Challenge: Trending topics bring in a new channel for poisoning attacks, resulting in negative impacts on society.
Approach: They propose an LLM-based multi-agent system to simulate trending topics in social media . they propose a time-aware interaction mechanism, centralized message dissemination, and an interactive system .
Outcome: The proposed system simulates trending topics under poisoning attacks on social media platforms.

Similar Papers

A Survey on Detection of LLMs-Generated Content (2024.findings-emnlp)

Copied to clipboard

Challenge: Recent advances in large language models have led to an increase in synthetic content generation . the ability to detect LLMs-generated content has become of paramount importance .
Approach: They propose to provide a detailed overview of existing detection strategies and benchmarks, scrutinizing their differences and advocating for more adaptable and robust models to enhance detection accuracy.
Outcome: The proposed model will be able to detect human-written content in real time.
PoisonedParrot: Subtle Data Poisoning Attacks to Elicit Copyright-Infringing Content from Large Language Models (2025.naacl-long)

Copied to clipboard

Challenge: PoisonedParrot is the first stealthy data poisoning attack that induces an LLM to generate copyrighted content even when the model has not been directly trained on the copyright material.
Approach: They propose a stealthy data poisoning attack that induces an LLM to generate copyrighted content even when it has not been directly trained on the copyright material.
Outcome: The proposed model induces an LLM to generate copyrighted content with no discernible side effects and is surprisingly effective at priming the model to generate content with little side effects.
Re-ranking Using Large Language Models for Mitigating Exposure to Harmful Content on Social Media Platforms (2025.acl-long)

Copied to clipboard

Challenge: Social media platforms use machine learning and artificial intelligence to maximize user engagement, but can indirectly cause exposure to harmful content.
Approach: They propose a re-ranking approach using Large Language Models to assess and rerank content sequences using large annotated data sets.
Outcome: The proposed method significantly outperforms existing proprietary moderation methods on three datasets, three models and across three configurations.
MOSAIC: Modeling Social AI for Content Dissemination and Regulation in Multi-Agent Simulations (2025.emnlp-main)

Copied to clipboard

Challenge: generative language agents predict user behaviors such as liking, sharing, and flagging content.
Approach: They propose a framework where generative language agents predict user behaviors such as liking, sharing, and flagging content.
Outcome: The proposed framework analyzes content moderation strategies and user engagement dynamics at scale and demonstrates that agents’ articulated reasoning for their social interactions aligns with their collective engagement patterns.
iAgent: LLM Agent as a Shield between User and Recommender Systems (2025.findings-acl)

Copied to clipboard

Challenge: Traditional recommender systems focus on the user-platform paradigm, where users are directly exposed under the control of the platform's recommendation algorithms.
Approach: They propose a user-agent-platform paradigm where agent serves as the protective shield between user and recommender system that enables indirect exposure.
Outcome: The proposed model improves 16.6% over baselines on four datasets and mitigates echo chamber effects and reduces model bias in disadvantaged users.
An Empirical Study of Collective Behaviors and Social Dynamics in Large Language Model Agents (2026.eacl-long)

Copied to clipboard

Challenge: Large Language Models (LLMs) are increasingly mediating our social, cultural, and political interactions.
Approach: They propose a method that reminds LLM agents to avoid harmful posting . they analyze 7M posts and interactions among 32K LLMs over a year .
Outcome: The proposed method aims to find out whether LLMs influence toxic posting patterns and polarization in their community.
Context-Aware Sentiment Forecasting via LLM-based Multi-Perspective Role-Playing Agents (2025.acl-long)

Copied to clipboard

Challenge: Existing methods to predict sentiments on social media are limited and do not consider reciprocal influences among social media users.
Approach: They propose a multi-perspective role-playing framework to simulate human response processes to extract sentiment-related features from social media messages.
Outcome: The proposed model improves sentiment forecasting at microscopic and macroscopic levels.
Author Profiling for Abuse Detection (C18-1)

Copied to clipboard

Challenge: Existing methods for detecting abusive content rely on textual cues and lexical cue information.
Approach: They propose a method that incorporates community-based profiling features of Twitter users to detect abusive content by using a dataset of 16k tweets.
Outcome: The proposed approach outperforms the current state-of-the-art in abuse detection on a dataset of 16k tweets.
ModelCitizens: Representing Community Voices in Online Safety (2025.emnlp-main)

Copied to clipboard

Challenge: Existing toxic language detection models are trained on annotations that collapse diverse perspectives into a single ground truth.
Approach: They propose to augment social media posts with conversational scenarios to reflect the impact of conversational context on toxicity.
Outcome: The proposed model outperforms existing models on social media with conversational scenarios.
Attacks, Defenses and Evaluations for LLM Conversation Safety: A Survey (2024.naacl-long)

Copied to clipboard

Challenge: Large Language Models (LLMs) are now commonplace in conversation applications, but their misuse for generating harmful responses has raised serious societal concerns.
Approach: They provide a comprehensive overview of recent studies covering attacks, defenses, and evaluations of Large Language Models (LLMs) .
Outcome: The proposed review summarizes three aspects of LLM conversation safety: attacks, defenses, and evaluations.

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