Real or Fake Text?: Investigating Human Ability to Detect Boundaries Between Human-Written and Machine-Generated Text

• URL: http://arxiv.org/abs/2212.12672v1
• Date: Sat, 24 Dec 2022 06:40:25 GMT
• Title: Real or Fake Text?: Investigating Human Ability to Detect Boundaries Between Human-Written and Machine-Generated Text
• Authors: Liam Dugan, Daphne Ippolito, Arun Kirubarajan, Sherry Shi, Chris Callison-Burch
• Abstract summary: We study a more realistic setting where text begins as human-written and transitions to being generated by state-of-the-art neural language models. We show that, while annotators often struggle at this task, there is substantial variance in annotator skill and that given proper incentives, annotators can improve at this task over time.
• Score: 23.622347443796183
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: As text generated by large language models proliferates, it becomes vital to understand how humans engage with such text, and whether or not they are able to detect when the text they are reading did not originate with a human writer. Prior work on human detection of generated text focuses on the case where an entire passage is either human-written or machine-generated. In this paper, we study a more realistic setting where text begins as human-written and transitions to being generated by state-of-the-art neural language models. We show that, while annotators often struggle at this task, there is substantial variance in annotator skill and that given proper incentives, annotators can improve at this task over time. Furthermore, we conduct a detailed comparison study and analyze how a variety of variables (model size, decoding strategy, fine-tuning, prompt genre, etc.) affect human detection performance. Finally, we collect error annotations from our participants and use them to show that certain textual genres influence models to make different types of errors and that certain sentence-level features correlate highly with annotator selection. We release the RoFT dataset: a collection of over 21,000 human annotations paired with error classifications to encourage future work in human detection and evaluation of generated text.

Related papers

• Detecting Machine-Generated Long-Form Content with Latent-Space Variables [54.07946647012579]
  Existing zero-shot detectors primarily focus on token-level distributions, which are vulnerable to real-world domain shifts. We propose a more robust method that incorporates abstract elements, such as event transitions, as key deciding factors to detect machine versus human texts.
  arXiv  Detail & Related papers  (2024-10-04T18:42:09Z)
• Detecting Subtle Differences between Human and Model Languages Using Spectrum of Relative Likelihood [5.404146472517001]
  This study provides a new perspective by using the relative likelihood values instead of absolute ones. We propose a detection procedure with two classification methods, supervised and supervised-based, respectively. Our method can also reveal subtle differences between human and model languages, which find theoretical roots in psycholinguistics studies.
  arXiv  Detail & Related papers  (2024-06-28T12:28:52Z)
• Who Writes the Review, Human or AI? [0.36498648388765503]
  This study proposes a methodology to accurately distinguish AI-generated and human-written book reviews. Our approach utilizes transfer learning, enabling the model to identify generated text across different topics. The experimental results demonstrate that it is feasible to detect the original source of text, achieving an accuracy rate of 96.86%.
  arXiv  Detail & Related papers  (2024-05-30T17:38:44Z)
• Few-Shot Detection of Machine-Generated Text using Style Representations [4.326503887981912]
  Language models that convincingly mimic human writing pose a significant risk of abuse. We propose to leverage representations of writing style estimated from human-authored text. We find that features effective at distinguishing among human authors are also effective at distinguishing human from machine authors.
  arXiv  Detail & Related papers  (2024-01-12T17:26:51Z)
• Humans and language models diverge when predicting repeating text [52.03471802608112]
  We present a scenario in which the performance of humans and LMs diverges. Human and GPT-2 LM predictions are strongly aligned in the first presentation of a text span, but their performance quickly diverges when memory begins to play a role. We hope that this scenario will spur future work in bringing LMs closer to human behavior.
  arXiv  Detail & Related papers  (2023-10-10T08:24:28Z)
• The Imitation Game: Detecting Human and AI-Generated Texts in the Era of ChatGPT and BARD [3.2228025627337864]
  We introduce a novel dataset of human-written and AI-generated texts in different genres. We employ several machine learning models to classify the texts. Results demonstrate the efficacy of these models in discerning between human and AI-generated text.
  arXiv  Detail & Related papers  (2023-07-22T21:00:14Z)
• MISMATCH: Fine-grained Evaluation of Machine-generated Text with Mismatch Error Types [68.76742370525234]
  We propose a new evaluation scheme to model human judgments in 7 NLP tasks, based on the fine-grained mismatches between a pair of texts. Inspired by the recent efforts in several NLP tasks for fine-grained evaluation, we introduce a set of 13 mismatch error types. We show that the mismatch errors between the sentence pairs on the held-out datasets from 7 NLP tasks align well with the human evaluation.
  arXiv  Detail & Related papers  (2023-06-18T01:38:53Z)
• MAGE: Machine-generated Text Detection in the Wild [82.70561073277801]
  Large language models (LLMs) have achieved human-level text generation, emphasizing the need for effective AI-generated text detection. We build a comprehensive testbed by gathering texts from diverse human writings and texts generated by different LLMs. Despite challenges, the top-performing detector can identify 86.54% out-of-domain texts generated by a new LLM, indicating the feasibility for application scenarios.
  arXiv  Detail & Related papers  (2023-05-22T17:13:29Z)
• On the Possibilities of AI-Generated Text Detection [76.55825911221434]
  We argue that as machine-generated text approximates human-like quality, the sample size needed for detection bounds increases. We test various state-of-the-art text generators, including GPT-2, GPT-3.5-Turbo, Llama, Llama-2-13B-Chat-HF, and Llama-2-70B-Chat-HF, against detectors, including oBERTa-Large/Base-Detector, GPTZero.
  arXiv  Detail & Related papers  (2023-04-10T17:47:39Z)
• Neural Deepfake Detection with Factual Structure of Text [78.30080218908849]
  We propose a graph-based model for deepfake detection of text. Our approach represents the factual structure of a given document as an entity graph. Our model can distinguish the difference in the factual structure between machine-generated text and human-written text.
  arXiv  Detail & Related papers  (2020-10-15T02:35:31Z)
• RoFT: A Tool for Evaluating Human Detection of Machine-Generated Text [25.80571756447762]
  We present Real or Fake Text (RoFT), a website that invites users to try their hand at detecting machine-generated text. We show preliminary results of using RoFT to evaluate detection of machine-generated news articles.
  arXiv  Detail & Related papers  (2020-10-06T22:47:43Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.