# Socio-Emotional Response Generation: A Human Evaluation Protocol for LLM-Based Conversational Systems

arXiv: https://arxiv.org/abs/2412.04492 · HTML: https://mlsanity.com/paper/2412.04492/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 24 of its 45 references that are in the map.
- First posted on arXiv 26 Nov 2024.

## Builds on (most cited first, 24 of 24)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension](https://mlsanity.com/paper/1910.13461/) (2019)
- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [A Call for Clarity in Reporting BLEU Scores](https://mlsanity.com/paper/1804.08771/) (2018)
- [LaMDA: Language Models for Dialog Applications](https://mlsanity.com/paper/2201.08239/) (2022)
- [DialoGPT: Large-Scale Generative Pre-training for Conversational Response Generation](https://mlsanity.com/paper/1911.00536/) (2019)
- [DailyDialog: A Manually Labelled Multi-turn Dialogue Dataset](https://mlsanity.com/paper/1710.03957/) (2017)
- [Towards Emotional Support Dialog Systems](https://mlsanity.com/paper/2106.01144/) (2021)
- [Gradio: Hassle-Free Sharing and Testing of ML Models in the Wild](https://mlsanity.com/paper/1906.02569/) (2019)
- [SODA: Million-scale Dialogue Distillation with Social Commonsense Contextualization](https://mlsanity.com/paper/2212.10465/) (2022)
- [Knowledge Bridging for Empathetic Dialogue Generation](https://mlsanity.com/paper/2009.09708/) (2020)
- [Enhancing Emotional Generation Capability of Large Language Models via Emotional Chain-of-Thought](https://mlsanity.com/paper/2401.06836/) (2024)
- [Generating Empathetic Responses by Looking Ahead the User's Sentiment](https://mlsanity.com/paper/1906.08487/) (2019)
- [EmoWOZ: A Large-Scale Corpus and Labelling Scheme for Emotion Recognition in Task-Oriented Dialogue Systems](https://mlsanity.com/paper/2109.04919/) (2021)
- [Towards an Online Empathetic Chatbot with Emotion Causes](https://mlsanity.com/paper/2105.11903/) (2021)
- [NLG Evaluation Metrics Beyond Correlation Analysis: An Empirical Metric Preference Checklist](https://mlsanity.com/paper/2305.08566/) (2023)
- [CAiRE: An Empathetic Neural Chatbot](https://mlsanity.com/paper/1907.12108/) (2019)
- [Empathetic Conversational Systems: A Review of Current Advances, Gaps, and Opportunities](https://mlsanity.com/paper/2206.05017/) (2022)
- [Enhancing Empathetic Response Generation by Augmenting LLMs with Small-scale Empathetic Models](https://mlsanity.com/paper/2402.11801/) (2024)
- [Don't Forget Your ABC's: Evaluating the State-of-the-Art in Chat-Oriented Dialogue Systems](https://mlsanity.com/paper/2212.09180/) (2022)
- [An Empirical Study on the Overlapping Problem of Open-Domain Dialogue Datasets](https://mlsanity.com/paper/2201.06219/) (2022)
- [How About Kind of Generating Hedges using End-to-End Neural Models?](https://mlsanity.com/paper/2306.14696/) (2023)
- [Seeing and hearing what has not been said; A multimodal client behavior classifier in Motivational Interviewing with interpretable fusion](https://mlsanity.com/paper/2309.14398/) (2023)

## Abstract (arXiv)

Conversational systems are now capable of producing impressive and generally relevant responses. However, we have no visibility nor control of the socio-emotional strategies behind state-of-the-art Large Language Models (LLMs), which poses a problem in terms of their transparency and thus their trustworthiness for critical applications. Another issue is that current automated metrics are not able to properly evaluate the quality of generated responses beyond the dataset's ground truth. In this paper, we propose a neural architecture that includes an intermediate step in planning socio-emotional strategies before response generation. We compare the performance of open-source baseline LLMs to the outputs of these same models augmented with our planning module. We also contrast the outputs obtained from automated metrics and evaluation results provided by human annotators. We describe a novel evaluation protocol that includes a coarse-grained consistency evaluation, as well as a finer-grained annotation of the responses on various social and emotional criteria. Our study shows that predicting a sequence of expected strategy labels and using this sequence to generate a response yields better results than a direct end-to-end generation scheme. It also highlights the divergences and the limits of current evaluation metrics for generated content. The code for the annotation platform and the annotated data are made publicly available for the evaluation of future models.