# New Terms, New Toxicity: Consensus-based Chinese Neologism Toxicity Detection via Search-Augmented LLMs

arXiv: https://arxiv.org/abs/2608.12361 · HTML: https://mlsanity.com/paper/2608.12361/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 17 of its 41 references that are in the map.
- First posted on arXiv 5 Jul 2026.

## Builds on (most cited first, 17 of 17)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [A Holistic Approach to Undesired Content Detection in the Real World](https://mlsanity.com/paper/2208.03274/) (2022)
- [FreshLLMs: Refreshing Large Language Models with Search Engine Augmentation](https://mlsanity.com/paper/2310.03214/) (2023)
- [Learning from the Worst: Dynamically Generated Datasets to Improve Online Hate Detection](https://mlsanity.com/paper/2012.15761/) (2020)
- [A New Generation of Perspective API: Efficient Multilingual Character-level Transformers](https://mlsanity.com/paper/2202.11176/) (2022)
- [COLD: A Benchmark for Chinese Offensive Language Detection](https://mlsanity.com/paper/2201.06025/) (2022)
- [Handling Bias in Toxic Speech Detection: A Survey](https://mlsanity.com/paper/2202.00126/) (2022)
- [Facilitating Fine-grained Detection of Chinese Toxic Language: Hierarchical Taxonomy, Resources, and Benchmarks](https://mlsanity.com/paper/2305.04446/) (2023)
- [ToxiCloakCN: Evaluating Robustness of Offensive Language Detection in Chinese with Cloaking Perturbations](https://mlsanity.com/paper/2406.12223/) (2024)
- [NEO-BENCH: Evaluating Robustness of Large Language Models with Neologisms](https://mlsanity.com/paper/2402.12261/) (2024)
- [NYTWIT: A Dataset of Novel Words in the New York Times](https://mlsanity.com/paper/2003.03444/) (2020)
- [Exploring Multimodal Challenges in Toxic Chinese Detection: Taxonomy, Benchmark, and Findings](https://mlsanity.com/paper/2505.24341/) (2025)
- [The structure of online social networks modulates the rate of lexical change](https://mlsanity.com/paper/2104.05010/) (2021)
- [Speculating LLMs' Chinese Training Data Pollution from Their Tokens](https://mlsanity.com/paper/2508.17771/) (2025)
- [Evaluating the retrieval effectiveness of Web search engines using a representative query sample](https://mlsanity.com/paper/1405.2210/) (2014)
- [ToxiFrench: Benchmarking and Enhancing Language Models via CoT Fine-Tuning for French Toxicity Detection](https://mlsanity.com/paper/2508.11281/) (2025)
- [Fine-Grained Chinese Hate Speech Understanding: Span-Level Resources, Coded Term Lexicon, and Enhanced Detection Frameworks](https://mlsanity.com/paper/2507.11292/) (2025)

## Abstract (arXiv)

Neologisms, emerging terms in meaning or form, can serve as new vehicles for toxic expression, like "country girl" as a stigmatizing label targeting feminism. Such toxic neologisms appear benign but have evolved into toxic usage in public consensus, posing challenges to moderation systems and remaining underexplored. In this paper, we investigate how to detect implicit toxicity expressed via neologisms. We first propose a taxonomy that captures the origins and consensus-verification criteria of toxic neologisms, followed by the construction of a lexicon spanning widely observed risk categories. To capture toxicity grounded in public consensus, we introduce SeTox, a search-augmented framework that enables static large language models (LLMs) to incorporate real-time web context for neologism toxicity detection. Experiments show that SeTox, even with 3B-scale models, outperforms recent large-scale models, demonstrating its scalability to incorporate real-world knowledge for toxic neologism detection. Disclaimer: this paper has offensive contents that may be disturbing to some readers.