# Meta-evaluation of Conversational Search Evaluation Metrics

arXiv: https://arxiv.org/abs/2104.13453 · HTML: https://mlsanity.com/paper/2104.13453/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 38 of its 102 references that are in the map.
- First posted on arXiv 27 Apr 2021.

## Builds on (most cited first, 30 of 38)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [SQuAD: 100,000+ Questions for Machine Comprehension of Text](https://mlsanity.com/paper/1606.05250/) (2016)
- [Sequence to Sequence Learning with Neural Networks](https://mlsanity.com/paper/1409.3215/) (2014)
- [MultiWOZ -- A Large-Scale Multi-Domain Wizard-of-Oz Dataset for Task-Oriented Dialogue Modelling](https://mlsanity.com/paper/1810.00278/) (2018)
- [DailyDialog: A Manually Labelled Multi-turn Dialogue Dataset](https://mlsanity.com/paper/1710.03957/) (2017)
- [Wizard of Wikipedia: Knowledge-Powered Conversational agents](https://mlsanity.com/paper/1811.01241/) (2018)
- [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)
- [FastText.zip: Compressing text classification models](https://mlsanity.com/paper/1612.03651/) (2016)
- [Why We Need New Evaluation Metrics for NLG](https://mlsanity.com/paper/1707.06875/) (2017)
- [USR: An Unsupervised and Reference Free Evaluation Metric for Dialog Generation](https://mlsanity.com/paper/2005.00456/) (2020)
- [A Hierarchical Latent Variable Encoder-Decoder Model for Generating Dialogues](https://mlsanity.com/paper/1605.06069/) (2016)
- [The Ubuntu Dialogue Corpus: A Large Dataset for Research in Unstructured Multi-Turn Dialogue Systems](https://mlsanity.com/paper/1506.08909/) (2015)
- [A Knowledge-Grounded Neural Conversation Model](https://mlsanity.com/paper/1702.01932/) (2017)
- [Survey on Evaluation Methods for Dialogue Systems](https://mlsanity.com/paper/1905.04071/) (2019)
- [Generating Informative and Diverse Conversational Responses via Adversarial Information Maximization](https://mlsanity.com/paper/1809.05972/) (2018)
- [Sequential Matching Network: A New Architecture for Multi-turn Response Selection in Retrieval-based Chatbots](https://mlsanity.com/paper/1612.01627/) (2016)
- [A Neural Network Approach to Context-Sensitive Generation of Conversational Responses](https://mlsanity.com/paper/1506.06714/) (2015)
- [Towards an Automatic Turing Test: Learning to Evaluate Dialogue Responses](https://mlsanity.com/paper/1708.07149/) (2017)
- [RUBER: An Unsupervised Method for Automatic Evaluation of Open-Domain Dialog Systems](https://mlsanity.com/paper/1701.03079/) (2017)
- [Better Automatic Evaluation of Open-Domain Dialogue Systems with Contextualized Embeddings](https://mlsanity.com/paper/1904.10635/) (2019)
- [Learning an Unreferenced Metric for Online Dialogue Evaluation](https://mlsanity.com/paper/2005.00583/) (2020)
- [Re-evaluating Automatic Metrics for Image Captioning](https://mlsanity.com/paper/1612.07600/) (2016)
- [Sentence-Level Fluency Evaluation: References Help, But Can Be Spared!](https://mlsanity.com/paper/1809.08731/) (2018)
- [Analyzing and Characterizing User Intent in Information-seeking Conversations](https://mlsanity.com/paper/1804.08759/) (2018)
- [The Eighth Dialog System Technology Challenge](https://mlsanity.com/paper/1911.06394/) (2019)
- [deltaBLEU: A Discriminative Metric for Generation Tasks with Intrinsically Diverse Targets](https://mlsanity.com/paper/1506.06863/) (2015)
- [WikiPassageQA: A Benchmark Collection for Research on Non-factoid Answer Passage Retrieval](https://mlsanity.com/paper/1805.03797/) (2018)
- [Response Ranking with Deep Matching Networks and External Knowledge in Information-seeking Conversation Systems](https://mlsanity.com/paper/1805.00188/) (2018)
- [Explicit State Tracking with Semi-Supervision for Neural Dialogue Generation](https://mlsanity.com/paper/1808.10596/) (2018)

## Built on by (most cited first, 6 of 6)

- [cushLEPOR: customising hLEPOR metric using Optuna for higher agreement with human judgments or pre-trained language model LaBSE](https://mlsanity.com/paper/2108.09484/) (2021)
- [A RAG-Based Multi-Agent LLM System for Natural Hazard Resilience and Adaptation](https://mlsanity.com/paper/2504.17200/) (2025)
- [Examining Large Pre-Trained Language Models for Machine Translation: What You Don't Know About It](https://mlsanity.com/paper/2209.07417/) (2022)
- [POSSCORE: A Simple Yet Effective Evaluation of Conversational Search with Part of Speech Labelling](https://mlsanity.com/paper/2109.03039/) (2021)
- [Dagstuhl Perspectives Workshop 24352 -- Conversational Agents: A Framework for Evaluation (CAFE): Manifesto](https://mlsanity.com/paper/2506.11112/) (2025)
- [The Laws of Context Allocation: Causal Measurement and Closed-Loop Orchestration in Generative Search](https://mlsanity.com/paper/2608.23252/) (2026)

## Abstract (arXiv)

Conversational search systems, such as Google Assistant and Microsoft Cortana, enable users to interact with search systems in multiple rounds through natural language dialogues. Evaluating such systems is very challenging given that any natural language responses could be generated, and users commonly interact for multiple semantically coherent rounds to accomplish a search task. Although prior studies proposed many evaluation metrics, the extent of how those measures effectively capture user preference remains to be investigated. In this paper, we systematically meta-evaluate a variety of conversational search metrics. We specifically study three perspectives on those metrics: (1) reliability: the ability to detect "actual" performance differences as opposed to those observed by chance; (2) fidelity: the ability to agree with ultimate user preference; and (3) intuitiveness: the ability to capture any property deemed important: adequacy, informativeness, and fluency in the context of conversational search. By conducting experiments on two test collections, we find that the performance of different metrics varies significantly across different scenarios whereas consistent with prior studies, existing metrics only achieve a weak correlation with ultimate user preference and satisfaction. METEOR is, comparatively speaking, the best existing single-turn metric considering all three perspectives. We also demonstrate that adapted session-based evaluation metrics can be used to measure multi-turn conversational search, achieving moderate concordance with user satisfaction. To our knowledge, our work establishes the most comprehensive meta-evaluation for conversational search to date.