# DAPI: Domain Adaptive Toxicity Probe Vector Intervention for Fine-Grained Detoxification

arXiv: https://arxiv.org/abs/2503.12882 · HTML: https://mlsanity.com/paper/2503.12882/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 23 references that are in the map.
- First posted on arXiv 17 Mar 2025.

## Builds on (most cited first, 14 of 14)

- [Pointer Sentinel Mixture Models](https://mlsanity.com/paper/1609.07843/) (2016)
- [The Curious Case of Neural Text Degeneration](https://mlsanity.com/paper/1904.09751/) (2019)
- [Understanding intermediate layers using linear classifier probes](https://mlsanity.com/paper/1610.01644/) (2016)
- [Transformer Feed-Forward Layers Are Key-Value Memories](https://mlsanity.com/paper/2012.14913/) (2020)
- [Inference-Time Intervention: Eliciting Truthful Answers from a Language Model](https://mlsanity.com/paper/2306.03341/) (2023)
- [RealToxicityPrompts: Evaluating Neural Toxic Degeneration in Language Models](https://mlsanity.com/paper/2009.11462/) (2020)
- [A Diversity-Promoting Objective Function for Neural Conversation Models](https://mlsanity.com/paper/1510.03055/) (2015)
- [The Woman Worked as a Babysitter: On Biases in Language Generation](https://mlsanity.com/paper/1909.01326/) (2019)
- [Transformer Feed-Forward Layers Build Predictions by Promoting Concepts in the Vocabulary Space](https://mlsanity.com/paper/2203.14680/) (2022)
- [DExperts: Decoding-Time Controlled Text Generation with Experts and Anti-Experts](https://mlsanity.com/paper/2105.03023/) (2021)
- [A Mechanistic Understanding of Alignment Algorithms: A Case Study on DPO and Toxicity](https://mlsanity.com/paper/2401.01967/) (2024)
- [A Language Model's Guide Through Latent Space](https://mlsanity.com/paper/2402.14433/) (2024)
- [Multi-property Steering of Large Language Models with Dynamic Activation Composition](https://mlsanity.com/paper/2406.17563/) (2024)
- [Systematic Rectification of Language Models via Dead-end Analysis](https://mlsanity.com/paper/2302.14003/) (2023)

## Built on by (most cited first, 1 of 1)

- [Test-Time Detoxification without Training or Learning Anything](https://mlsanity.com/paper/2602.02498/) (2026)

## Abstract (arXiv)

There have been attempts to utilize linear probe for detoxification, with existing studies relying on a single toxicity probe vector to reduce toxicity. However, toxicity can be fine-grained into various subcategories, making it difficult to remove certain types of toxicity by using a single toxicity probe vector. To address this limitation, we propose a category-specific toxicity probe vector approach. First, we train multiple toxicity probe vectors for different toxicity categories. During generation, we dynamically select the most relevant toxicity probe vector based on the current context. Finally, the selected vector is dynamically scaled and subtracted from model. Our method successfully mitigated toxicity from categories that the single probe vector approach failed to detoxify. Experiments demonstrate that our approach achieves up to a 78.52% reduction in toxicity on the evaluation dataset, while fluency remains nearly unchanged, with only a 0.052% drop compared to the unsteered model.