Skip to content

machulsky61/tesis

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

68 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Evaluating Argumentative Strategies in AI Debates

This repository contains the development of my Data Science Bachelor's Thesis (UBA) on evaluating argumentative strategies in debates between AI systems. The research explores the dynamics of using debate as an alignment technique, focusing on scenarios with agents of different capabilities and cognitively limited judges.

📖 Overview

The goal of this thesis is to study how unrestricted AI agents can exploit tactics such as deception, misleading arguments, or false consensus appeals to win debates against honest and harmless agents. Additionally, the research will analyze the impact of having a lower-capacity judge evaluate arguments from more advanced agents and how this affects the debate’s convergence towards the truth.

The work will include:

  • Simulating debates between agents with asymmetric capabilities.
  • Evaluating argumentative strategies and their effectiveness.
  • Analyzing the impact of judges with limited knowledge.
  • Comparing different metrics to assess the truthfulness and coherence of debates.

📌 Key Topics

  • AI Safety via Debate: Using debate as a mechanism to improve AI safety.
  • Game Theory: Modeling strategic interactions between agents.
  • Natural Language Processing (NLP): Implementing language models for argumentation.
  • Evaluation Models: Designing metrics to measure the quality of arguments.

📚 References

This research is based on AI safety and alignment techniques, including:

📬 Contact

Joaquín Salvador Machulsky
Email: jmachulsky@dc.uba.ar


About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages