Use LLMs to identify premises and claims within the ECHR dataset.

Fine-Tuning BERT on Political Debates for Enhanced Embeddings in Political Analysis

Multimodal Argument Mining Toolkit

An ontology for extracting dialectical perspectives from argumentative discourse.

st-annotator is a Streamlit component usefull to annotate text, expecially for NLP and Argument Mining purposes.

This paper addresses the problem of cross-register generalization in argument mining within political discourse. We examine whether models trained on adversarial, spontaneous U.S. presidential debates can generalize to the more diplomatic and prepared register of UN Security Council speeches.

Investigating the Impact of Prompt Engineering on LLMs in Argument Mining

Official source code for the paper "Leveraging Context for Multimodal Fallacy Classification in Political Debates", accepted at the ArgMining Workshop @ ACL 2025.

A CLI client to mine arguments and their relations from social media posts

This repository contains the code and data used for the evaluation paper "Limited Generalizability in Argument Mining: State-Of-The-Art Models Learn Datasets, Not Arguments"

Code for the paper "Towards an Argument Mining Pipeline Transforming Texts to Argument Graphs" presented at COMMA 2020

Multimodal Fallacy Classification in Political Debates: Dataset and Experiments.

An LLM-based Approach For Comprehensive Argument Mining

Novel unified representation to solve all the sub-tasks of argumentation mining

Welcome to the Framework for Mining Arguments repository! This project aims to provide a comprehensive framework for mining arguments from textual data.

This repository contains the code used for the method paper "BERTweet’s TACO Fiesta: Contrasting Flavors On The Path Of Inference And Information-Driven Argument Mining On Twitter".

This repository contains the annotation framework, dataset and code used for the resource paper "TACO -- Twitter Arguments from COnversations".

BERT--MINUS--FeaTxt Project for IJCNN 2023

Example application for applying QLoRA-based Parameter-Efficient Fine-Tuning (PEFT) to a Stance Detection task using Gemma-2-9B-Instruct

Analyzing and scoring reasoning traces of LLMs