Code to compute AnthroScore, a computational linguistic measure of anthropomorphism in text

The dataset contains 1,508 TikTok comments related to cyberbullying, focusing on humiliation pertaining to physical appearance, including ridicule, insults, or body-shaming.

HiSim: A Hybrid Social Media Simulation Framework

website repo for agent-based social movement simulation

Plurals: A System for Guiding LLMs Via Simulated Social Ensembles

A set of pre-trained machine-learning models that predict (im-)politeness scores in texts.

Open-Source Frontier Voice AI

[NAACL 2025] KMI: A Dataset of Korean Motivational Interviewing Dialogues for Psychotherapy

An open-source AI agent that brings the power of Gemini directly into your terminal.

Repository for paper 'Adaptive-VP: A Framework for LLM-Based Virtual Patients that Adapts to Trainees' Dialogue to Facilitate Nurse Communication Training'

A Korean political sentiment classifier fine-tuned on KoELECTRA, developed for analyzing political discourse in news, comments, and party statements.

Decoding Echo Chambers: LLM-Powered Simulations Revealing Polarization in Social Networks

AgentSociety: Large-scale Social Simulation to Understand Human Behaviors and Society through LLM-driven Agents

랭체인 튜토리얼

Source codes for the paper "Examining the Ordering of Rhetorical Strategies in Persuasive Requests"

Data and experiment code for "Beyond Demographics: Fine-tuning Large Language Models to Predict Individuals’ Subjective Text Perceptions" (ACL2025)

TyDiP Multilingual Politeness dataset and code

Data and code for the paper "An LLM Feature-based Framework for Dialogue Constructiveness Assessment,” EMNLP 2024

The most modern LLM evaluation toolkit

Trained models & code to predict toxic comments on all 3 Jigsaw Toxic Comment Challenges. Built using ⚡ Pytorch Lightning and 🤗 Transformers. For access to our API, please email us at contact@unita…

A Crisis of Civility? Modeling Incivility and Its Effects in Political Discourse Online

Can we use explanations to improve hate speech models? Our paper accepted at AAAI 2021 tries to explore that question.