Papers by Navid Madani
ESC-Judge: A Framework for Comparing Emotional Support Conversational Agents (2025.emnlp-main)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) increasingly power mental-health chatbots . yet the field lacks a scalable, theory-grounded way to decide which model is more effective to deploy. |
| Approach: | They propose a framework that grounds head-to-head comparisons of Emotional-Support LLMs in Hill’s Exploration–Insight–Action counselling model. |
| Outcome: | The proposed framework matches PhD-level annotators in 85% of Exploration, 83% of Insight, and 86% of Action decisions, demonstrating human-level reliability at a fraction of the cost. |
A Recipe For Building a Compliant Real Estate Chatbot (2025.coling-industry)
Copied to clipboard
| Challenge: | In recent years, there has been significant effort to align large language models with human preferences. |
| Approach: | They propose to use a general instruction-following dataset to generate a chatbot that can be used without perpetuating discriminatory practices like steering and redlining. |
| Outcome: | The proposed model can match closed-source models like GPT-4o while being safer and more compliant. |