Related papers: LLM-C3MOD: A Human-LLM Collaborative System for Cross-Cultural Hate Speech Moderation

Related papers

Mod-Guide: An LLM-based Content Moderation Feedback System to Address Insensitive Speech toward Indigenous Ethnic and Religious Minority Communities [22.15835643081041]
This paper focuses on Bangladesh's Hindu and Chakma communities, the country's largest religious and Indigenous ethnic minorities.<n>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)<n>Our tool, Mod-Guide, improves LLM sensitivity to minority viewpoints by leveraging contextual cues derived from lived experience.
arXiv Detail & Related papers (2026-06-11T14:28:18Z)
When Cow Urine Cures Constipation on YouTube: Limits of LLMs in Detecting Culture-specific Health Misinformation [2.4751701576209166]
Using gomutra (cow urine) discourse on YouTube in India as a case study, we present a post-facto Large Language Model (LLM)-assisted discourse analysis.<n>We show that promotional content blends sacred traditional language with pseudo-scientific claims in ways that sophisticated debunking content itself mirrors.<n>Our findings argue that cultural competency in LLM-assisted discourse analysis cannot be retrofitted through prompt engineering alone.
arXiv Detail & Related papers (2026-04-23T18:42:37Z)
Are Open-Weight LLMs Ready for Social Media Moderation? A Comparative Study on Bluesky [12.301422819746698]
Large language models (LLMs) can be effectively utilized for social media moderation tasks.<n>We evaluate seven state-of-the-art models: four proprietary and three open-weight.<n> specificity exceeds sensitivity for rudeness detection, but the opposite holds for intolerance and threats.
arXiv Detail & Related papers (2026-02-05T01:34:47Z)
LLMs and Cultural Values: the Impact of Prompt Language and Explicit Cultural Framing [0.21485350418225244]
Large Language Models (LLMs) are rapidly being adopted by users across the globe, who interact with them in a diverse range of languages.<n>We examine how prompt language and cultural framing influence model responses and their alignment with human values in different countries.
arXiv Detail & Related papers (2025-11-06T02:09:29Z)
Culture Cartography: Mapping the Landscape of Cultural Knowledge [50.502555170749694]
To serve global users safely and productively, LLMs need culture-specific knowledge that might not be learned during pre-training.<n>We propose a mixed-initiative methodology called CultureCartography.<n>Here, an LLM initializes an annotation with questions for which it has low-confidence answers, making explicit both its prior knowledge and the gaps therein.<n>This allows a human respondent to fill these gaps and steer the model towards salient topics through direct edits.<n>Compared to a baseline where humans answer LLM-proposed questions, we find that CultureExplorer more effectively produces knowledge that leading models like DeepSeek R1 and GPT-4o
arXiv Detail & Related papers (2025-10-31T17:37:34Z)
Evaluating & Reducing Deceptive Dialogue From Language Models with Multi-turn RL [64.3268313484078]
Large Language Models (LLMs) interact with millions of people worldwide in applications such as customer support, education and healthcare.<n>Their ability to produce deceptive outputs, whether intentionally or inadvertently, poses significant safety concerns.<n>We investigate the extent to which LLMs engage in deception within dialogue, and propose the belief misalignment metric to quantify deception.
arXiv Detail & Related papers (2025-10-16T05:29:36Z)
Code-Switching In-Context Learning for Cross-Lingual Transfer of Large Language Models [64.54005959758733]
We introduce code-switching in-context learning (CSICL) as a principled and robust approach for overcoming the translation barrier during inference.<n>We conduct extensive experiments across 4 LLMs, 6 datasets, and 10 languages, spanning both knowledge-intensive and reasoning-oriented domains.<n>Our results demonstrate CSICL consistently outperforms X-ICL baselines, achieving gains of 3.1%p and 1.9%p in both target and unseen languages.
arXiv Detail & Related papers (2025-10-07T08:35:42Z)
Bias Mitigation or Cultural Commonsense? Evaluating LLMs with a Japanese Dataset [34.65197313327234]
Large language models (LLMs) exhibit social biases, prompting the development of various debiasing methods.<n>Previous research has evaluated the impact of bias mitigation primarily through tasks measuring general language understanding.<n>Cultural commonsense is closely related to social biases, as both are rooted in social norms and values.
arXiv Detail & Related papers (2025-09-29T08:45:50Z)
Position: LLMs Can be Good Tutors in Foreign Language Education [87.88557755407815]
We argue that large language models (LLMs) have the potential to serve as effective tutors in foreign language education (FLE)<n> Specifically, LLMs can play three critical roles: (1) as data enhancers, improving the creation of learning materials or serving as student simulations; (2) as task predictors, serving as learner assessment or optimizing learning pathway; and (3) as agents, enabling personalized and inclusive education.
arXiv Detail & Related papers (2025-02-08T06:48:49Z)
Understanding the Dark Side of LLMs' Intrinsic Self-Correction [55.51468462722138]
Intrinsic self-correction was proposed to improve LLMs' responses via feedback prompts solely based on their inherent capability. Recent works show that LLMs' intrinsic self-correction fails without oracle labels as feedback prompts. We identify intrinsic self-correction can cause LLMs to waver both intermedia and final answers and lead to prompt bias on simple factual questions.
arXiv Detail & Related papers (2024-12-19T15:39:31Z)
Hate Personified: Investigating the role of LLMs in content moderation [64.26243779985393]
For subjective tasks such as hate detection, where people perceive hate differently, the Large Language Model's (LLM) ability to represent diverse groups is unclear. By including additional context in prompts, we analyze LLM's sensitivity to geographical priming, persona attributes, and numerical information to assess how well the needs of various groups are reflected.
arXiv Detail & Related papers (2024-10-03T16:43:17Z)
Beyond Metrics: Evaluating LLMs' Effectiveness in Culturally Nuanced, Low-Resource Real-World Scenarios [29.56889133557681]
This research evaluates the performance of seven leading Large Language Models (LLMs) in sentiment analysis on a dataset derived from WhatsApp chats. We find that while Mistral-7b and Mixtral-8x7b achieved high F1 scores, they and other LLMs such as GPT-3.5-Turbo, Llama-2-70b, and Gemma-7b struggled with understanding linguistic and contextual nuances. GPT-4 and GPT-4-Turbo excelled in grasping diverse linguistic inputs and managing various contextual information.
arXiv Detail & Related papers (2024-06-01T07:36:59Z)
Understanding the Capabilities and Limitations of Large Language Models for Cultural Commonsense [98.09670425244462]
Large language models (LLMs) have demonstrated substantial commonsense understanding. This paper examines the capabilities and limitations of several state-of-the-art LLMs in the context of cultural commonsense tasks.
arXiv Detail & Related papers (2024-05-07T20:28:34Z)
NormAd: A Framework for Measuring the Cultural Adaptability of Large Language Models [26.64843536942309]
Large language models (LLMs) may need to adapt outputs to user values and cultures, not just know about them.<n>We introduce NormAd, an evaluation framework to assess LLMs' cultural adaptability.<n>We create NormAd-Eti, a benchmark of 2.6k situational descriptions representing social-etiquette related cultural norms from 75 countries.
arXiv Detail & Related papers (2024-04-18T18:48:50Z)
CulturalTeaming: AI-Assisted Interactive Red-Teaming for Challenging LLMs' (Lack of) Multicultural Knowledge [69.82940934994333]
We introduce CulturalTeaming, an interactive red-teaming system that leverages human-AI collaboration to build challenging evaluation dataset. Our study reveals that CulturalTeaming's various modes of AI assistance support annotators in creating cultural questions. CULTURALBENCH-V0.1 is a compact yet high-quality evaluation dataset with users' red-teaming attempts.
arXiv Detail & Related papers (2024-04-10T00:25:09Z)
Is Translation All You Need? A Study on Solving Multilingual Tasks with Large Language Models [79.46179534911019]
Large language models (LLMs) have demonstrated multilingual capabilities; yet, they are mostly English-centric due to imbalanced training corpora. This work extends the evaluation from NLP tasks to real user queries. For culture-related tasks that need deep language understanding, prompting in the native language tends to be more promising.
arXiv Detail & Related papers (2024-03-15T12:47:39Z)
Large language models that replace human participants can harmfully misportray and flatten identity groups [36.36009232890876]
We show that there are two inherent limitations in the way current LLMs are trained that prevent this. We argue analytically for why LLMs are likely to both misportray and flatten the representations of demographic groups. We also discuss a third limitation about how identity prompts can essentialize identities.
arXiv Detail & Related papers (2024-02-02T21:21:06Z)
Large Language Models: The Need for Nuance in Current Debates and a Pragmatic Perspective on Understanding [1.3654846342364308]
Large Language Models (LLMs) are unparalleled in their ability to generate grammatically correct, fluent text. This position paper critically assesses three points recurring in critiques of LLM capacities. We outline a pragmatic perspective on the issue of real' understanding and intentionality in LLMs.
arXiv Detail & Related papers (2023-10-30T15:51:04Z)
Let Models Speak Ciphers: Multiagent Debate through Embeddings [84.20336971784495]
We introduce CIPHER (Communicative Inter-Model Protocol Through Embedding Representation) to address this issue. By deviating from natural language, CIPHER offers an advantage of encoding a broader spectrum of information without any modification to the model weights. This showcases the superiority and robustness of embeddings as an alternative "language" for communication among LLMs.
arXiv Detail & Related papers (2023-10-10T03:06:38Z)
Watch Your Language: Investigating Content Moderation with Large Language Models [5.306187298781318]
Large language models (LLMs) have exploded in popularity due to their ability to perform a wide array of natural language tasks. We evaluate a suite of commodity LLMs on two common content moderation tasks: rule-based community moderation and toxic content detection.
arXiv Detail & Related papers (2023-09-25T20:23:51Z)

This list is automatically generated from the titles and abstracts of the papers in this site.