# Pneg: Prompt-based Negative Response Generation for Dialogue Response Selection Task

arXiv: https://arxiv.org/abs/2210.17238 · HTML: https://mlsanity.com/paper/2210.17238/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 31 of its 77 references that are in the map.
- First posted on arXiv 31 Oct 2022.

## Builds on (most cited first, 30 of 31)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Dense Passage Retrieval for Open-Domain Question Answering](https://mlsanity.com/paper/2004.04906/) (2020)
- [Rethinking the Role of Demonstrations: What Makes In-Context Learning Work?](https://mlsanity.com/paper/2202.12837/) (2022)
- [When Does Label Smoothing Help?](https://mlsanity.com/paper/1906.02629/) (2019)
- [Personalizing Dialogue Agents: I have a dog, do you have pets too?](https://mlsanity.com/paper/1801.07243/) (2018)
- [EDA: Easy Data Augmentation Techniques for Boosting Performance on Text Classification Tasks](https://mlsanity.com/paper/1901.11196/) (2019)
- [Generating Natural Language Adversarial Examples](https://mlsanity.com/paper/1804.07998/) (2018)
- [WANLI: Worker and AI Collaboration for Natural Language Inference Dataset Creation](https://mlsanity.com/paper/2201.05955/) (2022)
- [Want To Reduce Labeling Cost? GPT-3 Can Help](https://mlsanity.com/paper/2108.13487/) (2021)
- [Generating Datasets with Pretrained Language Models](https://mlsanity.com/paper/2104.07540/) (2021)
- [TransferTransfo: A Transfer Learning Approach for Neural Network Based Conversational Agents](https://mlsanity.com/paper/1901.08149/) (2019)
- [GPT3Mix: Leveraging Large-scale Language Models for Text Augmentation](https://mlsanity.com/paper/2104.08826/) (2021)
- [A Good Prompt Is Worth Millions of Parameters: Low-resource Prompt-based Learning for Vision-Language Models](https://mlsanity.com/paper/2110.08484/) (2021)
- [Explaining The Efficacy of Counterfactually Augmented Data](https://mlsanity.com/paper/2010.02114/) (2020)
- [Robustness to Spurious Correlations via Human Annotations](https://mlsanity.com/paper/2007.06661/) (2020)
- [Improving Dialog Evaluation with a Multi-reference Adversarial Dataset and Large Scale Pretraining](https://mlsanity.com/paper/2009.11321/) (2020)
- [Debiased Contrastive Learning of Unsupervised Sentence Representations](https://mlsanity.com/paper/2205.00656/) (2022)
- [Generating Fluent Adversarial Examples for Natural Languages](https://mlsanity.com/paper/2007.06174/) (2020)
- [Do Response Selection Models Really Know What's Next? Utterance Manipulation Strategies for Multi-turn Response Selection](https://mlsanity.com/paper/2009.04703/) (2020)
- [Uncertain Natural Language Inference](https://mlsanity.com/paper/1909.03042/) (2019)
- [Building a Role Specified Open-Domain Dialogue System Leveraging Large-Scale Language Models](https://mlsanity.com/paper/2205.00176/) (2022)
- [On the Calibration and Uncertainty of Neural Learning to Rank Models](https://mlsanity.com/paper/2101.04356/) (2021)
- [Synthesizing Adversarial Negative Responses for Robust Response Ranking and Evaluation](https://mlsanity.com/paper/2106.05894/) (2021)
- [A Sequential Matching Framework for Multi-turn Response Selection in Retrieval-based Chatbots](https://mlsanity.com/paper/1710.11344/) (2017)
- [Contextual Fine-to-Coarse Distillation for Coarse-grained Response Selection in Open-Domain Conversations](https://mlsanity.com/paper/2109.13087/) (2021)
- [Learning Matching Models with Weak Supervision for Response Selection in Retrieval-based Chatbots](https://mlsanity.com/paper/1805.02333/) (2018)

## Built on by (most cited first, 3 of 3)

- [PairEval: Open-domain Dialogue Evaluation with Pairwise Comparison](https://mlsanity.com/paper/2404.01015/) (2024)
- [Transformers Go for the LOLs: Generating (Humourous) Titles from Scientific Abstracts End-to-End](https://mlsanity.com/paper/2212.10522/) (2022)
- [DEnsity: Open-domain Dialogue Evaluation Metric using Density Estimation](https://mlsanity.com/paper/2305.04720/) (2023)

## Abstract (arXiv)

In retrieval-based dialogue systems, a response selection model acts as a ranker to select the most appropriate response among several candidates. However, such selection models tend to rely on context-response content similarity, which makes models vulnerable to adversarial responses that are semantically similar but not relevant to the dialogue context. Recent studies have shown that leveraging these adversarial responses as negative training samples is useful for improving the discriminating power of the selection model. Nevertheless, collecting human-written adversarial responses is expensive, and existing synthesizing methods often have limited scalability. To overcome these limitations, this paper proposes a simple but efficient method for generating adversarial negative responses leveraging a large-scale language model. Experimental results on dialogue selection tasks show that our method outperforms other methods of synthesizing adversarial negative responses. These results suggest that our method can be an effective alternative to human annotators in generating adversarial responses. Our dataset and generation code is available at https://github.com/leenw23/generating-negatives-by-gpt3.