发表机构
Johannes Kepler University Linz; Thomson Reuters Labs; University of Toronto; Vector Institute（约翰开普勒林茨大学; 汤森路透实验室; 多伦多大学; 向量研究所）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该研究提出基于编码器的框架SenseShift，通过双向注意力等技术实现细粒度句子级情感控制文本生成，在故事与评论生成任务上，相比大解码器基线模型，情感可控性更强且文本质量与鲁棒性更优。
AI 中文摘要
近期针对情感控制的可控文本生成（CTG）大多聚焦于基于解码器的大语言模型，使得因果注意力成为主导范式。这类模型虽能生成流畅文本，但仍难以满足复杂约束，以及遵循用户指定的细粒度情感信号。现有感知情感的CTG方法通常将问题简化，把情感视为粗粒度分类标签（如正面或负面），或应用于整个文档的单一细粒度控制信号。因此，长文本内的句子级情感控制等更具挑战性的场景仍未得到充分探索。为解决这些局限，我们提出SenseShift，一种用于细粒度句子级CTG的基于编码器的框架。与标准解码器架构不同，SenseShift利用双向注意力、量化情感信号和迭代掩码填充，生成以目标情感强度为条件的局部句子。在故事与评论生成任务上的实证评估表明，与更大规模的基于解码器的基线模型相比，SenseShift在保持文本质量和域外生成鲁棒性的同时，实现了更强的情感可控性。
英文摘要
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.
CommentsPaper Accepted to EMNLP 2026
