CaM-Gen:Causally-aware Metric-guided Text Generation

TL;DR

This paper introduces CaM-Gen, a causally-aware text generation framework that uses causal inference to guide models towards target metrics, improving control over generated content while maintaining quality.

Contribution

It presents a novel causal inference-based approach for metric-guided text generation, integrating feedback mechanisms into variational autoencoder and Transformer models.

Findings

Outperforms baselines in controlling target metrics

Maintains fluency and language quality

First to incorporate causal inference for metric-guided generation

Abstract

Content is created for a well-defined purpose, often described by a metric or signal represented in the form of structured information. The relationship between the goal (metrics) of target content and the content itself is non-trivial. While large-scale language models show promising text generation capabilities, guiding the generated text with external metrics is challenging. These metrics and content tend to have inherent relationships and not all of them may be of consequence. We introduce CaM-Gen: Causally aware Generative Networks guided by user-defined target metrics incorporating the causal relationships between the metric and content features. We leverage causal inference techniques to identify causally significant aspects of a text that lead to the target metric and then explicitly guide generative models towards these by a feedback mechanism. We propose this mechanism for variational autoencoder and Transformer-based generative models. The proposed models beat baselines in terms of the target metric control while maintaining fluency and language quality of the generated text. To the best of our knowledge, this is one of the early attempts at controlled generation incorporating a metric guide using causal inference.