用编码器+掩码填充实现细粒度句级情感控制生成
SENSESHIFT: Continuous Sentiment-Controlled Text Generation via Encoder-based Mask Infilling
- 采用双向注意力与量化情感信号，通过迭代掩码填充生成目标情感句子
- 在故事和评论生成中实现更强情感可控性，优于更大解码器模型
- 适合需要精准情感调节的长文本生成任务
当前可控文本生成（CTG）主要基于解码器架构的大语言模型，依赖因果注意力，虽能生成流畅文本，但在满足复杂约束和精细情感指令方面仍存在不足。现有方法通常将情感简化为粗粒度类别（如正/负）或单一全局控制信号，导致句级情感控制等更复杂场景研究不足。为此，我们提出 SenseShift，一种基于编码器的细粒度句级可控生成框架。不同于标准解码器结构，SenseShift 利用双向注意力、量化情感信号和迭代掩码填充，生成受目标情感强度调控的局部句子。在故事和评论生成任务上的实证评估表明，SenseShift 在保持文本质量与域外生成鲁棒性的前提下，实现了比更大规模解码器基线更强的情感可控性。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。