# Healing Unsafe Dialogue Responses with Weak Supervision Signals

arXiv: https://arxiv.org/abs/2305.15757 · HTML: https://mlsanity.com/paper/2305.15757/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 32 of its 50 references that are in the map.
- First posted on arXiv 25 May 2023.

## Builds on (most cited first, 30 of 32)

- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Neural Network Acceptability Judgments](https://mlsanity.com/paper/1805.12471/) (2018)
- [DialoGPT: Large-Scale Generative Pre-training for Conversational Response Generation](https://mlsanity.com/paper/1911.00536/) (2019)
- [BARTScore: Evaluating Generated Text as Text Generation](https://mlsanity.com/paper/2106.11520/) (2021)
- [Recipes for building an open-domain chatbot](https://mlsanity.com/paper/2004.13637/) (2020)
- [Improving alignment of dialogue agents via targeted human judgements](https://mlsanity.com/paper/2209.14375/) (2022)
- [A Simple Language Model for Task-Oriented Dialogue](https://mlsanity.com/paper/2005.00796/) (2020)
- [A New Generation of Perspective API: Efficient Multilingual Character-level Transformers](https://mlsanity.com/paper/2202.11176/) (2022)
- [Build it Break it Fix it for Dialogue Safety: Robustness from Adversarial Human Attack](https://mlsanity.com/paper/1908.06083/) (2019)
- [Dash: Semi-Supervised Learning with Dynamic Thresholding](https://mlsanity.com/paper/2109.00650/) (2021)
- [PLATO: Pre-trained Dialogue Generation Model with Discrete Latent Variable](https://mlsanity.com/paper/1910.07931/) (2019)
- [Multi-Task Pre-Training for Plug-and-Play Task-Oriented Dialogue System](https://mlsanity.com/paper/2109.14739/) (2021)
- [Semantically Conditioned LSTM-based Natural Language Generation for Spoken Dialogue Systems](https://mlsanity.com/paper/1508.01745/) (2015)
- [TripPy: A Triple Copy Strategy for Value Independent Neural Dialog State Tracking](https://mlsanity.com/paper/2005.02877/) (2020)
- [Recent Advances in Deep Learning Based Dialogue Systems: A Systematic Survey](https://mlsanity.com/paper/2105.04387/) (2021)
- [UBAR: Towards Fully End-to-End Task-Oriented Dialog Systems with GPT-2](https://mlsanity.com/paper/2012.03539/) (2020)
- [Hello, It's GPT-2 -- How Can I Help You? Towards the Use of Pretrained Language Models for Task-Oriented Dialogue Systems](https://mlsanity.com/paper/1907.05774/) (2019)
- [Towards Conversational Recommendation over Multi-Type Dialogs](https://mlsanity.com/paper/2005.03954/) (2020)
- [MinTL: Minimalist Transfer Learning for Task-Oriented Dialogue Systems](https://mlsanity.com/paper/2009.12005/) (2020)
- [Does Gender Matter? Towards Fairness in Dialogue Systems](https://mlsanity.com/paper/1910.10486/) (2019)
- [Few-shot Natural Language Generation for Task-Oriented Dialog](https://mlsanity.com/paper/2002.12328/) (2020)
- [Recent Advances and Challenges in Task-oriented Dialog System](https://mlsanity.com/paper/2003.07490/) (2020)
- [On the Safety of Conversational Models: Taxonomy, Dataset, and Benchmark](https://mlsanity.com/paper/2110.08466/) (2021)
- [SOLOIST: Building Task Bots at Scale with Transfer Learning and Machine Teaching](https://mlsanity.com/paper/2005.05298/) (2020)
- [Challenges for Toxic Comment Classification: An In-Depth Error Analysis](https://mlsanity.com/paper/1809.07572/) (2018)
- [Just Say No: Analyzing the Stance of Neural Dialogue Generation in Offensive Contexts](https://mlsanity.com/paper/2108.11830/) (2021)
- [Adding Chit-Chat to Enhance Task-Oriented Dialogues](https://mlsanity.com/paper/2010.12757/) (2020)
- [Mitigating Gender Bias for Neural Dialogue Generation with Adversarial Learning](https://mlsanity.com/paper/2009.13028/) (2020)
- [SaFeRDialogues: Taking Feedback Gracefully after Conversational Safety Failures](https://mlsanity.com/paper/2110.07518/) (2021)
- [Zero-Resource Knowledge-Grounded Dialogue Generation](https://mlsanity.com/paper/2008.12918/) (2020)

## Built on by (most cited first, 1 of 1)

- [From Pixels to Personas: Investigating and Modeling Self-Anthropomorphism in Human-Robot Dialogues](https://mlsanity.com/paper/2410.03870/) (2024)

## Abstract (arXiv)

Recent years have seen increasing concerns about the unsafe response generation of large-scale dialogue systems, where agents will learn offensive or biased behaviors from the real-world corpus. Some methods are proposed to address the above issue by detecting and replacing unsafe training examples in a pipeline style. Though effective, they suffer from a high annotation cost and adapt poorly to unseen scenarios as well as adversarial attacks. Besides, the neglect of providing safe responses (e.g. simply replacing with templates) will cause the information-missing problem of dialogues. To address these issues, we propose an unsupervised pseudo-label sampling method, TEMP, that can automatically assign potential safe responses. Specifically, our TEMP method groups responses into several clusters and samples multiple labels with an adaptively sharpened sampling strategy, inspired by the observation that unsafe samples in the clusters are usually few and distribute in the tail. Extensive experiments in chitchat and task-oriented dialogues show that our TEMP outperforms state-of-the-art models with weak supervision signals and obtains comparable results under unsupervised learning settings.