Akbar Karimi

Postdoctoral Researcher · University of Bonn

CAISA Lab — Conversational AI and Social Analytics

Akbar Karimi

I study AI and language models and their applications in society — from social media analysis to health and medical data, and from data augmentation to model robustness under adversarial perturbations. My goal is to find ways to improve AI models and their benefits to society.

Currently I am a postdoctoral researcher at the University of Bonn, working on LLM reasoning, robustness, and AI safety at the Conversational AI and Social Analytics (CAISA) Lab led by Prof. Lucie Flek.

I completed my PhD at the University of Parma under Prof. Andrea Prati at IMP Lab, where I developed adversarial learning and data augmentation techniques for more robust language models.

Email Google Scholar ORCID GitHub

News

Dec 2025 Attending the Eurips Conference and presenting ArithmAttack and Multi-hop Reasoning with Hyperbolic Representations at the Ellis UnConference.
Nov 2025 New preprint: More Agents Helps but Adversarial Robustness Gap Persists.
Sep 2025 Attending the ECMLPKDD Conference in Porto to present the results from the Colliding with Adversaries Challenge.
Aug 2025 Attending Interspeech Conference in Rotterdam to present our recent work on speech data augmentation for German dialects.
Aug 2025 Attending ACL Conference in Vienna to present ArithmAttack and Multi-hop Reasoning with Hyperbolic Representations.

Publications

2026
Label-Consistent Data Generation for Aspect-Based Sentiment Analysis Using LLM Agents
soon to appear — WASSA @ EACL 2026
We propose an agentic data augmentation method for Aspect-Based Sentiment Analysis (ABSA) that uses iterative generation and verification to produce high-quality synthetic training examples.
2025
Multi-Hop Reasoning for Question Answering with Hyperbolic Representations
Findings of ACL
Through a simple integration of hyperbolic representations with an encoder-decoder model, we perform a controlled and comprehensive set of experiments to compare the capacity of hyperbolic space versus Euclidean space in multi-hop reasoning.
PDF
2025
ArithmAttack: Evaluating Robustness of LLMs to Noisy Context in Math Problem Solving
LLMSEC Workshop @ ACL
We propose ArithmAttack to examine how robust LLMs are when they encounter noisy prompts containing extra punctuation marks — an attack that causes no information loss yet consistently degrades performance across eight models.
PDF
2024
Do Multilingual Large Language Models Mitigate Stereotype Bias?
C3NLP Workshop @ ACL
We investigate the effect of multilingual training on bias mitigation by systematically training six LLMs of identical size (2.6B parameters): five monolingual and one multilingual model, showing that multilingual training consistently reduces bias while improving prediction accuracy.
PDF
2021
AEDA: An Easier Data Augmentation Technique for Text Classification
Findings of EMNLP
AEDA inserts punctuation marks randomly into text — simpler than EDA, lossless, and consistently superior across five classification datasets.
PDF
2020
Adversarial Training for Aspect-Based Sentiment Analysis with BERT
ICPR
We propose BERT Adversarial Training (BAT), a novel architecture that applies adversarial training to Aspect Extraction and Aspect Sentiment Classification, outperforming both general and domain post-trained BERT — the first study of its kind in ABSA.
PDF

Teaching

2025
Dialog Systems
Undergraduate · University of Bonn
Lab sessions on LLM agents, agentic frameworks including SmolAgents, LangChain, and LlamaIndex, and building personal chatbots using small models with internet search and tool-use capabilities.
2024
Dialog Systems
Undergraduate · University of Bonn
Core components of a dialog system: ASR, NLU, dialog manager, dialog state tracking, and NLG, and the tasks involved in each module.
2023
Introduction to Natural Language Processing
Undergraduate · University of Marburg
Core NLP concepts including TF-IDF, word embeddings, RNNs, and Transformers, as well as evaluation methodologies and applications in conversational systems and computational social science.
2022
Dialog Systems
Undergraduate · University of Marburg

CV

Experience
Postdoctoral Researcher & Scientific Coordinator
Oct 2023 – Dec 2025 · University of Bonn
CAISA Lab — Conversational AI and Social Analytics. Research on LLM robustness, adversarial NLP, and data augmentation; co-coordination of lab activities and student supervision.
Postdoctoral Researcher
2022 – 2023 · University of Marburg
Research on data augmentation and entity extraction for BioNLP; teaching Dialog Systems and Introduction to Natural Language Processing.
Education
Ph.D. in Information Technology
2022 · University of Parma
Thesis on adversarial learning and data augmentation for robust NLP models, under Prof. Andrea Prati at IMP Lab.
M.S. in Computer Science — Intelligent Systems
2017 · IASBS
B.S. in Computer Engineering — Software
2012 · Azad University of Zanjan
Download full CV (PDF)