# GTA: Gated Toxicity Avoidance for LM Performance Preservation

arXiv: https://arxiv.org/abs/2312.06122 · HTML: https://mlsanity.com/paper/2312.06122/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 23 references that are in the map.
- First posted on arXiv 11 Dec 2023.

## Builds on (most cited first, 18 of 18)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter](https://mlsanity.com/paper/1910.01108/) (2019)
- [The Power of Scale for Parameter-Efficient Prompt Tuning](https://mlsanity.com/paper/2104.08691/) (2021)
- [The Curious Case of Neural Text Degeneration](https://mlsanity.com/paper/1904.09751/) (2019)
- [Character-level Convolutional Networks for Text Classification](https://mlsanity.com/paper/1509.01626/) (2015)
- [Neural Network Acceptability Judgments](https://mlsanity.com/paper/1805.12471/) (2018)
- [Plug and Play Language Models: A Simple Approach to Controlled Text Generation](https://mlsanity.com/paper/1912.02164/) (2019)
- [CTRL: A Conditional Transformer Language Model for Controllable Generation](https://mlsanity.com/paper/1909.05858/) (2019)
- [DExperts: Decoding-Time Controlled Text Generation with Experts and Anti-Experts](https://mlsanity.com/paper/2105.03023/) (2021)
- [GeDi: Generative Discriminator Guided Sequence Generation](https://mlsanity.com/paper/2009.06367/) (2020)
- [FUDGE: Controlled Text Generation With Future Discriminators](https://mlsanity.com/paper/2104.05218/) (2021)
- [Reformulating Unsupervised Style Transfer as Paraphrase Generation](https://mlsanity.com/paper/2010.05700/) (2020)
- [Challenges in Detoxifying Language Models](https://mlsanity.com/paper/2109.07445/) (2021)
- [Detoxifying Language Models Risks Marginalizing Minority Voices](https://mlsanity.com/paper/2104.06390/) (2021)
- [DisCup: Discriminator Cooperative Unlikelihood Prompt-tuning for Controllable Text Generation](https://mlsanity.com/paper/2210.09551/) (2022)

## Built on by (most cited first, 3 of 3)

- [Guardians and Offenders: A Survey on Harmful Content Generation and Safety Mitigation of LLM](https://mlsanity.com/paper/2508.05775/) (2025)
- [Correct after Answer: Enhancing Multi-Span Question Answering with Post-Processing Method](https://mlsanity.com/paper/2410.16788/) (2024)
- [Measuring and Mitigating Toxicity in Large Language Models: A Comprehensive Replication Study](https://mlsanity.com/paper/2605.14087/) (2026)

## Abstract (arXiv)

Caution: This paper includes offensive words that could potentially cause unpleasantness. The fast-paced evolution of generative language models such as GPT-4 has demonstrated outstanding results in various NLP generation tasks. However, due to the potential generation of offensive words related to race or gender, various Controllable Text Generation (CTG) methods have been proposed to mitigate the occurrence of harmful words. However, existing CTG methods not only reduce toxicity but also negatively impact several aspects of the language model's generation performance, including topic consistency, grammar, and perplexity. This paper explores the limitations of previous methods and introduces a novel solution in the form of a simple Gated Toxicity Avoidance (GTA) that can be applied to any CTG method. We also evaluate the effectiveness of the proposed GTA by comparing it with state-of-the-art CTG methods across various datasets. Our findings reveal that gated toxicity avoidance efficiently achieves comparable levels of toxicity reduction to the original CTG methods while preserving the generation performance of the language model.