human-labeled sample size by up to 50% on experiments with GPT-4.

📄 PDF Abstract BibTeX arXiv:2403.07008

Code (1)

pierreboyeau/autoeval 공식 구현 jax

Methods 이 논문이 사용한 방법론

Attention 설명 없음
Position-Wise Feed-Forward Layer 설명 없음
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…
Residual Connection 설명 없음
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…

Similar Papers 제목 키워드 기반

Adaptive Prediction-Powered AutoEval with Reliability and Efficiency Guarantees

2025-05-24 · Sangwoo Park, Matteo Zecchin, Osvaldo Simeone

Selecting artificial intelligence (AI) models, such as large language models (LLMs), from multiple candidates requires accurate performance estimation. This is ideally achieved through empirical evaluations involving abu…

Quantization

AutoEval: Autonomous Evaluation of Generalist Robot Manipulation Policies in the Real World

2025-03-31 · Zhiyuan Zhou, Pranav Atreya, You Liang Tan, Karl Pertsch 외

Scalable and reproducible policy evaluation has been a long-standing challenge in robot learning. Evaluations are critical to assess progress and build better policies, but evaluation in the real world, especially at a s…

Robot ManipulationScheduling

AutoEval-Video: An Automatic Benchmark for Assessing Large Vision Language Models in Open-Ended Video Question Answering

2023-11-25 · Xiuyuan Chen, Yuan Lin, Yuchen Zhang, Weiran Huang

We propose a novel and challenging benchmark, AutoEval-Video, to comprehensively evaluate large vision-language models in open-ended video question answering. The comprehensiveness of AutoEval-Video is demonstrated in tw…

Question AnsweringVideo Question Answering

CAME: Contrastive Automated Model Evaluation

2023-08-22 · ICCV 2023 1 · Ru Peng, Qiuyang Duan, Haobo Wang, Jiachen Ma 외

The Automated Model Evaluation (AutoEval) framework entertains the possibility of evaluating a trained machine learning model without resorting to a labeled testing set. Despite the promise and some decent results, the e…

model

Energy-based Automated Model Evaluation

2024-01-23 · Ru Peng, Heming Zou, Haobo Wang, Yawen Zeng 외

The conventional evaluation protocols on machine learning models rely heavily on a labeled, i.i.d-assumed testing dataset, which is not often present in real world applications. The Automated Model Evaluation (AutoEval) …

model