vix.ing · top · new · best · stats · spec

CTRLEval: An Unsupervised Reference-Free Metric for Evaluating Controlled Text Generation

2022/04/02 by Pei Ke, Hao Zhou, Ke, Pei +11 · 1 citation
Computer Science · #AI in Service Interactions #Artificial Intelligence (cs.AI) #Computation and Language (cs.CL) #FOS: Computer and information sciences #Natural Language Processing Techniques #Topic Modeling

paper · pdf · doi:10.48550/arxiv.2204.00862

openalex publication_date 2022/04/02 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Existing reference-free metrics have obvious limitations for evaluating controlled text generation models. Unsupervised metrics can only provide a task-agnostic evaluation result which correlates weakly with human judgments, whereas supervised ones may overfit task-specific data with poor generalization ability to other datasets. In this paper, we propose an unsupervised reference-free metric called CTRLEval, which evaluates controlled text generation from different aspects by formulating each aspect into multiple text infilling tasks. On top of these tasks, the metric assembles the generation probabilities from a pre-trained language model without any model training. Experimental results show that our metric has higher correlations with human judgments than other baselines, while obtaining better generalization of evaluating generated texts from different models and with different qualities.

Cited by

Related