Challenge: Large Language Models are known to be brittle and biased against marginalised communities and dialects.
Approach: They investigate the robustness of hate speech classification using LLMs when explicit and implicit markers of the speaker’s ethnicity are injected into the input.
Outcome: The proposed model is robust when explicit and implicit markers of speaker's ethnicity are injected into the input.

Similar Papers

Probing LLMs for hate speech detection: strengths and vulnerabilities (2023.findings-emnlp)

Copied to clipboard

Challenge: Recent efforts to detect hateful or toxic language using large language models have not used explanation, additional context and victim community information in the detection process.
Approach: They use different prompt variations, input information and victim community information to evaluate large language models in zero shot setting without adding any in-context examples.
Outcome: The proposed models perform significantly better when included in the pipeline than baseline models.
Hate Personified: Investigating the role of LLMs in content moderation (2024.emnlp-main)

Copied to clipboard

Challenge: Our work provides preliminary guidelines and highlights the nuances of applying Large Language models in culturally sensitive cases.
Approach: They propose to use large language models to help with content moderation to assess how well the needs of diverse groups are reflected in annotated posts.
Outcome: The proposed model is able to leverage community-based flagging efforts and exposure to adversaries.
Don’t Go To Extremes: Revealing the Excessive Sensitivity and Calibration Limitations of LLMs in Implicit Hate Speech Detection (2024.acl-long)

Copied to clipboard

Challenge: Several studies have examined whether large language models exhibit bias or discrimination against individuals or groups in terms of protected attributes like race, gender, or religion.
Approach: They evaluate LLMs' ability to detect implicit hate speech and express confidence in their responses by considering prompt patterns and mainstream uncertainty estimation methods.
Outcome: The proposed models exhibit two extremes: (1) excessive sensitivity towards groups or topics that may cause fairness issues, resulting in misclassifying benign statements as hate speech; (2) confidence scores for each method excessively concentrate on a fixed range, remaining unchanged regardless of the dataset’s complexity.
The Risk of Racial Bias in Hate Speech Detection (P19-1)

Copied to clipboard

Challenge: Annotators’ insensitivity to differences in dialect can lead to racial bias in automatic hate speech detection models, potentially amplifying harm against minority populations.
Approach: They propose *dialect* and *race priming* as ways to reduce the racial bias in hate speech detection models by detecting differences in dialects in annotated tweets.
Outcome: The proposed models acquire and propagate these biases, such that AAE tweets and tweets by self-identified African Americans are up to two times more likely to be labelled as offensive compared to others.
Model-Dependent Moderation: Inconsistencies in Hate Speech Detection Across LLM-based Systems (2025.findings-acl)

Copied to clipboard

Challenge: Content moderation systems powered by large language models are increasingly deployed to detect hate speech . if two systems produce different outcomes for the same content, it undermines consistency and predictability .
Approach: They analyze 1.3+ million sentences from a factorial design to determine hate speech classification . they find identical content receives markedly different classification values across systems .
Outcome: The proposed model finds that identical content receives markedly different classification values across systems.
Whose Emotions and Moral Sentiments do Language Models Reflect? (2024.findings-acl)

Copied to clipboard

Challenge: Existing research has focused on positional alignment, which measures how closely the models mimic the opinions and stances of different social groups.
Approach: They define the problem of affective alignment, which measures how LMs’ emotional and moral tone represents those of different groups.
Outcome: The results show that the models represent the perspectives of some social groups better than others, suggesting a systemic bias within LMs.
Confident, Calibrated, or Complicit: Safety Alignment and Ideological Bias in LLM Hate Speech Detection (2026.acl-long)

Copied to clipboard

Challenge: censored models outperform uncensoreed counterparts in accuracy and robustness, achieving 69.0% accuracy versus 64.1% strict accuracy.
Approach: They examine how large language models with minimal safety alignment compare with more heavily aligned counterparts when deployed using political personas.
Outcome: The proposed model outperforms uncensored models in accuracy and robustness, while uncensors are more malleable to ideological framing.
Decoding Hate: Exploring Language Models’ Reactions to Hate Speech (2025.naacl-long)

Copied to clipboard

Challenge: Large Language Models (LLMs) are trained on vast amounts of unmoderated internet data, enabling them to generate text autonomously.
Approach: They investigate the responses of seven state-of-the-art Large Language Models (LLMs) to hate speech by qualitative analysis.
Outcome: The proposed models can handle hate speech inputs and mitigate it through fine-tuning and guideline guardrailing.
Investigating Bias in LLM-Based Bias Detection: Disparities between LLMs and Human Perception (2025.coling-main)

Copied to clipboard

Challenge: Detecting media bias is critical due to the spread of misinformation and disinformation on social media platforms.
Approach: They investigate the presence and nature of bias within large language models and its consequential impact on media bias detection.
Outcome: The proposed debiasing strategies include prompt engineering and model fine-tuning.
LLM generated responses to mitigate the impact of hate speech (2024.findings-emnlp)

Copied to clipboard

Challenge: a study aims to determine the effectiveness of large language models to counteract hate speech . it is the first real-life A/B test evaluating the effectiveness .
Approach: They conduct the first real-life A/B test assessing the effectiveness of LLM-generated counter-speech.
Outcome: The proposed system reduces user engagement by over 20%, the study shows . the proposed metric is based on a simple metric and is scalable to other platforms .

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations