# Empathetic Cascading Networks: A Multi-Stage Prompting Technique for Reducing Social Biases in Large Language Models

arXiv: https://arxiv.org/abs/2511.18696 · HTML: https://mlsanity.com/paper/2511.18696/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 13 of its 25 references that are in the map.
- First posted on arXiv 24 Nov 2025.

## Builds on (most cited first, 13 of 13)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [PaLM: Scaling Language Modeling with Pathways](https://mlsanity.com/paper/2204.02311/) (2022)
- [On the Opportunities and Risks of Foundation Models](https://mlsanity.com/paper/2108.07258/) (2021)
- [A Broad-Coverage Challenge Corpus for Sentence Understanding through Inference](https://mlsanity.com/paper/1704.05426/) (2017)
- [Language (Technology) is Power: A Critical Survey of "Bias" in NLP](https://mlsanity.com/paper/2005.14050/) (2020)
- [Improving fairness in machine learning systems: What do industry practitioners need?](https://mlsanity.com/paper/1812.05239/) (2018)
- [Tackling Data Bias in MUSIC-AVQA: Crafting a Balanced Dataset for Unbiased Question-Answering](https://mlsanity.com/paper/2310.06238/) (2023)
- [Deliberate Reasoning in Language Models as Structure-Aware Planning with an Accurate World Model](https://mlsanity.com/paper/2410.03136/) (2024)
- [AR Overlay: Training Image Pose Estimation on Curved Surface in a Synthetic Way](https://mlsanity.com/paper/2409.14577/) (2024)
- [Hedge Fund Portfolio Construction Using PolyModel Theory and iTransformer](https://mlsanity.com/paper/2408.03320/) (2024)
- [Mamba Fusion: Learning Actions Through Questioning](https://mlsanity.com/paper/2409.11513/) (2024)
- [Every Image Listens, Every Image Dances: Music-Driven Image Animation](https://mlsanity.com/paper/2501.18801/) (2025)
- [Face-GPS: A Comprehensive Technique for Quantifying Facial Muscle Dynamics in Videos](https://mlsanity.com/paper/2401.05625/) (2024)

## Abstract (arXiv)

This report presents the Empathetic Cascading Networks (ECN) framework, a multi-stage prompting method designed to enhance the empathetic and inclusive capabilities of large language models. ECN employs four stages: Perspective Adoption, Emotional Resonance, Reflective Understanding, and Integrative Synthesis, to guide models toward generating emotionally resonant and contextually aware responses. Experimental results demonstrate that ECN achieves the highest Empathy Quotient (EQ) scores across GPT-3.5-turbo and GPT-4, while maintaining competitive Regard and Perplexity metrics. These findings emphasize ECN's potential for applications requiring empathy and inclusivity in conversational AI.