# Mod-Guide: An LLM-based Content Moderation Feedback System to Address Insensitive Speech toward Indigenous Ethnic and Religious Minority Communities

arXiv: https://arxiv.org/abs/2606.13397 · HTML: https://mlsanity.com/paper/2606.13397/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 29 of its 109 references that are in the map.
- First posted on arXiv 11 Jun 2026.

## Builds on (most cited first, 29 of 29)

- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generation](https://mlsanity.com/paper/2305.14251/) (2023)
- [Leveraging Passage Retrieval with Generative Models for Open Domain Question Answering](https://mlsanity.com/paper/2007.01282/) (2020)
- [REPLUG: Retrieval-Augmented Black-Box Language Models](https://mlsanity.com/paper/2301.12652/) (2023)
- [Benchmarking Large Language Models in Retrieval-Augmented Generation](https://mlsanity.com/paper/2309.01431/) (2023)
- [Metrics for Explainable AI: Challenges and Prospects](https://mlsanity.com/paper/1812.04608/) (2018)
- [Auditing large language models: a three-layered approach](https://mlsanity.com/paper/2302.08500/) (2023)
- [Expanding Explainability: Towards Social Transparency in AI systems](https://mlsanity.com/paper/2101.04719/) (2021)
- [Human-centered Explainable AI: Towards a Reflective Sociotechnical Approach](https://mlsanity.com/paper/2002.01092/) (2020)
- [Hate Speech Detection and Racial Bias Mitigation in Social Media based on BERT model](https://mlsanity.com/paper/2008.06460/) (2020)
- [Evaluating Cultural Adaptability of a Large Language Model via Simulation of Synthetic Personas](https://mlsanity.com/paper/2408.06929/) (2024)
- [ChatGPT Perpetuates Gender Bias in Machine Translation and Ignores Non-Gendered Pronouns: Findings across Bengali and Five other Low-Resource Languages](https://mlsanity.com/paper/2305.10510/) (2023)
- ['Person' == Light-skinned, Western Man, and Sexualization of Women of Color: Stereotypes in Stable Diffusion](https://mlsanity.com/paper/2310.19981/) (2023)
- [Identifying Implicit Social Biases in Vision-Language Models](https://mlsanity.com/paper/2411.00997/) (2024)
- [Do Generative AI Models Output Harm while Representing Non-Western Cultures: Evidence from A Community-Centered Approach](https://mlsanity.com/paper/2407.14779/) (2024)
- [A Framework of Severity for Harmful Content Online](https://mlsanity.com/paper/2108.04401/) (2021)
- [Problematic Machine Behavior: A Systematic Literature Review of Algorithm Audits](https://mlsanity.com/paper/2102.04256/) (2021)
- [The "Colonial Impulse" of Natural Language Processing: An Audit of Bengali Sentiment Analysis Tools and Their Identity-based Biases](https://mlsanity.com/paper/2401.10535/) (2024)
- [A Trade-off-centered Framework of Content Moderation](https://mlsanity.com/paper/2206.03450/) (2022)
- [Your Large Language Model is Secretly a Fairness Proponent and You Should Prompt it Like One](https://mlsanity.com/paper/2402.12150/) (2024)
- [Interpretations, Representations, and Stereotypes of Caste within Text-to-Image Generators](https://mlsanity.com/paper/2408.01590/) (2024)
- [Designing Word Filter Tools for Creator-led Comment Moderation](https://mlsanity.com/paper/2202.08818/) (2022)
- [Data-Efficient Autoregressive Document Retrieval for Fact Verification](https://mlsanity.com/paper/2211.09388/) (2022)
- [Socio-Culturally Aware Evaluation Framework for LLM-Based Content Moderation](https://mlsanity.com/paper/2412.13578/) (2024)
- [Addressing interpersonal harm in online gaming communities: the opportunities and challenges for a restorative justice approach](https://mlsanity.com/paper/2211.01524/) (2022)
- [Watching the Watchers: A Comparative Fairness Audit of Cloud-based Content Moderation Services](https://mlsanity.com/paper/2406.14154/) (2024)
- [The Politics of Fear and the Experience of Bangladeshi Religious Minority Communities Using Social Media Platforms](https://mlsanity.com/paper/2410.15207/) (2024)
- [A Civics-oriented Approach to Understanding Intersectionally Marginalized Users' Experience with Hate Speech Online](https://mlsanity.com/paper/2410.14950/) (2024)
- [Characterizing Network Structure of Anti-Trans Actors on TikTok](https://mlsanity.com/paper/2501.16507/) (2025)

## Abstract (arXiv)

Language operates as a mechanism of both marginalization and resistance, especially for minority communities navigating insensitive and harmful speech online. As content moderation increasingly depends on large language models (LLMs), concerns arise about whether these systems can recognize culturally insensitive speech-language that disregards or marginalizes the cultural and religious perspectives of historically underrepresented communities, often through implicit erasure, misrepresentation, or normative framing, rather than overt hostility. Focusing on Bangladesh's Hindu and Chakma communities -- the country's largest religious and Indigenous ethnic minorities, respectively -- this paper investigates the epistemic limits of LLM-based moderation systems and explores methods for incorporating minority perspectives. We co-created a culturally grounded corpus of insensitive speech with community members and integrated their narratives into moderation pipelines using retrieval augmented generation (RAG). Our tool, Mod-Guide, improves LLM sensitivity to minority viewpoints by leveraging contextual cues derived from lived experience. Through mixed-method evaluations involving both minority and majority participants, we demonstrate that RAG-enhanced moderation responses are more contextually accurate and perceived differently across ethnic lines. This work advances research in human-computer interaction, AI ethics, and social computing by foregrounding restorative justice and hermeneutical inclusion in the design of content moderation systems.