TimpaTeks: Automatic In-place Text Sequence Modification via Diffusion Language Model Steering
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.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Real-Time Visual Place Recognition for Personal Localization on a Mobile Device
The paper presents an approach to indoor personal localization on a mobile device based on visual place recognition. We implemented on a smartphone two state-of-the-art algorithms that are representative to two different…
Visual Place RecognitionExploring Semi-Automatic Map Labeling
Label placement in maps is a very challenging task that is critical for the overall map quality. Most previous work focused on designing and implementing fully automatic solutions, but the resulting visual and aesthetic …
Leveraging Structure Knowledge and Deep Models for the Detection of Abnormal Handwritten Text
Currently, the destruction of the sequence structure in handwritten text has become one of the main bottlenecks restricting the recognition task. The typical situations include additional specific markers (the text swapp…
Joint Line Segmentation and Transcription for End-to-End Handwritten Paragraph Recognition
Offline handwriting recognition systems require cropped text line images for both training and recognition. On the one hand, the annotation of position and transcript at line level is costly to obtain. On the other hand,…
Handwriting RecognitionSegmentationJoint Line Segmentation and Transcription for End-to-End Handwritten Paragraph Recognition
Offline handwriting recognition systems require cropped text line images for both training and recognition. On the one hand, the annotation of position and transcript at line level is costly to obtain. On the other hand,…
Handwriting RecognitionSegmentation