用扩散模型实现文本原位修改，无需指令微调
TimpaTeks: Automatic In-place Text Sequence Modification via Diffusion Language Model Steering
- 通过激活控制在扩散语言模型中直接修改文本内容
- 在IMDB和猫狗数据集上成功实现概念迁移，降低困惑度
- 计算成本低于提示工程，保持原句结构
我们将激活控制扩展到扩散语言模型（DLMs），研究因DLM推理机制引发的新问题：在不改变原文结构的前提下，对文本进行原位概念修改。提出TimpaTeks，一种基于DLM的自动原位文本修改方法。在IMDB影评（情感）和合成猫狗数据集（任意、非传统概念控制）上的实验表明，TimpaTeks能有效实现原位输出调控，同时降低句子困惑度并保留原始句式，且无需指令微调模型。相比提示驱动的DLM控制，该方法通过原位去噪而非构建额外提示序列，计算开销更低。
原文摘要 · Abstract (English)
We extend activation steering to diffusion language models (DLMs) and study a novel problem that arose due to the inference mechanism of DLMs: Modifying a text in-place to manifest a different concept. We propose TimpaTeks, an automatic in-place text modification mechanism using DLMs. Experiments on IMDB movie reviews (sentiment) and a synthetic Cats and Dogs Dataset (arbitrary, more unconventional concept steering) show that TimpaTeks provides a feasible novel mechanism to steer diffusion language model outputs in-place. TimpaTeks enables in-place modification while simultaneously lowers sentence perplexity and retaining the original sentence structre without the need of instruction tuned models. TimpaTeks is also computationally cheaper than prompt-based DLM steering, as it performs denoising in-place rather than constructing an additional prompt-conditioned output sequence.
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。