Improving Harmful Text Detection with Joint Retrieval and External Knowledge

• URL: http://arxiv.org/abs/2504.02310v1
• Date: Thu, 03 Apr 2025 06:37:55 GMT
• Title: Improving Harmful Text Detection with Joint Retrieval and External Knowledge
• Authors: Zidong Yu, Shuo Wang, Nan Jiang, Weiqiang Huang, Xu Han, Junliang Du,
• Abstract summary: This study proposes a joint retrieval framework that integrates pre-trained language models with knowledge graphs to improve the accuracy and robustness of harmful text detection.<n> Experimental results demonstrate that the joint retrieval approach significantly outperforms single-model baselines.
• Score: 16.68620974551506
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Harmful text detection has become a crucial task in the development and deployment of large language models, especially as AI-generated content continues to expand across digital platforms. This study proposes a joint retrieval framework that integrates pre-trained language models with knowledge graphs to improve the accuracy and robustness of harmful text detection. Experimental results demonstrate that the joint retrieval approach significantly outperforms single-model baselines, particularly in low-resource training scenarios and multilingual environments. The proposed method effectively captures nuanced harmful content by leveraging external contextual information, addressing the limitations of traditional detection models. Future research should focus on optimizing computational efficiency, enhancing model interpretability, and expanding multimodal detection capabilities to better tackle evolving harmful content patterns. This work contributes to the advancement of AI safety, ensuring more trustworthy and reliable content moderation systems.

Related papers

• Improving Multilingual Retrieval-Augmented Language Models through Dialectic Reasoning Argumentations [65.11348389219887]
  We introduce Dialectic-RAG (DRAG), a modular approach that evaluates retrieved information by comparing, contrasting, and resolving conflicting perspectives. We show the impact of our framework both as an in-context learning strategy and for constructing demonstrations to instruct smaller models.
  arXiv  Detail & Related papers  (2025-04-07T06:55:15Z)
• Enhancing AI-based Generation of Software Exploits with Contextual Information [9.327315119028809]
  The study employs a dataset comprising real shellcodes to evaluate the models across various scenarios. The experiments are designed to assess the models' resilience against incomplete descriptions, their proficiency in leveraging context for enhanced accuracy, and their ability to discern irrelevant information. The models demonstrate an ability to filter out unnecessary context, maintaining high levels of accuracy in the generation of offensive security code.
  arXiv  Detail & Related papers  (2024-08-05T11:52:34Z)
• A Simple Background Augmentation Method for Object Detection with Diffusion Model [53.32935683257045]
  In computer vision, it is well-known that a lack of data diversity will impair model performance. We propose a simple yet effective data augmentation approach by leveraging advancements in generative models. Background augmentation, in particular, significantly improves the models' robustness and generalization capabilities.
  arXiv  Detail & Related papers  (2024-08-01T07:40:00Z)
• Analyzing Persuasive Strategies in Meme Texts: A Fusion of Language Models with Paraphrase Enrichment [0.23020018305241333]
  This paper describes our approach to hierarchical multi-label detection of persuasion techniques in meme texts. The scope of the study encompasses enhancing model performance through innovative training techniques and data augmentation strategies.
  arXiv  Detail & Related papers  (2024-07-01T20:25:20Z)
• 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)
• ToBlend: Token-Level Blending With an Ensemble of LLMs to Attack AI-Generated Text Detection [6.27025292177391]
  ToBlend is a novel token-level ensemble text generation method to challenge the robustness of current AI-content detection approaches. We find ToBlend significantly drops the performance of most mainstream AI-content detection methods.
  arXiv  Detail & Related papers  (2024-02-17T02:25:57Z)
• RegaVAE: A Retrieval-Augmented Gaussian Mixture Variational Auto-Encoder for Language Modeling [79.56442336234221]
  We introduce RegaVAE, a retrieval-augmented language model built upon the variational auto-encoder (VAE) It encodes the text corpus into a latent space, capturing current and future information from both source and target text. Experimental results on various datasets demonstrate significant improvements in text generation quality and hallucination removal.
  arXiv  Detail & Related papers  (2023-10-16T16:42:01Z)
• Exploring Large Language Model for Graph Data Understanding in Online Job Recommendations [63.19448893196642]
  We present a novel framework that harnesses the rich contextual information and semantic representations provided by large language models to analyze behavior graphs. By leveraging this capability, our framework enables personalized and accurate job recommendations for individual users.
  arXiv  Detail & Related papers  (2023-07-10T11:29:41Z)
• LLMDet: A Third Party Large Language Models Generated Text Detection Tool [119.0952092533317]
  Large language models (LLMs) are remarkably close to high-quality human-authored text. Existing detection tools can only differentiate between machine-generated and human-authored text. We propose LLMDet, a model-specific, secure, efficient, and extendable detection tool.
  arXiv  Detail & Related papers  (2023-05-24T10:45:16Z)
• Contextual information integration for stance detection via cross-attention [59.662413798388485]
  Stance detection deals with identifying an author's stance towards a target. Most existing stance detection models are limited because they do not consider relevant contextual information. We propose an approach to integrate contextual information as text.
  arXiv  Detail & Related papers  (2022-11-03T15:04:29Z)
• Interpretable Fake News Detection with Topic and Deep Variational Models [2.15242029196761]
  We focus on fake news detection using interpretable features and methods. We have developed a deep probabilistic model that integrates a dense representation of textual news. Our model achieves comparable performance to state-of-the-art competing models.
  arXiv  Detail & Related papers  (2022-09-04T05:31:00Z)
• InfoBERT: Improving Robustness of Language Models from An Information Theoretic Perspective [84.78604733927887]
  Large-scale language models such as BERT have achieved state-of-the-art performance across a wide range of NLP tasks. Recent studies show that such BERT-based models are vulnerable facing the threats of textual adversarial attacks. We propose InfoBERT, a novel learning framework for robust fine-tuning of pre-trained language models.
  arXiv  Detail & Related papers  (2020-10-05T20:49:26Z)

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.