# Mimicking How Humans Interpret Out-of-Context Sentences Through Controlled Toxicity Decoding

arXiv: https://arxiv.org/abs/2503.08159 · HTML: https://mlsanity.com/paper/2503.08159/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 25 references that are in the map.
- First posted on arXiv 11 Mar 2025.

## Builds on (most cited first, 21 of 21)

- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension](https://mlsanity.com/paper/1910.13461/) (2019)
- [The Curious Case of Neural Text Degeneration](https://mlsanity.com/paper/1904.09751/) (2019)
- [RealToxicityPrompts: Evaluating Neural Toxic Degeneration in Language Models](https://mlsanity.com/paper/2009.11462/) (2020)
- [COMET: A Neural Framework for MT Evaluation](https://mlsanity.com/paper/2009.09025/) (2020)
- [Diffusion-LM Improves Controllable Text Generation](https://mlsanity.com/paper/2205.14217/) (2022)
- [Plug and Play Language Models: A Simple Approach to Controlled Text Generation](https://mlsanity.com/paper/1912.02164/) (2019)
- [DExperts: Decoding-Time Controlled Text Generation with Experts and Anti-Experts](https://mlsanity.com/paper/2105.03023/) (2021)
- [ToxiGen: A Large-Scale Machine-Generated Dataset for Adversarial and Implicit Hate Speech Detection](https://mlsanity.com/paper/2203.09509/) (2022)
- [HateXplain: A Benchmark Dataset for Explainable Hate Speech Detection](https://mlsanity.com/paper/2012.10289/) (2020)
- [FUDGE: Controlled Text Generation With Future Discriminators](https://mlsanity.com/paper/2104.05218/) (2021)
- [Toward Controlled Generation of Text](https://mlsanity.com/paper/1703.00955/) (2017)
- [Latent Hatred: A Benchmark for Understanding Implicit Hate Speech](https://mlsanity.com/paper/2109.05322/) (2021)
- [Queens are Powerful too: Mitigating Gender Bias in Dialogue Generation](https://mlsanity.com/paper/1911.03842/) (2019)
- [Prompt Compression and Contrastive Conditioning for Controllability and Toxicity Reduction in Language Models](https://mlsanity.com/paper/2210.03162/) (2022)
- [A Plug-and-Play Method for Controlled Text Generation](https://mlsanity.com/paper/2109.09707/) (2021)
- [Like hiking? You probably enjoy nature: Persona-grounded Dialog with Commonsense Expansions](https://mlsanity.com/paper/2010.03205/) (2020)
- [Critic-Guided Decoding for Controlled Text Generation](https://mlsanity.com/paper/2212.10938/) (2022)
- [Adding Instructions during Pretraining: Effective Way of Controlling Toxicity in Language Models](https://mlsanity.com/paper/2302.07388/) (2023)
- [Interpretation modeling: Social grounding of sentences by reasoning over their implicit moral judgments](https://mlsanity.com/paper/2312.03726/) (2023)

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

- [How Ethos and Pathos Appeals Resonate in Reader Interpretations of Social Media Messages](https://mlsanity.com/paper/2607.00873/) (2026)

## Abstract (arXiv)

Interpretations of a single sentence can vary, particularly when its context is lost. This paper aims to simulate how readers perceive content with varying toxicity levels by generating diverse interpretations of out-of-context sentences. By modeling toxicity, we can anticipate misunderstandings and reveal hidden toxic meanings. Our proposed decoding strategy explicitly controls toxicity in the set of generated interpretations by (i) aligning interpretation toxicity with the input, (ii) relaxing toxicity constraints for more toxic input sentences, and (iii) promoting diversity in toxicity levels within the set of generated interpretations. Experimental results show that our method improves alignment with human-written interpretations in both syntax and semantics while reducing model prediction uncertainty.