mlsanityData to 14 Oct 2026

Importance of Search and Evaluation Strategies in Neural Dialogue Modeling

arXiv 1811.00907 ↗First posted 2 Nov 2018cs.CL cs.LGcited by 44

Not on the map. Why?

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.

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

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 12; 2022: 9; 2023: 4; 2024: 6; 2025: 10; 2026: 3.

44 papers.

Sort:

By area:

  1. 2022Survey of Hallucination in Natural Language Generationcited by 2,075
  2. 2024From Decoding to Meta-Generation: Inference-time Algorithms for Large Language Modelscited by 137
  3. 2025Jointly Reinforcing Diversity and Quality in Language Model Generationscited by 80
  4. 2022A Survey on Non-Autoregressive Generation for Neural Machine Translation and Beyondcited by 64
  5. 2022Human Evaluation of Conversations is an Open Problem: comparing the sensitivity of various methods for evaluating dialogue agentscited by 62
  6. 2024DeAL: Decoding-time Alignment for Large Language Modelscited by 55
  7. 2025The Homogenizing Effect of Large Language Models on Human Expression and Thoughtcited by 35
  8. 2022Meet Your Favorite Character: Open-domain Chatbot Mimicking Fictional Characters with only a Few Utterancescited by 32
  9. 2021More but Correct: Generating Diversified and Entity-revised Medical Responsecited by 31
  10. 2022Submix: Practical Private Prediction for Large-Scale Language Modelscited by 31
  11. 2021Focus Attention: Promoting Faithfulness and Diversity in Summarizationcited by 30
  12. 2021Diversifying Dialog Generation via Adaptive Label Smoothingcited by 25
32 more
  1. 2022The Authenticity Gap in Human Evaluationcited by 24
  2. 2021Am I Me or You? State-of-the-Art Dialogue Models Cannot Maintain an Identitycited by 22
  3. 2023An Overview on Language Models: Recent Developments and Outlookcited by 22
  4. 2025Entropy-Gated Branching for Efficient Test-Time Reasoningcited by 22
  5. 2021ProtAugment: Unsupervised diverse short-texts paraphrasing for intent detection meta-learningcited by 18
  6. 2023Controllable Text Summarization: Unraveling Challenges, Approaches, and Prospects -- A Surveycited by 18
  7. 2022Measuring and Improving Semantic Diversity of Dialogue Generationcited by 16
  8. 2024QUEST: Quality-Aware Metropolis-Hastings Sampling for Machine Translationcited by 16
  9. 2023Building Persona Consistent Dialogue Agents with Offline Reinforcement Learningcited by 14
  10. 2021A Cognitive Regularizer for Language Modelingcited by 11
  11. 2024Generating Diverse and High-Quality Texts by Minimum Bayes Risk Decodingcited by 11
  12. 2022Active Evaluation: Efficient NLG Evaluation with Few Pairwise Comparisonscited by 10
  13. 2025A Multimodal PDE Foundation Model for Prediction and Scientific Text Descriptionscited by 10
  14. 2021Towards Efficiently Diversifying Dialogue Generation via Embedding Augmentationcited by 9
  15. 2025Reference-free Evaluation Metrics for Text Generation: A Surveycited by 9
  16. 2021How to Evaluate a Summarizer: Study Design and Statistical Analysis for Manual Linguistic Quality Evaluationcited by 7
  17. 2021Towards Standard Criteria for human evaluation of Chatbots: A Surveycited by 6
  18. 2022Diversifying Neural Dialogue Generation via Negative Distillationcited by 6
  19. 2024The Unreasonable Ineffectiveness of Nucleus Sampling on Mitigating Text Memorizationcited by 6
  20. 2021EmpBot: A T5-based Empathetic Chatbot focusing on Sentimentscited by 5
  21. 2026Controlling Repetition in Protein Language Modelscited by 5
  22. 2021Understanding and Improving the Exemplar-based Generation for Open-domain Conversationcited by 3
  23. 2025States of LLM-generated Texts and Phase Transitions between themcited by 3
  24. 2025Geometry of Knowledge Allows Extending Diversity Boundaries of Large Language Modelscited by 3
  25. 2021Diversifying Neural Text Generation with Part-of-Speech Guided Softmax and Samplingcited by 2
  26. 2025Tokenized Bandit for LLM Decoding and Alignmentcited by 2
  27. 2025Efficient semantic uncertainty quantification in language models via diversity-steered samplingcited by 2
  28. 2024ConvKGYarn: Spinning Configurable and Scalable Conversational Knowledge Graph QA datasets with Large Language Modelscited by 1
  29. 2026Assessing the Impact of Typological Features on Multilingual Machine Translation in the Age of Large Language Modelscited by 1
  30. 2023Exploring the Impact of Human Evaluator Group on Chat-Oriented Dialogue Evaluationcited by 0
  31. 2025Multi-Hypothesis Distillation of Multilingual Neural Translation Models for Low-Resource Languagescited by 0
  32. 2026Construting Reverse Thinking: Developing Large Language Models' Reverse Thingking Abilitycited by 0