Learning to Rewrite: Generalized LLM-Generated Text Detection

• URL: http://arxiv.org/abs/2408.04237v1
• Date: Thu, 8 Aug 2024 05:53:39 GMT
• Title: Learning to Rewrite: Generalized LLM-Generated Text Detection
• Authors: Wei Hao, Ran Li, Weiliang Zhao, Junfeng Yang, Chengzhi Mao,
• Abstract summary: Large language models (LLMs) can be abused at scale to create non-factual content and spread disinformation. We propose training an LLM to rewrite input text, producing minimal edits for LLM-generated content and more edits for human-written text. Our work suggests that LLM can effectively detect machine-generated text if they are trained properly.
• Score: 19.9477991969521
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Large language models (LLMs) can be abused at scale to create non-factual content and spread disinformation. Detecting LLM-generated content is essential to mitigate these risks, but current classifiers often fail to generalize in open-world contexts. Prior work shows that LLMs tend to rewrite LLM-generated content less frequently, which can be used for detection and naturally generalizes to unforeseen data. However, we find that the rewriting edit distance between human and LLM content can be indistinguishable across domains, leading to detection failures. We propose training an LLM to rewrite input text, producing minimal edits for LLM-generated content and more edits for human-written text, deriving a distinguishable and generalizable edit distance difference across different domains. Experiments on text from 21 independent domains and three popular LLMs (e.g., GPT-4o, Gemini, and Llama-3) show that our classifier outperforms the state-of-the-art zero-shot classifier by up to 20.6% on AUROC score and the rewriting classifier by 9.2% on F1 score. Our work suggests that LLM can effectively detect machine-generated text if they are trained properly.

Related papers

• Which LLMs are Difficult to Detect? A Detailed Analysis of Potential Factors Contributing to Difficulties in LLM Text Detection [43.66875548677324]
  We train AI-generated (AIG) text classifiers using the LibAUC library for training classifiers with imbalanced datasets. Our results in the Deepfake Text dataset show that AIG-text detection varies across domains, with scientific writing being relatively challenging. In the Rewritten Ivy Panda dataset focusing on student essays, we find that the OpenAI family of LLMs was substantially difficult for our classifiers to distinguish from human texts.
  arXiv  Detail & Related papers  (2024-10-18T21:42:37Z)
• Can AI writing be salvaged? Mitigating Idiosyncrasies and Improving Human-AI Alignment in the Writing Process through Edits [39.00434175773803]
  We hired professional writers to edit paragraphs in several creative domains. We curated the LAMP corpus: 1,057 LLM-generated paragraphs edited by professional writers according to our taxonomy. Analysis of LAMP reveals that none of the LLMs used in our study outperform each other in terms of writing quality.
  arXiv  Detail & Related papers  (2024-09-22T16:13:00Z)
• Robustness of LLMs to Perturbations in Text [2.0670689746336]
  Large language models (LLMs) have shown impressive performance, but can they handle the inevitable noise in real-world data? This work tackles this critical question by investigating LLMs' resilience against morphological variations in text. Our findings show that contrary to popular beliefs, generative LLMs are quiet robust to noisy perturbations in text.
  arXiv  Detail & Related papers  (2024-07-12T04:50:17Z)
• WikiContradict: A Benchmark for Evaluating LLMs on Real-World Knowledge Conflicts from Wikipedia [59.96425443250666]
  Retrieval-augmented generation (RAG) has emerged as a promising solution to mitigate the limitations of large language models (LLMs) In this work, we conduct a comprehensive evaluation of LLM-generated answers to questions based on contradictory passages from Wikipedia. We benchmark a diverse range of both closed and open-source LLMs under different QA scenarios, including RAG with a single passage, and RAG with 2 contradictory passages.
  arXiv  Detail & Related papers  (2024-06-19T20:13:42Z)
• ReMoDetect: Reward Models Recognize Aligned LLM's Generations [55.06804460642062]
  Large language models (LLMs) generate human-preferable texts. In this paper, we identify the common characteristics shared by these models. We propose two training schemes to further improve the detection ability of the reward model.
  arXiv  Detail & Related papers  (2024-05-27T17:38:33Z)
• TM-TREK at SemEval-2024 Task 8: Towards LLM-Based Automatic Boundary Detection for Human-Machine Mixed Text [0.0]
  This paper explores the ability of large language models to identify boundaries in human-written and machine-generated mixed texts. Our ensemble model of LLMs achieved first place in the 'Human-Machine Mixed Text Detection' sub-task of the SemEval'24 Competition Task 8.
  arXiv  Detail & Related papers  (2024-04-01T03:54:42Z)
• Unsupervised Information Refinement Training of Large Language Models for Retrieval-Augmented Generation [128.01050030936028]
  We propose an information refinement training method named InFO-RAG. InFO-RAG is low-cost and general across various tasks. It improves the performance of LLaMA2 by an average of 9.39% relative points.
  arXiv  Detail & Related papers  (2024-02-28T08:24:38Z)
• See the Unseen: Better Context-Consistent Knowledge-Editing by Noises [73.54237379082795]
  Knowledge-editing updates knowledge of large language models (LLMs) Existing works ignore this property and the editing lacks generalization. We empirically find that the effects of different contexts upon LLMs in recalling the same knowledge follow a Gaussian-like distribution.
  arXiv  Detail & Related papers  (2024-01-15T09:09:14Z)
• LLMRefine: Pinpointing and Refining Large Language Models via Fine-Grained Actionable Feedback [65.84061725174269]
  Recent large language models (LLM) are leveraging human feedback to improve their generation quality. We propose LLMRefine, an inference time optimization method to refine LLM's output. We conduct experiments on three text generation tasks, including machine translation, long-form question answering (QA), and topical summarization. LLMRefine consistently outperforms all baseline approaches, achieving improvements up to 1.7 MetricX points on translation tasks, 8.1 ROUGE-L on ASQA, 2.2 ROUGE-L on topical summarization.
  arXiv  Detail & Related papers  (2023-11-15T19:52:11Z)
• LLatrieval: LLM-Verified Retrieval for Verifiable Generation [67.93134176912477]
  Verifiable generation aims to let the large language model (LLM) generate text with supporting documents. We propose LLatrieval (Large Language Model Verified Retrieval), where the LLM updates the retrieval result until it verifies that the retrieved documents can sufficiently support answering the question. Experiments show that LLatrieval significantly outperforms extensive baselines and achieves state-of-the-art results.
  arXiv  Detail & Related papers  (2023-11-14T01:38:02Z)
• Detecting LLM-Generated Text in Computing Education: A Comparative Study for ChatGPT Cases [0.0]
  Large Language Models (LLMs) have posed a serious threat to academic integrity in education. Modern detectors are still in need of improvements so that they can offer a full-proof solution to help maintain academic integrity.
  arXiv  Detail & Related papers  (2023-07-10T12:18:34Z)

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.