SENSESHIFT: Continuous Sentiment-Controlled Text Generation via Encoder-based Mask Infilling

2026-08-25

AI Summary

本文提出SenseShift框架，通过编码器和迭代掩码填充方法解决长文本中句子级情感控制问题，实现细粒度情感控制的同时保持文本质量。

Abstract

Recent controllable text generation (CTG) for sentiment control has largely focused on decoder-based large language models, making causal attention the dominant paradigm. While effective for fluent generation, these models still struggle to satisfy complex constraints and follow fine-grained sentiment signals specified by users. Existing sentiment-aware CTG methods typically simplify the problem by treating sentiment either as a coarse categorical label (e.g., positive or negative) or as a single fine-grained control signal applied to an entire document. Consequently, more challenging settings such as sentence-level sentiment control within long-form text remain underexplored. To address these limitations, we introduce SenseShift , an encoder-based framework for fine-grained sentence-level CTG. Unlike standard decoder architectures, SenseShift leverages bidirectional attention, quantized sentiment signals, and iterative mask infilling to generate local sentences conditioned on target sentiment intensity. Empirical evaluations on story and review generation demonstrate that SenseShift achieves stronger sentiment controllability while maintaining text quality and robustness to out-of-domain generation compared to larger decoder-based baselines.

Problem

• controllable text generation
• sentiment control
• decoder-based models
• fine-grained sentiment signals
• sentence-level control

Innovation

• encoder-based framework
• fine-grained sentence-level CTG
• bidirectional attention
• quantized sentiment signals
• iterative mask infilling