# Importance of Search and Evaluation Strategies in Neural Dialogue Modeling

arXiv: https://arxiv.org/abs/1811.00907 · HTML: https://mlsanity.com/paper/1811.00907/

## Key facts

- Cited by 44 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 Nov 2018.

## Built on by (most cited first, 30 of 44)

- [Survey of Hallucination in Natural Language Generation](https://mlsanity.com/paper/2202.03629/) (2022)
- [From Decoding to Meta-Generation: Inference-time Algorithms for Large Language Models](https://mlsanity.com/paper/2406.16838/) (2024)
- [Jointly Reinforcing Diversity and Quality in Language Model Generations](https://mlsanity.com/paper/2509.02534/) (2025)
- [A Survey on Non-Autoregressive Generation for Neural Machine Translation and Beyond](https://mlsanity.com/paper/2204.09269/) (2022)
- [Human Evaluation of Conversations is an Open Problem: comparing the sensitivity of various methods for evaluating dialogue agents](https://mlsanity.com/paper/2201.04723/) (2022)
- [DeAL: Decoding-time Alignment for Large Language Models](https://mlsanity.com/paper/2402.06147/) (2024)
- [The Homogenizing Effect of Large Language Models on Human Expression and Thought](https://mlsanity.com/paper/2508.01491/) (2025)
- [Meet Your Favorite Character: Open-domain Chatbot Mimicking Fictional Characters with only a Few Utterances](https://mlsanity.com/paper/2204.10825/) (2022)
- [More but Correct: Generating Diversified and Entity-revised Medical Response](https://mlsanity.com/paper/2108.01266/) (2021)
- [Submix: Practical Private Prediction for Large-Scale Language Models](https://mlsanity.com/paper/2201.00971/) (2022)
- [Focus Attention: Promoting Faithfulness and Diversity in Summarization](https://mlsanity.com/paper/2105.11921/) (2021)
- [Diversifying Dialog Generation via Adaptive Label Smoothing](https://mlsanity.com/paper/2105.14556/) (2021)
- [The Authenticity Gap in Human Evaluation](https://mlsanity.com/paper/2205.11930/) (2022)
- [Am I Me or You? State-of-the-Art Dialogue Models Cannot Maintain an Identity](https://mlsanity.com/paper/2112.05843/) (2021)
- [An Overview on Language Models: Recent Developments and Outlook](https://mlsanity.com/paper/2303.05759/) (2023)
- [Entropy-Gated Branching for Efficient Test-Time Reasoning](https://mlsanity.com/paper/2503.21961/) (2025)
- [ProtAugment: Unsupervised diverse short-texts paraphrasing for intent detection meta-learning](https://mlsanity.com/paper/2105.12995/) (2021)
- [Controllable Text Summarization: Unraveling Challenges, Approaches, and Prospects -- A Survey](https://mlsanity.com/paper/2311.09212/) (2023)
- [Measuring and Improving Semantic Diversity of Dialogue Generation](https://mlsanity.com/paper/2210.05725/) (2022)
- [QUEST: Quality-Aware Metropolis-Hastings Sampling for Machine Translation](https://mlsanity.com/paper/2406.00049/) (2024)
- [Building Persona Consistent Dialogue Agents with Offline Reinforcement Learning](https://mlsanity.com/paper/2310.10735/) (2023)
- [A Cognitive Regularizer for Language Modeling](https://mlsanity.com/paper/2105.07144/) (2021)
- [Generating Diverse and High-Quality Texts by Minimum Bayes Risk Decoding](https://mlsanity.com/paper/2401.05054/) (2024)
- [Active Evaluation: Efficient NLG Evaluation with Few Pairwise Comparisons](https://mlsanity.com/paper/2203.06063/) (2022)
- [A Multimodal PDE Foundation Model for Prediction and Scientific Text Descriptions](https://mlsanity.com/paper/2502.06026/) (2025)
- [Towards Efficiently Diversifying Dialogue Generation via Embedding Augmentation](https://mlsanity.com/paper/2103.01534/) (2021)
- [Reference-free Evaluation Metrics for Text Generation: A Survey](https://mlsanity.com/paper/2501.12011/) (2025)
- [How to Evaluate a Summarizer: Study Design and Statistical Analysis for Manual Linguistic Quality Evaluation](https://mlsanity.com/paper/2101.11298/) (2021)
- [Towards Standard Criteria for human evaluation of Chatbots: A Survey](https://mlsanity.com/paper/2105.11197/) (2021)
- [Diversifying Neural Dialogue Generation via Negative Distillation](https://mlsanity.com/paper/2205.02795/) (2022)

## Abstract (arXiv)

We investigate the impact of search strategies in neural dialogue modeling. We first compare two standard search algorithms, greedy and beam search, as well as our newly proposed iterative beam search which produces a more diverse set of candidate responses. We evaluate these strategies in realistic full conversations with humans and propose a model-based Bayesian calibration to address annotator bias. These conversations are analyzed using two automatic metrics: log-probabilities assigned by the model and utterance diversity. Our experiments reveal that better search algorithms lead to higher rated conversations. However, finding the optimal selection mechanism to choose from a more diverse set of candidates is still an open question.