arXiv subjects

Jinqiang Wang

Publications and source records attributed to Jinqiang Wang.

12 recordsLinked to original sources

arXiv2026

Towards Proactive Detection of User-Side Implicit Conflicts in Human-LLM Dialogue

In Human-LLM dialogue, follow-up user utterances may implicitly conflict with earlier intents, leading the LLM to misinterpret user needs and generate inappropriate responses. A reliable dialogue system should proactively detect user-side conflicts before generating a response and seek clarification when necessary. However, prior work has largely focused on LLM-side conflicts, leaving user-side conflicts underexplored. To fill this gap, we construct UC-Bench, a human-annotated benchmark for evaluating user-side conflict detection. Preliminary experiments show that existing LLMs struggle with this task, especially when conflicts arise from implicit incompatibilities grounded in dialogue history. To improve lightweight LLMs with limited training data, we investigate data synthesis for user-side conflict detection. Existing synthesis methods do not explicitly model the implicit incompatibilities between historical and current user utterances, making it difficult to capture the evolution of conflicts and to generate reliably labeled implicit conflict samples. We propose SynUC, a constraint-guided synthesis method that represents user-side conflicts in a constraint space and uses the SPEAKING framework to guide traceable constraint transformations. Applying SynUC to WildChat, we construct UC-Data, a user-side conflict training set containing 2,487 samples. On UC-Bench, Qwen3.5-4B trained on UC-Data outperforms larger general-purpose LLMs such as Claude Opus 4.8, as well as the same backbone trained on data synthesized by existing methods.

cs.CL↗

arXiv2025

LLM-Driven Preference Data Synthesis for Proactive Prediction of the Next User Utterance in Human-Machine Dialogue

Proactively predicting a users next utterance in human-machine dialogue can streamline interaction and improve user experience. Existing commercial API-based solutions are subject to privacy concerns while deploying general-purpose LLMs locally remains computationally expensive. As such, training a compact, task-specific LLM provides a practical alternative. Although user simulator methods can predict a user's next utterance, they mainly imitate their speaking style rather than advancing the dialogue. Preference data synthesis has been investigated to generate data for proactive next utterance prediction and help align LLMs with user preferences. Yet existing methods lack the ability to explicitly model the intent reasoning that leads to the user's next utterance and to define and synthesize preference and non-preference reasoning processes for predicting the user's next utterance.To address these challenges, we propose ProUtt, an LLM-driven preference data synthesis method for proactive next utterance prediction. ProUtt converts dialogue history into an intent tree and explicitly models intent reasoning trajectories by predicting the next plausible path from both exploitation and exploration perspectives. It then constructs preference and non-preference reasoning processes by perturbing or revising intent tree paths at different future turns. Extensive evaluations using LLM-as-a-judge and human judgments demonstrate that ProUtt consistently outperforms existing data synthesis methods, user simulators, and commercial LLM APIs across four benchmark datasets. We release both the code and the synthesized datasets to facilitate future research.

cs.CL↗

arXiv2025

CTourLLM: Enhancing LLMs with Chinese Tourism Knowledge

Recently, large language models (LLMs) have demonstrated their effectiveness in various natural language processing (NLP) tasks. However, the lack of tourism knowledge limits the performance of LLMs in tourist attraction presentations and travel planning. To address this challenge, we constructed a supervised fine-tuning dataset for the Chinese culture and tourism domain, named Cultour. This dataset consists of three parts: tourism knowledge base data, travelogues data, and tourism QA data. Additionally, we propose CTourLLM, a Qwen-based model supervised fine-tuned with Cultour, to improve the quality of information about attractions and travel planning. To evaluate the performance of CTourLLM, we proposed a human evaluation criterion named RRA (Relevance, Readability, Availability), and employed both automatic and human evaluation. The experimental results demonstrate that CTourLLM outperforms ChatGPT, achieving an improvement of 1.21 in BLEU-1 and 1.54 in Rouge-L, thereby validating the effectiveness of the response outcomes. Our proposed Cultour is accessible at https://github.com/mrweiqk/Cultour.

cs.CL↗

arXiv2025

A Data Synthesis Method Driven by Large Language Models for Proactive Mining of Implicit User Intentions in Tourism

In the tourism domain, Large Language Models (LLMs) often struggle to mine implicit user intentions from tourists' ambiguous inquiries and lack the capacity to proactively guide users toward clarifying their needs. A critical bottleneck is the scarcity of high-quality training datasets that facilitate proactive questioning and implicit intention mining. While recent advances leverage LLM-driven data synthesis to generate such datasets and transfer specialized knowledge to downstream models, existing approaches suffer from several shortcomings: (1) lack of adaptation to the tourism domain, (2) skewed distributions of detail levels in initial inquiries, (3) contextual redundancy in the implicit intention mining module, and (4) lack of explicit thinking about tourists' emotions and intention values. Therefore, we propose SynPT (A Data Synthesis Method Driven by LLMs for Proactive Mining of Implicit User Intentions in the Tourism), which constructs an LLM-driven user agent and assistant agent to simulate dialogues based on seed data collected from Chinese tourism websites. This approach addresses the aforementioned limitations and generates SynPT-Dialog, a training dataset containing explicit reasoning. The dataset is utilized to fine-tune a general LLM, enabling it to proactively mine implicit user intentions. Experimental evaluations, conducted from both human and LLM perspectives, demonstrate the superiority of SynPT compared to existing methods. Furthermore, we analyze key hyperparameters and present case studies to illustrate the practical applicability of our method, including discussions on its adaptability to English-language scenarios. All code and data are publicly available.

cs.CL↗

arXiv2024

A Survey on Large Language Models from General Purpose to Medical Applications: Datasets, Methodologies, and Evaluations

Large Language Models (LLMs) have demonstrated surprising performance across various natural language processing tasks. Recently, medical LLMs enhanced with domain-specific knowledge have exhibited excellent capabilities in medical consultation and diagnosis. These models can smoothly simulate doctor-patient dialogues and provide professional medical advice. Most medical LLMs are developed through continued training of open-source general LLMs, which require significantly fewer computational resources than training LLMs from scratch. Additionally, this approach offers better patient privacy protection than API-based solutions. Given the above advantages, this survey systematically summarizes how to train medical LLMs based on open-source general LLMs from a more fine-grained perspective. It covers (a) how to acquire training corpus and construct customized medical training sets, (b) how to choose an appropriate training paradigm, (c) how to choose a suitable evaluation benchmark, and (d) existing challenges and promising research directions are discussed. This survey can provide guidance for the development of LLMs focused on various medical applications, such as medical education, diagnostic planning, and clinical assistants. Related resources and supplemental information can be found on the GitHub repository.

cs.CL↗

arXiv2024

Language-assisted Vision Model Debugger: A Sample-Free Approach to Finding and Fixing Bugs

Vision models with high overall accuracy often exhibit systematic errors in specific scenarios, posing potential serious safety concerns. Diagnosing bugs of vision models is gaining increased attention, however traditional diagnostic approaches require annotation efforts (eg rich metadata accompanying each samples of CelebA). To address this issue,We propose a language-assisted diagnostic method that uses texts instead of images to diagnose bugs in vision models based on multi-modal models (eg CLIP). Our approach connects the embedding space of CLIP with the buggy vision model to be diagnosed; meanwhile, utilizing a shared classifier and the cross-modal transferability of embedding space from CLIP, the text-branch of CLIP become a proxy model to find bugs in the buggy model. The proxy model can classify texts paired with images. During the diagnosis, a Large Language Model (LLM) is employed to obtain task-relevant corpora, and this corpora is used to extract keywords. Descriptions constructed with templates containing these keywords serve as input text to probe errors in the proxy model. Finally, we validate the ability to diagnose existing visual models using language on the Waterbirds and CelebA datasets, we can identify bugs comprehensible to human experts, uncovering not only known bugs but also previously unknown ones.

cs.AI↗

arXiv2023

An Improved Masking Strategy for Self-supervised Masked Reconstruction in Human Activity Recognition

Masked reconstruction serves as a fundamental pretext task for self-supervised learning, enabling the model to enhance its feature extraction capabilities by reconstructing the masked segments from extensive unlabeled data. In human activity recognition, this pretext task employed a masking strategy centered on the time dimension. However, this masking strategy fails to fully exploit the inherent characteristics of wearable sensor data and overlooks the inter-channel information coupling, thereby limiting its potential as a powerful pretext task. To address these limitations, we propose a novel masking strategy called Channel Masking. It involves masking the sensor data along the channel dimension, thereby compelling the encoder to extract channel-related features while performing the masked reconstruction task. Moreover, Channel Masking can be seamlessly integrated with masking strategies along the time dimension, thereby motivating the self-supervised model to undertake the masked reconstruction task in both the time and channel dimensions. Integrated masking strategies are named Time-Channel Masking and Span-Channel Masking. Finally, we optimize the reconstruction loss function to incorporate the reconstruction loss in both the time and channel dimensions. We evaluate proposed masking strategies on three public datasets, and experimental results show that the proposed strategies outperform prior strategies in both self-supervised and semi-supervised scenarios.

cs.HC↗

arXiv2023

The coupling effect between the environment and strategies drives the emergence of group cooperation

Introducing environmental feedback into evolutionary game theory has led to the development of eco-evolutionary games, which have gained popularity due to their ability to capture the intricate interplay between the environment and decision-making processes. However, current researches in this field focus on the study to macroscopic evolutionary dynamics in infinite populations. In this study, we propose a multi-agent computational model based on reinforcement learning to explore the coupled dynamics between strategies and the environment in finite populations from a bottom-up perspective. Our findings indicate that even in environments that favor defectors, high levels of group cooperation can emerge from self-interested individuals, highlighting the significant role of the coupling effect between the environment and strategies. Over time, the higher payoff of defection can be diluted due to environmental degradation, while cooperation can become the dominant strategy when positively reinforced by the environment. Remarkably, individuals can accurately detect the inflection point of the environment solely through rewards, when a reinforcing positive feedback loop are triggered, resulting in a rapid increase in agents' rewards and facilitating the establishment and maintenance of group cooperation. Our research provides a fresh perspective on understanding the emergence of group cooperation and sheds light on the underlying mechanisms involving individuals and the environment.

physics.bio-ph↗

arXiv2023

A Multi-Task Deep Learning Approach for Sensor-based Human Activity Recognition and Segmentation

Sensor-based human activity segmentation and recognition are two important and challenging problems in many real-world applications and they have drawn increasing attention from the deep learning community in recent years. Most of the existing deep learning works were designed based on pre-segmented sensor streams and they have treated activity segmentation and recognition as two separate tasks. In practice, performing data stream segmentation is very challenging. We believe that both activity segmentation and recognition may convey unique information which can complement each other to improve the performance of the two tasks. In this paper, we firstly proposes a new multitask deep neural network to solve the two tasks simultaneously. The proposed neural network adopts selective convolution and features multiscale windows to segment activities of long or short time durations. First, multiple windows of different scales are generated to center on each unit of the feature sequence. Then, the model is trained to predict, for each window, the activity class and the offset to the true activity boundaries. Finally, overlapping windows are filtered out by non-maximum suppression, and adjacent windows of the same activity are concatenated to complete the segmentation task. Extensive experiments were conducted on eight popular benchmarking datasets, and the results show that our proposed method outperforms the state-of-the-art methods both for activity recognition and segmentation.

cs.CV↗

arXiv2022

Sensor Data Augmentation by Resampling for Contrastive Learning in Human Activity Recognition

While deep learning has contributed to the advancement of sensor-based Human Activity Recognition (HAR), it is usually a costly and challenging supervised task with the needs of a large amount of labeled data. To alleviate this issue, contrastive learning has been applied for sensor-based HAR. Data augmentation is an essential part of contrastive learning and has a significant impact on the performance of downstream tasks. However, current popular augmentation methods do not achieve competitive performance in contrastive learning for sensor-based HAR. Motivated by this issue, we propose a new sensor data augmentation method by resampling, which simulates more realistic activity data by varying the sampling frequency to maximize the coverage of the sampling space. In addition, we extend MoCo, a popular contrastive learning framework, to MoCoHAR for HAR. The resampling augmentation method will be evaluated on two contrastive learning frameworks, SimCLRHAR and MoCoHAR, using UCI-HAR, MotionSensor, and USC-HAD datasets. The experiment results show that the resampling augmentation method outperforms all state-of-the-art methods under a small amount of labeled data, on SimCLRHAR and MoCoHAR, with mean F1-score as the evaluation metric. The results also demonstrate that not all data augmentation methods have positive effects in the contrastive learning framework.

cs.HC↗

arXiv2022

Negative Selection by Clustering for Contrastive Learning in Human Activity Recognition

Contrastive learning has been applied to Human Activity Recognition (HAR) based on sensor data owing to its ability to achieve performance comparable to supervised learning with a large amount of unlabeled data and a small amount of labeled data. The pre-training task for contrastive learning is generally instance discrimination, which specifies that each instance belongs to a single class, but this will consider the same class of samples as negative examples. Such a pre-training task is not conducive to human activity recognition tasks, which are mainly classification tasks. To address this problem, we follow SimCLR to propose a new contrastive learning framework that negative selection by clustering in HAR, which is called ClusterCLHAR. Compared with SimCLR, it redefines the negative pairs in the contrastive loss function by using unsupervised clustering methods to generate soft labels that mask other samples of the same cluster to avoid regarding them as negative samples. We evaluate ClusterCLHAR on three benchmark datasets, USC-HAD, MotionSense, and UCI-HAR, using mean F1-score as the evaluation metric. The experiment results show that it outperforms all the state-of-the-art methods applied to HAR in self-supervised learning and semi-supervised learning.

cs.CV↗

arXiv2021

Understanding and Testing Generalization of Deep Networks on Out-of-Distribution Data

Deep network models perform excellently on In-Distribution (ID) data, but can significantly fail on Out-Of-Distribution (OOD) data. While developing methods focus on improving OOD generalization, few attention has been paid to evaluating the capability of models to handle OOD data. This study is devoted to analyzing the problem of experimental ID test and designing OOD test paradigm to accurately evaluate the practical performance. Our analysis is based on an introduced categorization of three types of distribution shifts to generate OOD data. Main observations include: (1) ID test fails in neither reflecting the actual performance of a single model nor comparing between different models under OOD data. (2) The ID test failure can be ascribed to the learned marginal and conditional spurious correlations resulted from the corresponding distribution shifts. Based on this, we propose novel OOD test paradigms to evaluate the generalization capacity of models to unseen data, and discuss how to use OOD test results to find bugs of models to guide model debugging.

cs.LG↗