# Do Response Selection Models Really Know What's Next? Utterance Manipulation Strategies for Multi-turn Response Selection

arXiv: https://arxiv.org/abs/2009.04703 · HTML: https://mlsanity.com/paper/2009.04703/

## Key facts

- Cited by 36 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 10 Sep 2020.

## Built on by (most cited first, 30 of 36)

- [MMDialog: A Large-scale Multi-turn Dialogue Dataset Towards Multi-modal Open-domain Conversation](https://mlsanity.com/paper/2211.05719/) (2022)
- [InstructDial: Improving Zero and Few-shot Generalization in Dialogue through Instruction Tuning](https://mlsanity.com/paper/2205.12673/) (2022)
- [Self-supervised Dialogue Learning for Spoken Conversational Question Answering](https://mlsanity.com/paper/2106.02182/) (2021)
- [Structural Pre-training for Dialogue Comprehension](https://mlsanity.com/paper/2105.10956/) (2021)
- [Synthesizing Adversarial Negative Responses for Robust Response Ranking and Evaluation](https://mlsanity.com/paper/2106.05894/) (2021)
- [Dialogue History Matters! Personalized Response Selectionin Multi-turn Retrieval-based Chatbots](https://mlsanity.com/paper/2103.09534/) (2021)
- [Task Compass: Scaling Multi-task Pre-training with Task Prefix](https://mlsanity.com/paper/2210.06277/) (2022)
- [Advances in Multi-turn Dialogue Comprehension: A Survey](https://mlsanity.com/paper/2103.03125/) (2021)
- [Exploring Dense Retrieval for Dialogue Response Selection](https://mlsanity.com/paper/2110.06612/) (2021)
- [Less is More: Mitigate Spurious Correlations for Open-Domain Dialogue Response Generation Models by Causal Discovery](https://mlsanity.com/paper/2303.01962/) (2023)
- [Dialogue-oriented Pre-training](https://mlsanity.com/paper/2106.00420/) (2021)
- [Contextual Fine-to-Coarse Distillation for Coarse-grained Response Selection in Open-Domain Conversations](https://mlsanity.com/paper/2109.13087/) (2021)
- [P5: Plug-and-Play Persona Prompting for Personalized Response Selection](https://mlsanity.com/paper/2310.06390/) (2023)
- [Multi-Stage Pre-training Enhanced by ChatGPT for Multi-Scenario Multi-Domain Dialogue Summarization](https://mlsanity.com/paper/2310.10285/) (2023)
- [Netmarble AI Center's WMT21 Automatic Post-Editing Shared Task Submission](https://mlsanity.com/paper/2109.06515/) (2021)
- [Small Changes Make Big Differences: Improving Multi-turn Response Selection in Dialogue Systems via Fine-Grained Contrastive Learning](https://mlsanity.com/paper/2111.10154/) (2021)
- [A Systematic Evaluation of Response Selection for Open Domain Dialogue](https://mlsanity.com/paper/2208.04379/) (2022)
- [A Transformer-based Response Evaluator for Open-Domain Spoken Conversation](https://mlsanity.com/paper/2302.04424/) (2023)
- [Challenging Instances are Worth Learning: Generating Valuable Negative Samples for Response Selection Training](https://mlsanity.com/paper/2109.06538/) (2021)
- [Pneg: Prompt-based Negative Response Generation for Dialogue Response Selection Task](https://mlsanity.com/paper/2210.17238/) (2022)
- [Uni-Encoder: A Fast and Accurate Response Selection Paradigm for Generation-Based Dialogue Systems](https://mlsanity.com/paper/2106.01263/) (2021)
- [Two-Level Supervised Contrastive Learning for Response Selection in Multi-Turn Dialogue](https://mlsanity.com/paper/2203.00793/) (2022)
- [Dial-MAE: ConTextual Masked Auto-Encoder for Retrieval-based Dialogue Systems](https://mlsanity.com/paper/2306.04357/) (2023)
- [An Evaluation Dataset and Strategy for Building Robust Multi-turn Response Selection Model](https://mlsanity.com/paper/2109.04834/) (2021)
- [CORAL: Contextual Response Retrievability Loss Function for Training Dialog Generation Models](https://mlsanity.com/paper/2205.10558/) (2022)
- [Learning Locality and Isotropy in Dialogue Modeling](https://mlsanity.com/paper/2205.14583/) (2022)
- [Tri-Attention: Explicit Context-Aware Attention Mechanism for Natural Language Processing](https://mlsanity.com/paper/2211.02899/) (2022)
- [Improve Retrieval-based Dialogue System via Syntax-Informed Attention](https://mlsanity.com/paper/2303.06605/) (2023)
- [Chat-Ghosting: A Comparative Study of Methods for Auto-Completion in Dialog Systems](https://mlsanity.com/paper/2507.05940/) (2025)
- [Advances in Multi-turn Dialogue Comprehension: A Survey](https://mlsanity.com/paper/2110.04984/) (2021)

## Abstract (arXiv)

In this paper, we study the task of selecting the optimal response given a user and system utterance history in retrieval-based multi-turn dialog systems. Recently, pre-trained language models (e.g., BERT, RoBERTa, and ELECTRA) showed significant improvements in various natural language processing tasks. This and similar response selection tasks can also be solved using such language models by formulating the tasks as dialog--response binary classification tasks. Although existing works using this approach successfully obtained state-of-the-art results, we observe that language models trained in this manner tend to make predictions based on the relatedness of history and candidates, ignoring the sequential nature of multi-turn dialog systems. This suggests that the response selection task alone is insufficient for learning temporal dependencies between utterances. To this end, we propose utterance manipulation strategies (UMS) to address this problem. Specifically, UMS consist of several strategies (i.e., insertion, deletion, and search), which aid the response selection model towards maintaining dialog coherence. Further, UMS are self-supervised methods that do not require additional annotation and thus can be easily incorporated into existing approaches. Extensive evaluation across multiple languages and models shows that UMS are highly effective in teaching dialog consistency, which leads to models pushing the state-of-the-art with significant margins on multiple public benchmark datasets.