From One to Many: Expanding the Scope of Toxicity Mitigation in Language Models (2024.findings-acl)
Copied to clipboard
| Challenge: | toxicity mitigation in language models has been focused on single-language settings . however, widespread adoption of LLMs has introduced a range of unknown -harms . |
| Approach: | They employ translated data to evaluate and enhance mitigation techniques in the absence of sufficient annotated datasets across languages. |
| Outcome: | The proposed approach compares translation quality and retrieval-augmented mitigation techniques under static and continual toxicity mitigation scenarios. |
Similar Papers
A Survey of Toxicity Mitigation Strategies for Multilingual Language Models (2026.findings-acl)
Copied to clipboard
| Challenge: | Large language models can reproduce and amplify toxic content, including hate speech, harassment, and bias. |
| Approach: | They propose a comprehensive survey of the many detoxification methods tailored to multilingual LLMs. |
| Outcome: | The proposed methods are based on data filtering, style transfer, expert-based logit steering, retrieval augmentation, and human feedback. |
Safety of Large Language Models Beyond English: A Systematic Literature Review of Risks, Biases, and Safeguards (2026.eacl-long)
Copied to clipboard
| Challenge: | Large language models (LLMs) have a growing number of applications that generate harmful, biased, or unsafe content. |
| Approach: | They synthesize findings from recent studies that evaluate their robustness across languages . they highlight gaps in multilingual safety research and recommend future work . |
| Outcome: | The systematic review examines the multilingual safety of large language models in English . it identifies challenges such as dataset availability and evaluation biases . |
Challenges in Detoxifying Language Models (2021.findings-emnlp)
Copied to clipboard
Johannes Welbl, Amelia Glaese, Jonathan Uesato, Sumanth Dathathri, John Mellor, Lisa Anne Hendricks, Kirsty Anderson, Pushmeet Kohli, Ben Coppin, Po-Sen Huang
| Challenge: | Prior work often relies on automatic evaluation of LM toxicity. |
| Approach: | They evaluate toxicity mitigation strategies for automated and human evaluations . they find human raters disagree with high automatic toxicity scores after strong toxicity reduction interventions . |
| Outcome: | The proposed methods reduce LM toxicity but lower coverage for marginalized texts . human raters disagree with high toxicity scores after strong toxicity reduction interventions . |
Cross-Lingual Transfer of Debiasing and Detoxification in Multilingual LLMs: An Extensive Investigation (2025.findings-acl)
Copied to clipboard
| Challenge: | Prior work has shown that finetuning on specialized datasets can mitigate this behavior, and doing so in English can transfer to other languages. |
| Approach: | They propose to fine tune generative large language models to provide safe responses to harmful user input and to use direct preference optimization to mitigate toxicity. |
| Outcome: | The proposed models show that finetuning on specialized datasets reduces biases but also produces fluent and diverse text in non-English languages. |
Mitigating Societal Harms in Large Language Models (2023.emnlp-tutorial)
Copied to clipboard
| Challenge: | Recent studies have highlighted societal harms that can be caused by language generation models deployed in the wild. |
| Approach: | They propose to use a typology of technical approaches to mitigating harms of language generation models to provide an overview of potential social issues in language generation including toxicity, social biases, misinformation, factual inconsistency, and privacy violations. |
| Outcome: | The proposed typology addresses toxicity, biases, misinformation, factual inconsistency, and privacy violations in language generation models. |
Language Generation Models Can Cause Harm: So What Can We Do About It? An Actionable Survey (2023.eacl-main)
Copied to clipboard
| Challenge: | Recent advances in the capacity of large language models to generate human-like text have prompted a heated discourse around the risks of societal harms they introduce. |
| Approach: | They propose a taxonomy of interventions organized around the different phases where they can be adopted to mitigate harms. |
| Outcome: | The proposed methods are based on several prior works’ taxonomies of language model risks and provide an overview of strategies for detecting and ameliorating different kinds of risks/harms. |
Toxicity in Multilingual Machine Translation at Scale (2023.findings-emnlp)
Copied to clipboard
Marta Costa-jussà, Eric Smith, Christophe Ropers, Daniel Licht, Jean Maillard, Javier Ferrando, Carlos Escolano
| Challenge: | In this paper, we evaluate and analyze added toxicity when translating a large dataset from English into 164 languages. |
| Approach: | They evaluate added toxicity when translating a large dataset from English into 164 languages. |
| Outcome: | The results show that added toxicity is more prevalent in low-resource languages than in high-resolution translations. |
Fairness in Language Models Beyond English: Gaps and Challenges (2023.findings-eacl)
Copied to clipboard
| Challenge: | Language models are inequitable at encoding and re-presentation, but there is much to be studied and criticism for the existing research that remains to be addressed. |
| Approach: | They propose to survey fairness in multilingual and non-English contexts . they argue that it is infeasible to achieve comprehensive coverage in terms of fairness datasets based on English . |
| Outcome: | The proposed methods are infeasible to scale across languages and cultures, the authors argue . they argue that the current methods are too narrowly focused on specific dimensions and types of biases and cannot scale across cultures. |
Goodtriever: Adaptive Toxicity Mitigation with Retrieval-augmented Models (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods for mitigating toxicity require drastic modifications to model parameters or the use of computationally intensive auxiliary models. |
| Approach: | They propose a method that matches current state-of-the-art toxicity mitigation while achieving 43% relative latency reduction during inference. |
| Outcome: | The proposed method achieves 43% latency reduction during inference and is more computationally efficient. |
Realistic Evaluation of Toxicity in Large Language Models (2024.findings-acl)
Copied to clipboard
| Challenge: | a large amount of data exposes large language models to toxicity and bias . prompt engineering can be easily bypassed with minimal prompt engineering. |
| Approach: | They propose a dataset that uses manually crafted prompts to nullify protective layers of large language models. |
| Outcome: | The proposed dataset shows that prompts can nullify protective layers of large language models. |