# Towards Boosting the Open-Domain Chatbot with Human Feedback

arXiv: https://arxiv.org/abs/2208.14165 · HTML: https://mlsanity.com/paper/2208.14165/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Placed in Human values and AI feedback alignment, one of 10 directions in LLM alignment / RLHF / preference optimisation.
- Builds on 33 of its 43 references that are in the map.
- First posted on arXiv 30 Aug 2022.

## Placed in

- LLM alignment / RLHF / preference optimisation / [Human values and AI feedback alignment](https://mlsanity.com/alignment/human-values-and-ai-feedback-alignment/)

## Builds on (most cited first, 30 of 33)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [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)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [PaLM: Scaling Language Modeling with Pathways](https://mlsanity.com/paper/2204.02311/) (2022)
- [Overcoming catastrophic forgetting in neural networks](https://mlsanity.com/paper/1612.00796/) (2016)
- [Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2204.05862/) (2022)
- [WebGPT: Browser-assisted question-answering with human feedback](https://mlsanity.com/paper/2112.09332/) (2021)
- [LaMDA: Language Models for Dialog Applications](https://mlsanity.com/paper/2201.08239/) (2022)
- [A Diversity-Promoting Objective Function for Neural Conversation Models](https://mlsanity.com/paper/1510.03055/) (2015)
- [A General Language Assistant as a Laboratory for Alignment](https://mlsanity.com/paper/2112.00861/) (2021)
- [Personalizing Dialogue Agents: I have a dog, do you have pets too?](https://mlsanity.com/paper/1801.07243/) (2018)
- [Unified Language Model Pre-training for Natural Language Understanding and Generation](https://mlsanity.com/paper/1905.03197/) (2019)
- [DailyDialog: A Manually Labelled Multi-turn Dialogue Dataset](https://mlsanity.com/paper/1710.03957/) (2017)
- [Recipes for building an open-domain chatbot](https://mlsanity.com/paper/2004.13637/) (2020)
- [Wizard of Wikipedia: Knowledge-Powered Conversational agents](https://mlsanity.com/paper/1811.01241/) (2018)
- [Towards a Human-like Open-Domain Chatbot](https://mlsanity.com/paper/2001.09977/) (2020)
- [How NOT To Evaluate Your Dialogue System: An Empirical Study of Unsupervised Evaluation Metrics for Dialogue Response Generation](https://mlsanity.com/paper/1603.08023/) (2016)
- [The Design and Implementation of XiaoIce, an Empathetic Social Chatbot](https://mlsanity.com/paper/1812.08989/) (2018)
- [Can You Put it All Together: Evaluating Conversational Agents' Ability to Blend Skills](https://mlsanity.com/paper/2004.08449/) (2020)
- [Learning from Dialogue after Deployment: Feed Yourself, Chatbot!](https://mlsanity.com/paper/1901.05415/) (2019)
- [Human-centric Dialog Training via Offline Reinforcement Learning](https://mlsanity.com/paper/2010.05848/) (2020)
- [Anticipating Safety Issues in E2E Conversational AI: Framework and Tooling](https://mlsanity.com/paper/2107.03451/) (2021)
- [A Large-Scale Chinese Short-Text Conversation Dataset](https://mlsanity.com/paper/2008.03946/) (2020)
- [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)
- [PLATO-XL: Exploring the Large-scale Pre-training of Dialogue Generation](https://mlsanity.com/paper/2109.09519/) (2021)
- [Learning New Skills after Deployment: Improving open-domain internet-driven dialogue with human feedback](https://mlsanity.com/paper/2208.03270/) (2022)
- [Towards Coherent and Engaging Spoken Dialog Response Generation Using Automatic Conversation Evaluators](https://mlsanity.com/paper/1904.13015/) (2019)
- [EVA: An Open-Domain Chinese Dialogue System with Large-Scale Generative Pre-Training](https://mlsanity.com/paper/2108.01547/) (2021)
- [EVA2.0: Investigating Open-Domain Chinese Dialogue Systems with Large-Scale Pre-Training](https://mlsanity.com/paper/2203.09313/) (2022)

## Built on by (most cited first, 11 of 11)

- [Personalisation within bounds: A risk taxonomy and policy framework for the alignment of large language models with personalised feedback](https://mlsanity.com/paper/2303.05453/) (2023)
- [Compression Represents Intelligence Linearly](https://mlsanity.com/paper/2404.09937/) (2024)
- [The Past, Present and Better Future of Feedback Learning in Large Language Models for Subjective Human Preferences and Values](https://mlsanity.com/paper/2310.07629/) (2023)
- [Position: Towards Bidirectional Human-AI Alignment](https://mlsanity.com/paper/2406.09264/) (2024)
- [Dynamic Stochastic Decoding Strategy for Open-Domain Dialogue Generation](https://mlsanity.com/paper/2406.07850/) (2024)
- [GLM-Dialog: Noise-tolerant Pre-training for Knowledge-grounded Dialogue Generation](https://mlsanity.com/paper/2302.14401/) (2023)
- [The Empty Signifier Problem: Towards Clearer Paradigms for Operationalising "Alignment" in Large Language Models](https://mlsanity.com/paper/2310.02457/) (2023)
- [UniRetriever: Multi-task Candidates Selection for Various Context-Adaptive Conversational Retrieval](https://mlsanity.com/paper/2402.16261/) (2024)
- [InFact: Informativeness Alignment for Improved LLM Factuality](https://mlsanity.com/paper/2505.20487/) (2025)
- [PLATO-K: Internal and External Knowledge Enhanced Dialogue Generation](https://mlsanity.com/paper/2211.00910/) (2022)
- [Learning to love diligent trolls: Accounting for rater effects in the dialogue safety task](https://mlsanity.com/paper/2310.19271/) (2023)

## Abstract (arXiv)

Many open-domain dialogue models pre-trained with social media comments can generate coherent replies but have difficulties producing engaging responses when interacting with real users. This phenomenon might mainly result from the deficiency of annotated human-human conversations and the misalignment with human preference. In this paper, we propose a novel and efficient approach Diamante to boost the open-domain chatbot, where two kinds of human feedback (including explicit demonstration and implicit preference) are collected and leveraged. By asking annotators to select or amend the model-generated candidate responses, Diamante efficiently collects the human demonstrated responses and constructs a Chinese chit-chat dataset. To enhance the alignment with human preference, Diamante leverages the implicit preference in the data collection process and introduces the generation-evaluation joint training. Comprehensive experiments indicate that the Diamante dataset and joint training paradigm can significantly boost the performance of Chinese pre-trained dialogue models.