论文检索

Ali Köksal, Jingjing Gu, Kotaro Hara, Jing Jiang, Joo-Hwee Lim, Qianli Xu

We present SPASCA - a conversational AI system that promotes psychological and cognitive well-being of persons living with dementia (PLWD). This system features an AI agent that provides social presence and support to PLWD through verbal communications, without physical presence of human caregivers. The system integrates (1) a novel dialogue model that generates dialogue items relevant to the user's experiences and lifestyle, (2) a digital avatar in the form of a talking head with the identity of a caregiver who is familiar to the demented user. We develop prototypes that adopt various interaction modalities and conversational styles and report the pros and cons of different system configurations through expert review. Our system shows the potential of conversational AI for personalized and affordable healthcare services.

Rong-Ching Chang, Hao-Chuan Wang

The increasing adoption of conversational agents powered by large language models (LLMs) raises questions about its effects across culturally diverse interactions. While these agents are linguistically versatile and multilingual, their ability to adapt along cultural dimensions--defined as geographically and communally nurtured sets of values and behavioral norms--lacks close scrutiny of both their design and deployment. To achieve inclusive conversational AI, it is essential to understand how agents adapt to users from diverse cultural backgrounds. In this study, we analyze dialogues between human users from different countries and LLM-powered agents to examine how both parties adapt their word use, a salient aspect of linguistic styles, toward one another throughout casual conversations. Our analysis reveals that LLMs exhibit varying degrees of style matching based on users' national cultures and demonstrate asymmetric adaptation when interacting with culturally diverse users. Moreover, we observe a reciprocal dynamic where both the LLMs and users from certain cultures adjust their styles in response to one another. Additionally, our findings support the hypothesis that LLMs and users naturally converge in conversational styles over the course of interactions, mirroring the dynamics of human conversations that accommodate and converge. To develop localized and culturally aware agents, there's a potential to utilize such cross-cultural convergence process during fine-tuning to align LLMs.

Tianlong Xu, YiFan Zhang, Zhendong Chu, Shen Wang, Qingsong Wen

Students frequently make mistakes while solving mathematical problems, and traditional error correction methods are both time-consuming and labor-intensive. This paper introduces an innovative Virtual AI Teacher system designed to autonomously analyze and correct student Errors (VATE). Leveraging advanced large language models (LLMs) like GPT-4, the system uses student drafts as a primary source for error analysis, which enhances understanding of the student's learning process. It incorporates sophisticated prompt engineering and maintains an error pool to reduce computational overhead. The AI-driven system also features a real-time dialogue component for efficient student interaction. Our approach demonstrates significant advantages over traditional and machine learning-based error correction methods, including reduced educational costs, high scalability, and superior generalizability. The system has been deployed in Squirrel AI's learning platform for elementary mathematics education, where it achieves 78.3% accuracy in error analysis and shows a marked improvement in student learning efficiency. Satisfaction surveys indicate a strong positive reception, highlighting the system's potential to transform educational practices.

Jiayi Zhou, Jiaming Ji, Josef Dai, Yaodong Yang

Aligning the behavior of Large language models (LLMs) with human intentions and values remains a critical challenge. Reinforcement learning from human feedback (RLHF) aligns LLMs by training a reward model (RM) on human preferences and fine-tuning the LLMs to maximize RM feedback. Despite its effectiveness and popularity, RLHF is prone to biased local optimization. It means RM fails to provide feedback that accurately aligns with human preference, causing LLMs to explore unexpected generalizations, and failing to achieve alignment objectives. To mitigate this issue, we propose a novel sequence-to-sequence (seq2seq) reward modeling method. Its key insight is that learning from language feedback rather than scalar feedback improves RLHF without additional annotations. We replaced the reward modeling target from binary maximum likelihood estimation (MLE) with sequence MLE. This method enables richer and fine-grained language feedback without additional annotations, models, or training stages. Our experiments demonstrated its effectiveness, specifically, reducing the refusal-to-response paradigm in single-turn safety dialogues and the long-response bias in text summarization tasks. We provide further analysis that seq2seq RM improves RLHF performance across 2B and 7B LLMs on 3 NLP tasks, achieving an average win rate of 76.9%. We further show that seq2seq RM can still improve the performance of RLHF under out-of-distribution prompts.

Lin Ling, Fazle Rabbi, Song Wang, Jinqiu Yang

Large language models (LLMs) have significantly advanced the field of automated code generation. However, a notable research gap exists in evaluating social biases that may be present in the code produced by LLMs. To solve this issue, we propose a novel fairness framework, i.e., Solar, to assess and mitigate the social biases of LLM-generated code. Specifically, Solar can automatically generate test cases for quantitatively uncovering social biases of the auto-generated code by LLMs. To quantify the severity of social biases in generated code, we develop a dataset that covers a diverse set of social problems. We applied Solar and the crafted dataset to four state-of-the-art LLMs for code generation. Our evaluation reveals severe bias in the LLM-generated code from all the subject LLMs. Furthermore, we explore several prompting strategies for mitigating bias, including Chain-of-Thought (CoT) prompting, combining positive role-playing with CoT prompting and dialogue with Solar. Our experiments show that dialogue with Solar can effectively reduce social bias in LLM-generated code by up to 90%. Last, we make the code and data publicly available is highly extensible to evaluate new social problems.

Jinfeng Zhou, Yongkang Huang, Bosi Wen, Guanqun Bi, Yuxuan Chen, Pei Ke, Zhuang Chen, Xiyao Xiao, Libiao Peng, Kuntian Tang 等

Character-based dialogue (aka role-playing) enables users to freely customize characters for interaction, which often relies on LLMs, raising the need to evaluate LLMs’ character customization capability. However, existing benchmarks fail to ensure a robust evaluation as they often only involve a single character category or evaluate limited dimensions. Moreover, the sparsity of character features in responses makes feature-focused generative evaluation both ineffective and inefficient. To address these issues, we propose CharacterBench, the largest bilingual generative benchmark, with 22,859 human-annotated samples covering 3,956 characters from 25 detailed character categories. We define 11 dimensions of 6 aspects, classified as sparse and dense dimensions based on whether character features evaluated by specific dimensions manifest in each response. We enable effective and efficient evaluation by crafting tailored queries for each dimension to induce characters’ responses related to specific dimensions. Further, we develop CharacterJudge model for cost-effective and stable evaluations. Experiments show its superiority over SOTA automatic judges (e.g., GPT-4) and our benchmark’s potential to optimize LLMs’ character customization.

Lulu Zhao, Weihao Zeng, Xiaofeng Shi, Hua Zhou

Recently, both closed-source and open-source LLMs have made significant strides, outperforming humans in various general domains. However, their performance in specific professional domains such as medicine, especially within the open-source community, remains suboptimal due to the complexity of medical knowledge. In this paper, we propose CareBot, a bilingual medical LLM, which leverages a comprehensive approach integrating continuous pre-training (CPT), supervised fine-tuning (SFT), and reinforcement learning with human feedback (RLHF). Our novel two-stage CPT method, comprising Stable CPT and Boost CPT, effectively bridges the gap between general and domain-specific data, facilitating a smooth transition from pre-training to fine-tuning and enhancing domain knowledge progressively. We also introduce DataRater, a model designed to assess data quality during CPT, ensuring that the training data is both accurate and relevant. For SFT, we develope a large and diverse bilingual dataset, along with ConFilter, a metric to enhance multi-turn dialogue quality, which is crucial to improving the model's ability to handle more complex dialogues. The combination of high-quality data sources and innovative techniques significantly improves CareBot's performance across a range of medical applications. Our rigorous evaluations on Chinese and English benchmarks confirm CareBot's effectiveness in medical consultation and education. These advancements not only address current limitations in medical LLMs but also set a new standard for developing effective and reliable open-source models in the medical domain.

Dingbo Yuan, Yipeng Chen, Guodong Liu, Chenchen Li, Chengfu Tang, Dongxu Zhang, Zhenkui Wang, Xudong Wang, Song Liu

Recent years have witnessed a profound evolution in the abilities of Large Language Model, which has significantly boosted the proliferation of role-playing agents and platforms. Nonetheless, there is a conspicuous absence of systematic and comprehensive evaluations of role-playing abilities which are truly aligned with users' interaction scenarios in real-world. To address this gap, we have devised DMT-RoleBench, a benchmark designed to evaluate the role-playing abilities of large language models and agents based on dynamic multi-turn dialogues. Compared with existed role-playing benchmarks, DMT-RoleBench boasts several principal advantages: (1) It contains a more diverse role types and system prompts of different formats. (2) We propose an innovative evaluation paradigm to assess role-playing abilities based on dynamically generating multi-turn dialogues constrained by specific evaluation intents and topics, which is well aligned with users' interaction scenarios in real-world. (3) We define a three-tiered metric system and provide DMT-RM, which is a reward model aligned with human annotations, to annotate the dialogues. And we propose DMT-Score to calculate the final scores based on the annotated dialogues. Our experiments and analysis of leading models equipped with role-playing abilities have demonstrated the effectiveness of DMT-RoleBench.

Yujing Wang, Hainan Zhang, Liang Pang, Binghui Guo, Hongwei Zheng, Zhiming Zheng

In a real-world RAG system, the current query often involves spoken ellipses and ambiguous references from dialogue contexts, necessitating query rewriting to better describe user's information needs. However, traditional context-based rewriting has minimal enhancement on downstream generation tasks due to the lengthy process from query rewriting to response generation. Some researchers try to utilize reinforcement learning with generation feedback to assist the rewriter, but this sparse rewards provide little guidance in most cases, leading to unstable training and generation results.We find that user's needs are also reflected in the gold documents, retrieved documents and ground-truth. Therefore, by feeding back these multi-aspect dense rewards to query rewriting, more stable and satisfactory responses can be achieved. In this paper, we propose a novel query rewriting method MaFeRw, which improves RAG performance by integrating multi-aspect feedback from both the retrieval process and generated results. Specifically, we first use manual data to train a T5 model for the rewriter initialization. Next, we design three metrics as reinforcement learning feedback: the similarity between the rewritten query and the gold document, the ranking metrics, and ROUGE between the generation and the ground truth. Inspired by RLAIF, we train three kinds of reward models for the above metrics to achieve more efficient training. Finally, we combine the scores of these reward models as feedback, and use PPO algorithm to explore the optimal query rewriting strategy.Experimental results on two conversational RAG datasets demonstrate that MaFeRw achieves superior generation metrics and more stable training compared to baselines.

Yueqian Wang, Xiaojun Meng, Yuxuan Wang, Jianxin Liang, Qun Liu, Dongyan Zhao

Multi-modal multi-party conversation (MMC) is a less studied yet important topic of research due to that it well fits real-world scenarios and thus potentially has more widely-used applications. Compared with the traditional multi-modal conversations, MMC requires stronger character-centered understanding abilities as there are many interlocutors appearing in both the visual and textual context. To facilitate the study of this problem, we present Friends-MMC in this paper, an MMC dataset that contains 24,000+ unique utterances paired with video context. To explore the character-centered understanding of the dialogue, we also annotate the speaker of each utterance, the names and bounding bboxes of faces that appear in the video. Based on this Friends-MMC dataset, we further study two fundamental MMC tasks: conversation speaker identification and conversation response prediction, both of which have the multi-party nature with the video or image as visual context. For conversation speaker identification, we demonstrate the inefficiencies of existing methods such as pre-trained models, and propose a simple yet effective baseline method that leverages an optimization solver to utilize the context of two modalities to achieve better performance. For conversation response prediction, we fine-tune generative dialogue models on Friend-MMC, and analyze the benefits of speaker information. The code and dataset will be publicly available, and thus we call for more attention on modelling speaker information when understanding conversations.

Jieyi Wang, Yue Huang, Zeming Liu, Dexuan Xu, Chuan Wang, Xiaoming Shi, Ruiyuan Guan, Hongxing Wang, Weihua Yue, Yu Huang

Online psychological counseling dialogue systems are trending, offering a convenient and accessible alternative to traditional in-person therapy. However, existing psychological counseling dialogue systems mainly focus on basic empathetic dialogue or QA with minimal professional knowledge and without goal guidance. In many real-world counseling scenarios, clients often seek multi-type help, such as diagnosis, consultation, therapy, console, and common questions, but existing dialogue systems struggle to combine different dialogue types naturally. In this paper, we identify this challenge as how to construct mixed-type dialogue systems for psychological counseling that enable clients to clarify their goals before proceeding with counseling. To mitigate the challenge, we collect a mixed-type counseling dialogues corpus termed STAMPsy, covering five dialogue types, task-oriented dialogue for diagnosis, knowledge-grounded dialogue, conversational recommendation, empathetic dialogue, and question answering, over 5,000 conversations. Moreover, spatiotemporal-aware knowledge enables systems to have world awareness and has been proven to affect one's mental health. Therefore, we link dialogues in STAMPsy to spatiotemporal state and propose a spatiotemporal-aware mixed-type psychological counseling dataset. Additionally, we build baselines on STAMPsy and develop an iterative self-feedback psychological dialogue generation framework, named Self-STAMPsy. Results indicate that clarifying dialogue goals in advance and utilizing spatiotemporal states are effective.

Pratik Rakesh Singh, Mohammadi Zaki, Pankaj Wasnik

We address the challenging task of neural machine translation (NMT) in the entertainment domain, where the objective is to automatically translate a given dialogue from a source language content to a target language. This task has various applications, particularly in automatic dubbing, subtitling, and other content localization tasks, enabling source content to reach a wider audience. Traditional NMT systems typically translate individual sentences in isolation, without facilitating knowledge transfer of crucial elements such as the context and style from previously encountered sentences. In this work, we emphasize the significance of these fundamental aspects in producing pertinent and captivating translations. We demonstrate their significance through several examples and propose a novel framework for entertainment translation, which, to our knowledge, is the first of its kind. Furthermore, we introduce an algorithm to estimate the context and style of the current session and use these estimations to generate a prompt that guides a Large Language Model (LLM) to generate high-quality translations. Our method is both language and LLM-agnostic, making it a general-purpose tool. We demonstrate the effectiveness of our algorithm through various numerical studies and observe significant improvement in the COMET scores over various state-of-the-art LLMs. Moreover, our proposed method consistently outperforms baseline LLMs in terms of win-ratio.

Priyanshu Priya, Rishikant Chigrupaatii, Mauajama Firdaus, Asif Ekbal

Developing intelligent negotiation dialogue systems that resolve conflicts and promote equitable, inclusive, and sustainable outcomes is at the forefront of advancing automated negotiation technology for social good. Negotiation involves balancing cooperation and competition to maximize value without causing offense. Using polite language fosters mutual understanding and creates a respectful and collaborative environment essential for successful negotiations in various domains. Considering this, in this paper, we propose a polite negotiation dialogue system, GENTEEL-NEGOTIATOR for social good applications to boost the overall quality of negotiation outcomes. We focus on developing a negotiation dialogue system for two key application areas, namely tourism and e-commerce. We begin by curating a unique negotiation dialogue dataset, NEGOCHAT for tourism. We further enrich the NEGOCHAT and Integrative Negotiation Dataset (IND) for e-commerce with various negotiation strategies. These datasets are then used to develop the GENTEEL-NEGOTIATOR, leveraging the Large Language Model (LLM) and mixture-of-expert (MoE)-based reinforcement learning approach. The proposed MoE-based method employs heuristic experts dedicated to negotiation, politeness, and dialogue coherence to facilitate the learning of diverse semantics by analyzing the dialogue context. A novel reward function with negotiation strategy congruence, politeness, dialogue coherence, and engagingness rewards is designed to guide the policy’s learning for generating responses. Automatic and human evaluations on NEGOCHAT and IND datasets validate the effectiveness of GENTEEL-NEGOTIATOR in generating polite responses during negotiation while maintaining conversation goals, including coherence and engagingness.

Atsumoto Ohashi, Ryuichiro Higashinaka

Post-processing networks (PPNs) are components that modify the outputs of arbitrary modules in task-oriented dialogue systems and are optimized using reinforcement learning (RL) to improve the overall task completion capability of the system. However, previous PPN-based approaches have been limited to handling only a subset of modules within a system, which poses a significant limitation in improving the system performance. In this study, we propose a joint optimization method for post-processing the outputs of all modules using universal post-processing networks (UniPPNs), which are language-model-based networks that can modify the outputs of arbitrary modules in a system as a sequence-transformation task. Moreover, our RL algorithm, which employs a module-level Markov decision process, enables fine-grained value and advantage estimation for each module, thereby stabilizing joint learning for post-processing the outputs of all modules. Through both simulation-based and human evaluation experiments using the MultiWOZ dataset, we demonstrated that UniPPN outperforms conventional PPNs in the task completion capability of task-oriented dialogue systems.

Tingyu Mo, Jacqueline C. K. Lam, Victor O. K. Li, Lawrence Y. L. Cheung

Alzheimer’s Disease (AD) is an irreversible neurodegenerative disease affecting 50 million people worldwide. Low-cost, accurate identification of key markers of AD is crucial for timely diagnosis and intervention. Language impairment is one of the earliest signs of cognitive decline, which can be used to discriminate AD patients from normal control (NC) individuals. Patient-interviewer dialogues may be used to detect such impairments, but they are often mixed with ambiguous, noisy, and irrelevant information, making the AD detection task difficult. Moreover, the limited availability of AD speech samples and variability in their speech styles pose significant challenges in developing robust speech-based AD detection models. To address these challenges, we propose DECT, a novel speech-based domain-specific approach leveraging large language models (LLMs) for fine-grained linguistic analysis and label-switched label-preserved (LSLP) data generation. Our study presents four novelties: (1) We harness the summarizing capabilities of LLMs to identify and distill key Cognitive-Linguistic (CL) information (atoms) from noisy speech transcripts, effectively filtering irrelevant information. (2) We leverage the inherent linguistic knowledge of LLMs to extract linguistic markers from unstructured and heterogeneous audio transcripts. (3) We exploit the compositional ability of LLMs to generate LSLP AD speech transcripts consisting of diverse linguistic patterns to overcome the speech data scarcity challenge and enhance the robustness of AD detection models. (4) We use the augmented AD textual speech transcript dataset and a more fine-grained representation of AD textual speech transcript data to fine-tune the AD detection model. The results have shown that DECT, an integrated, LLM-assisted, speech-based AD detection model demonstrates superior model performance with an 11% improvement in AD detection accuracy on the datasets from DementiaBank compared to the baselines.

Kshitij Mishra, Manisha Burja, Asif Ekbal

Individuals living with disabilities often face challenges in their daily lives, from managing physical tasks to coping with emotional needs. It is imperative to provide them with personalized, courteous, and empathetic support that can address their unique needs. To bridge this gap, we propose an Empathetic Disability Support System (EDiSS), designed to offer personalized support tailored with correct politeness and empathetic strategies as per individual users’ OCEAN traits, gender, and age. To train EDiSS, first, a specialized personalized disability support dialogue dataset (PDCARE) is created encompassing a wide spectrum of disabilities, such as Spinal Cord Injuries, Neurological Disorders, Orthopedic Disabilities, etc, and support areas like Physical Therapy Exercises, Pain Management, Emotional Support, etc. EDiSS employs a reinforcement learning-based dialogue model with a novel reward function. It adapts its tone and content based on the user’s persona, gender, and age to provide respectful and empathetic assistance across various aspects of daily living. Our experiments and evaluation demonstrate the effectiveness of EDiSS in improving the quality of life of individuals with disabilities, marking a significant advancement in leveraging technology to provide much-needed support and assistance in their daily challenges.

Ziyang Ma, Yakun Song, Chenpeng Du, Jian Cong, Zhuo Chen, Yuping Wang, Yuxuan Wang, Xie Chen

Dialogue serves as the most natural manner of human-computer interaction (HCI). Recent advancements in speech language models (SLM), have significantly enhanced speech-based conversational AI. However, these models are limited to turn-based conversation, lacking the ability to interact with humans in real-time spoken scenarios, for example, being interrupted when the generated content is not satisfactory. To address these limitations, we explore full duplex modeling (FDM) in interactive speech language models (iSLM), focusing on enhancing real-time interaction and, more explicitly, exploring the quintessential ability of interruption. We introduce a novel model design, namely listening-while-speaking language model (LSLM), an end-to-end system equipped with both listening and speaking channels. Our LSLM employs a token-based decoder-only TTS for speech generation and a streaming self-supervised learning (SSL) encoder for real-time audio input. LSLM fuses both channels for autoregressive generation and detects turn-taking in real time. Three fusion strategies—early fusion, middle fusion, and late fusion—are explored, with middle fusion achieving an optimal balance between speech generation and real-time interaction. Two experimental settings, command-based FDM and voice-based FDM, demonstrate LSLM’s robustness to noise and sensitivity to diverse instructions. Our results highlight LSLM’s capability to achieve duplex communication with minimal impact on existing systems. This study aims to advance the development of interactive speech dialogue systems, enhancing their applicability in real-world contexts.

Shichao Ma, Xinfeng Zhang, Zeng Zhao, Bai Liu, Changjie Fan, Zhipeng Hu

In recent years, diffusion modeling has shown great potential for image generation and editing. Beyond single-model approaches, various drawing workflows now exist to handle diverse drawing tasks. However, few solutions effectively identify user intentions through dialogue and progressively complete drawings. We introduce DialogDraw, which facilitates image generation and editing through continuous dialogue interaction. DialogDraw enables users to create and refine drawings using natural language and integrates with numerous open-source drawing workflows and models. The system accurately recognizes intentions and extracts user inputs via parameterization, adapts to various drawing function parameters, and provides an intuitive interaction mode. It effectively executes user instructions, supports dozens of image generation and editing methods, and offers robust scalability. Moreover, we employ SFT and RLHF to iterate the Intention Recognition and Parameter Extraction Model (IRPEM). To evaluate DialogDraw's functionality, we propose DrawnConvos, a dataset rich in drawing functions and command dialogue data collected from the open-source community. Our evaluation demonstrates that DialogDraw excels in command compliance, identifying and adapting to user drawing intentions, thereby proving the effectiveness of our method.

Yanhua Li, Xiaocao Ouyang, Chaofan Pan, Jie Zhang, Sen Zhao, Shuyin Xia, Xin Yang, Guoyin Wang, Tianrui Li

Open intent classification is critical for the development of dialogue systems, aiming to accurately classify known intents into their corresponding classes while identifying unknown intents. Prior boundary-based methods assumed known intents fit within compact spherical regions, focusing on coarse-grained representation and precise spherical decision boundaries. However, these assumptions are often violated in practical scenarios, making it difficult to distinguish known intent classes from unknowns using a single spherical boundary. To tackle these issues, we propose a Multi-granularity Open intent classification method via adaptive Granular-Ball decision boundary (MOGB). Our MOGB method consists of two modules: representation learning and decision boundary acquiring. To effectively represent the intent distribution, we design a hierarchical representation learning method. This involves iteratively alternating between adaptive granular-ball clustering and nearest sub-centroid classification to capture fine-grained semantic structures within known intent classes. Furthermore, multi-granularity decision boundaries are constructed for open intent classification by employing granular-balls with varying centroids and radii. Extensive experiments conducted on three public datasets demonstrate the effectiveness of our proposed method.

Wiradee Imrattanatrai, Masaki Asada, Kimihiro Hasegawa, Zhi-Qi Cheng, Ken Fukuda, Teruko Mitamura

This paper presents VDAct, a dataset for a Video-grounded Dialogue on Event-driven Activities, alongside VDEval, a session-based context evaluation metric specially designed for the task. Unlike existing datasets, VDAct includes longer and more complex video sequences that depict a variety of event-driven activities that require advanced contextual understanding for accurate response generation. The dataset comprises 3,000 dialogues with over 30,000 question-and-answer pairs, derived from 1,000 videos with diverse activity scenarios. VDAct displays a notably challenging characteristic due to its broad spectrum of activity scenarios and wide range of question types. Empirical studies on state-of-the-art vision foundation models highlight their limitations in addressing certain question types on our dataset. Furthermore, VDEval, which integrates dialogue session history and video content summaries extracted from our supplementary Knowledge Graphs to evaluate individual responses, demonstrates a significantly higher correlation with human assessments on the VDAct dataset than existing evaluation metrics that rely solely on the context of single dialogue turns.