用可控生成文本提升仇恨言论识别与屏蔽效果
LLMs-Integrated Automatic Hate Speech Recognition Using Controllable Text Generation Models
- 融合ASR编码器与LLM解码器，实现语音转写与内容过滤同步
- 通过思维链提示生成带文化语境的仇恨文本，过滤后构建可控数据集
- 渐进式训练提升识别准确率至58.6%，适合内容安全场景应用
本文提出一种基于大语言模型（LLMs）的自动仇恨言论识别方法。将语音识别（ASR）模型的编码器与LLM的解码器结合，实现语音转写与内容屏蔽同步处理。为指导LLM进行仇恨词掩码，需标注数据集，但此类数据稀缺。因此，采用思维链（CoT）提示技术，结合文化背景与示例生成文本样本，并通过文本转语音（TTS）系统生成语音。部分样本虽含仇恨相关词但实际非仇恨言论，影响屏蔽效果。本文使用文本分类模型筛选出正确标注为仇恨的内容样本，并通过调整正确分类模型数量阈值，控制生成数据集中仇恨程度，实现分阶段课程学习训练。实验表明，该方法对仇恨相关词的掩码准确率达58.6%，优于先前基线。同时验证了课程学习在提升转写与屏蔽效率方面的有效性。
原文摘要 · Abstract (English)
This paper proposes an automatic speech recognition (ASR) model for hate speech using large language models (LLMs). The proposed method integrates the encoder of the ASR model with the decoder of the LLMs, enabling simultaneous transcription and censorship tasks to prevent the exposure of harmful content. Instruction tuning of the LLM to mask hate-related words with specific tokens requires an annotated hate speech dataset, which is limited. We generate text samples using an LLM with the Chain-of-Thought (CoT) prompting technique guided by cultural context and examples and then convert them into speech samples using a text-to-speech (TTS) system. However, some of them contain non-hate speech samples with hate-related words, which degrades the censorship performance. This paper filters the samples which text classification models correctly label as hate content. By adjusting the threshold for the number of correct answer models, we can control the level of hate in the generated dataset, allowing us to train the LLMs through curriculum learning in a gradual manner. Experimental results show that the proposed method achieves a masking accuracy of 58.6\% for hate-related words, surpassing previous baselines. We also confirm that the curriculum training contributes to the efficiency of both transcription and censorship tasks.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。