# Approximating Online Human Evaluation of Social Chatbots with Prompting

arXiv: https://arxiv.org/abs/2304.05253 · HTML: https://mlsanity.com/paper/2304.05253/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Builds on 36 of its 56 references that are in the map.
- First posted on arXiv 11 Apr 2023.

## Builds on (most cited first, 30 of 36)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [PaLM: Scaling Language Modeling with Pathways](https://mlsanity.com/paper/2204.02311/) (2022)
- [Scaling Instruction-Finetuned Language Models](https://mlsanity.com/paper/2210.11416/) (2022)
- [TruthfulQA: Measuring How Models Mimic Human Falsehoods](https://mlsanity.com/paper/2109.07958/) (2021)
- [Emergent Abilities of Large Language Models](https://mlsanity.com/paper/2206.07682/) (2022)
- [LaMDA: Language Models for Dialog Applications](https://mlsanity.com/paper/2201.08239/) (2022)
- [Exploiting Cloze Questions for Few Shot Text Classification and Natural Language Inference](https://mlsanity.com/paper/2001.07676/) (2020)
- [Recipes for building an open-domain chatbot](https://mlsanity.com/paper/2004.13637/) (2020)
- [Towards a Human-like Open-Domain Chatbot](https://mlsanity.com/paper/2001.09977/) (2020)
- [How NOT To Evaluate Your Dialogue System: An Empirical Study of Unsupervised Evaluation Metrics for Dialogue Response Generation](https://mlsanity.com/paper/1603.08023/) (2016)
- [Unsupervised Evaluation of Interactive Dialog with DialoGPT](https://mlsanity.com/paper/2006.12719/) (2020)
- [MIME: MIMicking Emotions for Empathetic Response Generation](https://mlsanity.com/paper/2010.01454/) (2020)
- [ProsocialDialog: A Prosocial Backbone for Conversational Agents](https://mlsanity.com/paper/2205.12688/) (2022)
- [Towards an Automatic Turing Test: Learning to Evaluate Dialogue Responses](https://mlsanity.com/paper/1708.07149/) (2017)
- [Evaluating Human-Language Model Interaction](https://mlsanity.com/paper/2212.09746/) (2022)
- [A Comprehensive Assessment of Dialog Evaluation Metrics](https://mlsanity.com/paper/2106.03706/) (2021)
- [RUBER: An Unsupervised Method for Automatic Evaluation of Open-Domain Dialog Systems](https://mlsanity.com/paper/1701.03079/) (2017)
- [ACUTE-EVAL: Improved Dialogue Evaluation with Optimized Questions and Multi-turn Comparisons](https://mlsanity.com/paper/1909.03087/) (2019)
- [GRADE: Automatic Graph-Enhanced Coherence Metric for Evaluating Open-Domain Dialogue Systems](https://mlsanity.com/paper/2010.03994/) (2020)
- [DynaEval: Unifying Turn and Dialogue Level Evaluation](https://mlsanity.com/paper/2106.01112/) (2021)
- [A Taxonomy of Empathetic Response Intents in Human Social Conversations](https://mlsanity.com/paper/2012.04080/) (2020)
- [Overview of the Ninth Dialog System Technology Challenge: DSTC9](https://mlsanity.com/paper/2011.06486/) (2020)
- [Approximating Interactive Human Evaluation with Self-Play for Open-Domain Dialog Systems](https://mlsanity.com/paper/1906.09308/) (2019)
- [Conversations Are Not Flat: Modeling the Dynamic Information Flow across Dialogue Utterances](https://mlsanity.com/paper/2106.02227/) (2021)
- [Predictive Engagement: An Efficient Metric For Automatic Evaluation of Open-Domain Dialogue Systems](https://mlsanity.com/paper/1911.01456/) (2019)
- [Spot The Bot: A Robust and Efficient Framework for the Evaluation of Conversational Dialogue Systems](https://mlsanity.com/paper/2010.02140/) (2020)
- [DEAM: Dialogue Coherence Evaluation using AMR-based Semantic Manipulations](https://mlsanity.com/paper/2203.09711/) (2022)
- [What is wrong with you?: Leveraging User Sentiment for Automatic Dialog Evaluation](https://mlsanity.com/paper/2203.13927/) (2022)

## Built on by (most cited first, 11 of 11)

- [Sociotechnical Safety Evaluation of Generative AI Systems](https://mlsanity.com/paper/2310.11986/) (2023)
- [Deep Learning for Cross-Domain Data Fusion in Urban Computing: Taxonomy, Advances, and Outlook](https://mlsanity.com/paper/2402.19348/) (2024)
- [The Challenges of Evaluating LLM Applications: An Analysis of Automated, Human, and LLM-Based Approaches](https://mlsanity.com/paper/2406.03339/) (2024)
- [Real or Robotic? Assessing Whether LLMs Accurately Simulate Qualities of Human Responses in Dialogue](https://mlsanity.com/paper/2409.08330/) (2024)
- [LLM Roleplay: Simulating Human-Chatbot Interaction](https://mlsanity.com/paper/2407.03974/) (2024)
- [Large Language Models as User-Agents for Evaluating Task-Oriented-Dialogue Systems](https://mlsanity.com/paper/2411.09972/) (2024)
- [A Comparison of LLM Finetuning Methods & Evaluation Metrics with Travel Chatbot Use Case](https://mlsanity.com/paper/2408.03562/) (2024)
- [Synthetic Users, Real Differences: an Evaluation Framework for User Simulation in Multi-Turn Conversations](https://mlsanity.com/paper/2605.02624/) (2026)
- [A Concise Agent is Less Expert: Revealing Side Effects of Using Style Features on Conversational Agents](https://mlsanity.com/paper/2601.10809/) (2026)
- [From RAG to QA-RAG: Integrating Generative AI for Pharmaceutical Regulatory Compliance Process](https://mlsanity.com/paper/2402.01717/) (2024)
- [Online vs Offline: A Comparative Study of First-Party and Third-Party Evaluations of Social Chatbots](https://mlsanity.com/paper/2409.07823/) (2024)

## Abstract (arXiv)

As conversational models become increasingly available to the general public, users are engaging with this technology in social interactions. Such unprecedented interaction experiences may pose considerable social and psychological risks to the users unless the technology is properly controlled. This highlights the need for scalable and robust evaluation metrics for conversational chatbots. Existing evaluation metrics aim to automate offline user evaluation and approximate human judgment of pre-curated dialogs. However, they are limited in their ability to capture subjective perceptions of users who actually interact with the bots and might not generalize to real-world settings. To address this limitation, we propose an approach to approximate online human evaluation leveraging large language models (LLMs) from the GPT family. We introduce a new Dialog system Evaluation framework based on Prompting (DEP), which enables a fully automatic evaluation pipeline that replicates live user studies and achieves an impressive correlation with human judgment (up to Pearson r=0.95 on a system level). The DEP approach involves collecting synthetic chat logs of evaluated bots with an LLM in the other-play setting, where the LLM is carefully conditioned to follow a specific scenario. We further explore different prompting approaches to produce evaluation scores with the same LLM. The best performing prompts, which contain few-shot demonstrations and instructions, show outstanding performance on the tested dataset and demonstrate the ability to generalize to other dialog corpora.