Personalized dialogue generation aims to leverage persona profiles and dialogue history to generate persona-relevant and consistent responses. Mainstream models typically rely on token-level language model training with persona dialogue data, such as Next Token Prediction, to implicitly achieve personalization, making these methods tend to neglect the given personas and generate generic responses. To address this issue, we propose a novel Persona-Aware Alignment Framework (PAL), which directly treats persona alignment as the training objective of dialogue generation. Specifically, PAL employs a two-stage training method including Persona-aware Learning and Persona Alignment, equipped with an easy-to-use inference strategy Select then Generate, to improve persona sensitivity and generate more persona-relevant responses at the semantics level. Through extensive experiments, we demonstrate that our framework outperforms many state-of-the-art personalized dialogue methods and large language models.
"In Dialogues We Learn": Towards Personalized Dialogue Without Pre-defined Profiles through In-Dialogue Learning
Gaoling School of Artificial Intelligence, Renmin University of China（中国人民大学高瓴人工智能学院）；Ant Group（蚂蚁集团）；University of Electronic Science and Technology of China（电子科技大学）；Kunming University of Science and Technology（昆明理工大学）
When Personalization Misleads: Understanding and Mitigating Hallucinations in Personalized LLMs
Gaoling School of Artificial Intelligence, Renmin University of China（中国人民大学首都人工智能学院）；AI Lab at Lenovo Research（联想研究院人工智能实验室）；School of Artificial Intelligence and Data Science, University of International Business and Economics（国际商务与经济大学人工智能与数据科学学院）
From Persona to Person: Enhancing the Naturalness with Multiple Discourse Relations Graph Learning in Personalized Dialogue Generation
Department of Computer Science（计算机科学系）；Information Engineering, National Cheng Kung University, Taiwan（信息工程系，国立云林科技大学，台湾）；Department of Computer Science, National Tsing Hua University, Taiwan（计算机科学系，国立清华大学，台湾）
Tsinghua University（清华大学）；Samsung Research China - Beijing (SRC-B)（三星中国研究院-北京（SRC-B））；NetEase Inc.（网易公司）
Endowing dialogue systems with personas is essential to deliver more human-like conversations. However, this problem is still far from well explored due to the difficulties of both embodying personalities in natural languages and the persona sparsity issue observed in most dialogue corpora. This paper proposes a pre-training based personalized dialogue model that can generate coherent responses using persona-sparse dialogue data. In this method, a pre-trained language model is used to initialize an encoder and decoder, and personal attribute embeddings are devised to model richer dialogue cont…
A Personalized Conversational Benchmark: Towards Simulating Personalized Conversations
University of Southern California（南加州大学）；Adobe Research（Adobe研究院）；University of California, San Diego（加州大学圣地亚哥分校）；Intel AI Research（英特尔人工智能研究）；University of Maryland, College Park（马里兰大学学院市分校）；Vanderbilt University（范德比大学）；Virginia Polytechnic Institute and State University（弗吉尼亚理工学院和州立大学）；University of Notre Dame（诺特丹大学）；University of Oregon（俄勒冈大学）；University of Illinois Chicago（伊利诺伊大学芝加哥分校）；Arizona State University（亚利桑那州立大学）
Large Language Models Empowered Personalized Web Agents
National University of Singapore（新加坡国立大学）；The Hong Kong Polytechnic University（香港理工大学）；University of Science and Technology of China（中国科学技术大学）；Eastern Institute of Technology（宁波东方理工大学）
MORPHEUS: Modeling Role from Personalized Dialogue History by Exploring and Utilizing Latent Space
School of New Media and Communication, Tianjin University（天津大学新媒体与传播学院）；College of Intelligence and Computing, Tianjin University（天津大学智能与计算学部）；AI Lab, China Mobile Communication Group Tianjin Co., Ltd.（中国移动通信集团天津有限公司AI实验室）
ReGraP-LLaVA: Reasoning enabled Graph-based Personalized Large Language and Vision Assistant
Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences（中国科学院深圳先进技术研究所）；School of Engineering, Westlake University（西湖大学工程学院）；University of Minnesota – Twin Cities（明尼苏达大学双城分校）；University of Toronto（多伦多大学）
The generation of personalized dialogue is vital to natural and human-like conversation. Typically, personalized dialogue generation models involve conditioning the generated response on the dialogue history and a representation of the persona/personality of the interlocutor. As it is impractical to obtain the persona/personality representations for every interlocutor, recent works have explored the possibility of generating personalized dialogue by finetuning the model with dialogue examples corresponding to a given persona instead. However, in real-world implementations, a sufficient number …
Hong Kong University of Science and Technology（香港科技大学）
Training a personalized dialogue system requires a lot of data, and the data collected for a single user is usually insufficient. One common practice for this problem is to share training dialogues between different users and train multiple sequence-to-sequence dialogue models together with transfer learning. However, current sequence-to-sequence transfer learning models operate on the entire sentence, which might cause negative transfer if different personal information from different users is mixed up. We propose a personalized decoder model to transfer finer granularity phrase-level knowled…
Renmin University of China（中国人民大学）；University of Montreal（蒙特利尔大学）
Personalized dialogue systems explore the problem of generating responses that are consistent with the user's personality, which has raised much attention in recent years. Existing personalized dialogue systems have tried to extract user profiles from dialogue history to guide personalized response generation. Since the dialogue history is usually long and noisy, most existing methods truncate the dialogue history to model the user's personality. Such methods can generate some personalized responses, but a large part of dialogue history is wasted, leading to sub-optimal performance of personal…
With the flourish of services on the Internet, a prerequisite for service providers to precisely deliver services to their customers is to capture user requirements comprehensively, accurately, and efficiently. This is called the ``Service Requirement Elicitation (SRE)'' task. Considering the amount of customers is huge, it is an inefficient way for service providers to interact with each user by face-to-face dialog. Therefore, to elicit user requirements with the assistance of virtual intelligent assistants has become a mainstream way. Since user requirements generally consist of different le…
Center for Artificial Intelligence Research (CAiRE)（人工智能研究中心（CAiRE））；The Hong Kong University of Science and Technology（香港科技大学）
Existing personalized dialogue models use human designed persona descriptions to improve dialogue consistency. Collecting such descriptions from existing dialogues is expensive and requires hand-crafted feature designs. In this paper, we propose to extend Model-Agnostic Meta-Learning (MAML)(Finn et al., 2017) to personalized dialogue learning without using any persona descriptions. Our model learns to quickly adapt to new personas by leveraging only a few dialogue samples collected from the same user, which is fundamentally different from conditioning the response on the persona descriptions. …
Nanyang Technological University（南洋理工大学）；Institute for Infocomm Research A*STAR（新加坡科技研究局资讯通信研究院）
Conventional approaches to personalized dialogue generation typically require a large corpus, as well as predefined persona information. However, in a real-world setting, neither a large corpus of training data nor persona information are readily available. To address these practical limitations, we propose a novel multi-task meta-learning approach which involves training a model to adapt to new personas without relying on a large corpus, or on any predefined persona information. Instead, the model is tasked with generating personalized responses based on only the dialogue context. Unlike prio…
Gaoling School of Artificial Intelligence, Renmin University of China（中国人民大学高瓴人工智能学院）；School of Information, Renmin University of China（中国人民大学信息学院）；Université de Montréal（蒙特利尔大学）
Natural language dialogue systems raise great attention recently. As many dialogue models are data-driven, high-quality datasets are essential to these systems. In this paper, we introduce Pchatbot, a large-scale dialogue dataset that contains two subsets collected from Weibo and Judicial forums respectively. To adapt the raw dataset to dialogue systems, we elaborately normalize the raw dataset via processes such as anonymization, deduplication, segmentation, and filtering. The scale of Pchatbot is significantly larger than existing Chinese datasets, which might benefit the data-driven models.…
University of California, Santa Barbara（加州大学圣塔芭芭拉分校）；Tencent（腾讯）；Carnegie Mellon University（卡内基梅隆大学）
Neural conversational models have long suffered from the problem of inconsistency and lacking coherent personality. To address the issue, persona-based models capturing individual characteristics have been proposed, but they still face the dilemma of model adaption and data privacy. To break this dilemma, we propose a novel Federated Natural Language Generation (FedNLG) framework, which learns personalized representations from various dataset on distributed devices, and thus implements the personalized dialogue system efficiently and safely. FedNLG first pre-trains parameters of standard neura…
Maintaining consistent personas is essential for dialogue agents. Although tremendous advancements have been brought, the limited-scale of annotated persona-dense data are still barriers towards training robust and consistent persona-based dialogue models. In this work, we show how the challenges can be addressed by disentangling persona-based dialogue generation into two sub-tasks with a novel BERT-over-BERT (BoB) model. Specifically, the model consists of a BERT-based encoder and two BERT-based decoders, where one decoder is for response generation, and another is for consistency understandi…
The Hong Kong University of Science and Technology（香港科技大学）
It is difficult to train a personalized task-oriented dialogue system because the data collected from each individual is often insufficient. Personalized dialogue systems trained on a small dataset can overfit and make it difficult to adapt to different user needs. One way to solve this problem is to consider a collection of multiple users' data as a source domain and an individual user's data as a target domain, and to perform a transfer learning from the source to the target domain. By following this idea, we propose "PETAL"(PErsonalized Task-oriented diALogue), a transfer-learning framework…
Research Center for Social Computing and Information Retrieval（社会计算与信息检索研究中心）；Harbin Institute of Technology（哈尔滨工业大学）
Consistency is one of the major challenges faced by dialogue agents. A human-like dialogue agent should not only respond naturally, but also maintain a consistent persona. In this paper, we exploit the advantages of natural language inference (NLI) technique to address the issue of generating persona consistent dialogues. Different from existing work that re-ranks the retrieved responses through an NLI model, we cast the task as a reinforcement learning problem and propose to exploit the NLI signals from response-persona pairs as rewards for the process of dialogue generation. Specifically, ou…
The University of Sydney（悉尼大学）；Tencent AI Lab（腾讯人工智能实验室）；Eindhoven University of Technology（埃因霍温理工大学）；JD Explore Academy（京东探索研究院）
Towards building intelligent dialogue agents, there has been a growing interest in introducing explicit personas in generation models. However, with limited persona-based dialogue data at hand, it may be difficult to train a dialogue generation model well. We point out that the data challenges of this generation task lie in two aspects: first, it is expensive to scale up current persona-based dialogue datasets; second, each data sample in this task is more complex to learn with than conventional dialogue data. To alleviate the above data issues, we propose a data manipulation method, which is …
University of Maryland, Baltimore County（马里兰大学巴尔的摩县分校）
In this paper, we present a study on personalized emphasis framing which can be used to tailor the content of a message to enhance its appeal to different individuals. With this framework, we directly model content selection decisions based on a set of psychologically-motivated domain-independent personal traits including personality (e.g., extraversion and conscientiousness) and basic human values (e.g., self-transcendence and hedonism). We also demonstrate how the analysis results can be used in automated personalized content selection for persuasive message generation.
Dialogue systems without consistent responses are not fascinating. In this study, we build a dialogue system that can respond based on a given character setting (persona) to bring consistency. Considering the trend of the rapidly increasing scale of language models, we propose an approach that uses prompt-tuning, which has low learning costs, on pre-trained large-scale language models. The results of automatic and manual evaluations in English and Japanese show that it is possible to build a dialogue system with more natural and personalized responses using less computational resources than fi…
MIRACLE: Towards Personalized Dialogue Generation with Latent-Space Multiple Personal Attribute Control
Huazhong University of Science and Technology（华中科技大学）；Ping An Property & Casualty Insurance Company of China, Ltd.（中国平安财产保险股份有限公司）；Beijing Institute of Technology（北京理工大学）；Brilliance Technology Co. Ltd.（华晨科技股份有限公司）
Maintaining engagement and consistency is particularly important in dialogue systems. Existing works have improved the performance of dialogue systems by intentionally learning interlocutor personas with sophisticated network structures. One issue with this approach is that it requires more personal corpora with annotations. Additionally, these models typically perform the next utterance prediction to generate a response but neglect the discourse coherence in the entire conversation. To address these issues, this study proposes a method of learning to memorize entailment and discourse relation…
