paper-with-me

홈 › Papers

Frankentext: Stitching random text fragments into long-form narratives

2025-05-23 · Chau Minh Pham, Jenna Russell, Dzung Pham, Mohit Iyyer

We introduce Frankentexts, a new type of long-form narratives produced by LLMs under the extreme constraint that most tokens (e.g., 90%) must be copied verbatim from human writings. This task presents a challenging test of controllable generation, requiring models to satisfy a writing prompt, integrate disparate text fragments, and still produce a coherent narrative. To generate Frankentexts, we instruct the model to produce a draft by selecting and combining human-written passages, then iteratively revise the draft while maintaining a user-specified copy ratio. We evaluate the resulting Frankentexts along three axes: writing quality, instruction adherence, and detectability. Gemini-2.5-Pro performs surprisingly well on this task: 81% of its Frankentexts are coherent and 100% relevant to the prompt. Notably, up to 59% of these outputs are misclassified as human-written by detectors like Pangram, revealing limitations in AI text detectors. Human annotators can sometimes identify Frankentexts through their abrupt tone shifts and inconsistent grammar between segments, especially in longer generations. Beyond presenting a challenging generation task, Frankentexts invite discussion on building effective detectors for this new grey zone of authorship, provide training data for mixed authorship detection, and serve as a sandbox for studying human-AI co-writing processes.

📄 PDF Abstract BibTeX arXiv:2505.18128

Code (1)

chtmp223/frankentext 공식 구현

Tasks

Form

Similar Papers 제목 키워드 기반

Semantic Mosaicing of Histo-Pathology Image Fragments using Visual Foundation Models

2025-08-05 · Stefan Brandstätter, Maximilian Köller, Philipp Seeböck, Alissa Blessing 외 arxiv

In histopathology, tissue samples are often larger than a standard microscope slide, making stitching of multiple fragments necessary to process entire structures such as tumors. Automated stitching is a prerequisite for…

Pose Estimation

Context-Former: Stitching via Latent Conditioned Sequence Modeling

2024-01-29 · Ziqi Zhang, Jingzehua Xu, Jinxin Liu, Zifeng Zhuang 외

Offline reinforcement learning (RL) algorithms can learn better decision-making compared to behavior policies by stitching the suboptimal trajectories to derive more optimal ones. Meanwhile, Decision Transformer (DT) abs…

D4RLDecision MakingImitation LearningOffline RL+1

VLMs Can Aggregate Scattered Training Patches

2025-06-04 · Zhanhui Zhou, Lingjie Chen, Chao Yang, Chaochao Lu

One way to mitigate risks in vision-language models (VLMs) is to remove dangerous samples in their training data. However, such data moderation can be easily bypassed when harmful images are split into small, benign-look…

Data Poisoning

Is Temporal Difference Learning the Gold Standard for Stitching in RL?

2025-10-24 · Michał Bortkiewicz, Władysław Pałucki, Mateusz Ostaszewski, Benjamin Eysenbach arxiv

Reinforcement learning (RL) promises to solve long-horizon tasks even when training data contains only short fragments of the behaviors. This experience stitching capability is often viewed as the purview of temporal dif…

Reinforcement Learning

Local-peak scale-invariant feature transform for fast and random image stitching

2024-05-14 · Hao Li, Lipo Wang, Tianyun Zhao, Wei Zhao

Image stitching aims to construct a wide field of view with high spatial resolution, which cannot be achieved in a single exposure. Typically, conventional image stitching techniques, other than deep learning, require co…

Image Stitching