paper-with-me

홈 › Papers

MAUVE: Measuring the Gap Between Neural Text and Human Text using Divergence Frontiers

2021-02-02 · NeurIPS 2021 12 · Krishna Pillutla, Swabha Swayamdipta, Rowan Zellers, John Thickstun, Sean Welleck, Yejin Choi, Zaid Harchaoui

As major progress is made in open-ended text generation, measuring how close machine-generated text is to human language remains a critical open problem. We introduce MAUVE, a comparison measure for open-ended text generation, which directly compares the learnt distribution from a text generation model to the distribution of human-written text using divergence frontiers. MAUVE scales up to modern text generation models by computing information divergences in a quantized embedding space. Through an extensive empirical study on three open-ended generation tasks, we find that MAUVE identifies known properties of generated text, scales naturally with model size, and correlates with human judgments, with fewer restrictions than existing distributional evaluation metrics.

📄 PDF Abstract BibTeX arXiv:2102.01454

Code (5)

krishnap25/mauve 공식 구현 pytorch
krishnap25/mauve-experiments 공식 구현 pytorch
jdeschena/sdtt pytorch
martiansideofthemoon/rankgen jax
ylXuu/ALiiCE pytorch

Tasks

Text Generation

Similar Papers 제목 키워드 기반

MAUVE Scores for Generative Models: Theory and Practice

2022-12-30 · Krishna Pillutla, Lang Liu, John Thickstun, Sean Welleck 외

Generative artificial intelligence has made significant strides, producing text indistinguishable from human prose and remarkably photorealistic images. Automatically measuring how close the generated data distribution i…

Quantization

On the Usefulness of Embeddings, Clusters and Strings for Text Generator Evaluation

2022-05-31 · Tiago Pimentel, Clara Meister, Ryan Cotterell

A good automatic evaluation metric for language generation ideally correlates highly with human judgements of text quality. Yet, there is a dearth of such metrics, which inhibits the rapid and efficient progress of langu…

Language ModellingText Generation

An Empirical Study On Contrastive Search And Contrastive Decoding For Open-ended Text Generation

2022-11-19 · Yixuan Su, Jialu Xu

In the study, we empirically compare the two recently proposed decoding methods, i.e. Contrastive Search (CS) and Contrastive Decoding (CD), for open-ended text generation. The automatic evaluation results suggest that, …

DiversityText Generation

From Aesthetics to Human Preferences: Comparative Perspectives of Evaluating Text-to-Music Systems

2025-04-30 · huan zhang, Jinhua Liang, Huy Phan, Wenwu Wang 외

Evaluating generative models remains a fundamental challenge, particularly when the goal is to reflect human preferences. In this paper, we use music generation as a case study to investigate the gap between automatic ev…

Music Generation

Adversarial Robustness of Neural-Statistical Features in Detection of Generative Transformers

2022-03-02 · Evan Crothers, Nathalie Japkowicz, Herna Viktor, Paula Branco

The detection of computer-generated text is an area of rapidly increasing significance as nascent generative models allow for efficient creation of compelling human-like text, which may be abused for the purposes of spam…

Adversarial RobustnessAdversarial Text