Facilitating NSFW Text Detection in Open-Domain Dialogue Systems via Knowledge Distillation

• URL: http://arxiv.org/abs/2309.09749v3
• Date: Thu, 21 Mar 2024 01:57:38 GMT
• Title: Facilitating NSFW Text Detection in Open-Domain Dialogue Systems via Knowledge Distillation
• Authors: Huachuan Qiu, Shuai Zhang, Hongliang He, Anqi Li, Zhenzhong Lan,
• Abstract summary: CensorChat is a dialogue monitoring dataset aimed at NSFW dialogue detection. This dataset offers a cost-effective means of constructing NSFW content detectors. The proposed approach not only advances NSFW content detection but also aligns with evolving user protection needs in AI-driven dialogues.
• Score: 26.443929802292807
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: NSFW (Not Safe for Work) content, in the context of a dialogue, can have severe side effects on users in open-domain dialogue systems. However, research on detecting NSFW language, especially sexually explicit content, within a dialogue context has significantly lagged behind. To address this issue, we introduce CensorChat, a dialogue monitoring dataset aimed at NSFW dialogue detection. Leveraging knowledge distillation techniques involving GPT-4 and ChatGPT, this dataset offers a cost-effective means of constructing NSFW content detectors. The process entails collecting real-life human-machine interaction data and breaking it down into single utterances and single-turn dialogues, with the chatbot delivering the final utterance. ChatGPT is employed to annotate unlabeled data, serving as a training set. Rationale validation and test sets are constructed using ChatGPT and GPT-4 as annotators, with a self-criticism strategy for resolving discrepancies in labeling. A BERT model is fine-tuned as a text classifier on pseudo-labeled data, and its performance is assessed. The study emphasizes the importance of AI systems prioritizing user safety and well-being in digital conversations while respecting freedom of expression. The proposed approach not only advances NSFW content detection but also aligns with evolving user protection needs in AI-driven dialogues.

Related papers

• Context Does Matter: Implications for Crowdsourced Evaluation Labels in Task-Oriented Dialogue Systems [57.16442740983528]
  Crowdsourced labels play a crucial role in evaluating task-oriented dialogue systems. Previous studies suggest using only a portion of the dialogue context in the annotation process. This study investigates the influence of dialogue context on annotation quality.
  arXiv  Detail & Related papers  (2024-04-15T17:56:39Z)
• Facilitating Pornographic Text Detection for Open-Domain Dialogue Systems via Knowledge Distillation of Large Language Models [26.443929802292807]
  Pornographic content occurring in human-machine interaction dialogues can cause severe side effects for users in open-domain dialogue systems. We introduce CensorChat, a dialogue monitoring dataset aimed at detecting whether the dialogue session contains pornographic content.
  arXiv  Detail & Related papers  (2024-03-20T02:29:09Z)
• Acknowledgment of Emotional States: Generating Validating Responses for Empathetic Dialogue [21.621844911228315]
  This study introduces the first framework designed to engender empathetic dialogue with validating responses. Our approach incorporates a tripartite module system: 1) validation timing detection, 2) users' emotional state identification, and 3) validating response generation.
  arXiv  Detail & Related papers  (2024-02-20T07:20:03Z)
• A Benchmark for Understanding Dialogue Safety in Mental Health Support [15.22008156903607]
  This paper aims to develop a theoretically and factually grounded taxonomy that prioritizes the positive impact on help-seekers. We analyze the dataset using popular language models, including BERT-base, RoBERTa-large, and ChatGPT. The developed dataset and findings serve as valuable benchmarks for advancing research on dialogue safety in mental health support.
  arXiv  Detail & Related papers  (2023-07-31T07:33:16Z)
• SuperDialseg: A Large-scale Dataset for Supervised Dialogue Segmentation [55.82577086422923]
  We provide a feasible definition of dialogue segmentation points with the help of document-grounded dialogues. We release a large-scale supervised dataset called SuperDialseg, containing 9,478 dialogues. We also provide a benchmark including 18 models across five categories for the dialogue segmentation task.
  arXiv  Detail & Related papers  (2023-05-15T06:08:01Z)
• SPACE-2: Tree-Structured Semi-Supervised Contrastive Pre-training for Task-Oriented Dialog Understanding [68.94808536012371]
  We propose a tree-structured pre-trained conversation model, which learns dialog representations from limited labeled dialogs and large-scale unlabeled dialog corpora. Our method can achieve new state-of-the-art results on the DialoGLUE benchmark consisting of seven datasets and four popular dialog understanding tasks.
  arXiv  Detail & Related papers  (2022-09-14T13:42:50Z)
• KETOD: Knowledge-Enriched Task-Oriented Dialogue [77.59814785157877]
  Existing studies in dialogue system research mostly treat task-oriented dialogue and chit-chat as separate domains. We investigate how task-oriented dialogue and knowledge-grounded chit-chat can be effectively integrated into a single model.
  arXiv  Detail & Related papers  (2022-05-11T16:01:03Z)
• Graph Based Network with Contextualized Representations of Turns in Dialogue [0.0]
  Dialogue-based relation extraction (RE) aims to extract relation(s) between two arguments that appear in a dialogue. We propose the TUrn COntext awaRE Graph Convolutional Network (TUCORE-GCN) modeled by paying attention to the way people understand dialogues.
  arXiv  Detail & Related papers  (2021-09-09T03:09:08Z)
• Persuasive Dialogue Understanding: the Baselines and Negative Results [27.162062321321805]
  We demonstrate the limitations of a Transformer-based approach coupled with Conditional Random Field (CRF) for the task of persuasive strategy recognition. We leverage inter- and intra-speaker contextual semantic features, as well as label dependencies to improve the recognition.
  arXiv  Detail & Related papers  (2020-11-19T16:52:43Z)
• Exploiting Unsupervised Data for Emotion Recognition in Conversations [76.01690906995286]
  Emotion Recognition in Conversations (ERC) aims to predict the emotional state of speakers in conversations. The available supervised data for the ERC task is limited. We propose a novel approach to leverage unsupervised conversation data.
  arXiv  Detail & Related papers  (2020-10-02T13:28:47Z)
• TOD-BERT: Pre-trained Natural Language Understanding for Task-Oriented Dialogue [113.45485470103762]
  In this work, we unify nine human-human and multi-turn task-oriented dialogue datasets for language modeling. To better model dialogue behavior during pre-training, we incorporate user and system tokens into the masked language modeling.
  arXiv  Detail & Related papers  (2020-04-15T04:09:05Z)

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.