The interpretative efficacy of large language models (LLMs) fundamentally hinges on the intricate alignment between user inputs and model-specific linguistic priors. Existing methodologies predominantly employ static input optimization strategies, failing to account for the empirically observed divergence in linguistic preference spaces across distinct LLM architectures, including variations in syntactic parsing heuristics, semantic grounding mechanisms, and knowledge retrieval pathways. We propose QueryAligner, an adaptive rewriting system implementing dynamic model-aware input transformation through architecture-specific preference modeling. Our framework introduces two pivotal innovations: 1) A dual-phase optimization engine integrating supervised learning on reverse-engineered cross-architectural training data with reinforcement learning driven by multi-objective reward signals, ensuring simultaneous preservation of semantic integrity and maximization of target model compatibility; 2) An architecture-informed rewriting protocol that automatically discovers latent alignment patterns encoded within distinct LLMs' parametric configurations. Experimental results demonstrate that our method achieves superior performance compared to conventional input optimization techniques.

Empathy relies on the cognitive capacity to relate to similar past experiences. Consequently, retrieval-based approaches utilize analogous exemplars to guide empathetic dialogue generation. However, existing methods prioritize semantic similarity over emotion characteristics, often leading to unempathetic responses. To address this, we propose REG, a framework that integrates four Emotion Attributes into the retrieval process to ensure explicit emotional alignment. Furthermore, to mitigate the noise and limited diversity caused by coarse-grained sentence-level attributes, we incorporate Token-level Retrieval for finer granularity and a Retrieval Candidate Augmentation strategy to enhance diversity. Empirical results on the EmpatheticDialogues dataset demonstrate that REG significantly outperforms baselines, offering a robust solution for empathetic generation.

Role-playing systems powered by large language models (LLMs) have become increasingly influential in emotional communication applications. However, these systems are susceptible to character hallucinations, where the model deviates from predefined character roles and generates responses that are inconsistent with the intended persona. This paper presents the first systematic analysis of character hallucination from an attack perspective, introducing the RoleBreak framework. Our framework identifies two core mechanisms—query sparsity and role-query conflict—as key factors driving character hallucination. Leveraging these insights, we construct a novel dataset, RoleBreakEval, to evaluate existing hallucination mitigation techniques. Our experiments reveal that even enhanced models trained to minimize hallucination remain vulnerable to attacks. To address these vulnerabilities, we propose a novel defence strategy, the Narrator Mode, which generates supplemental context through narration to mitigate role-query conflicts and improve query generalization. Experimental results demonstrate that Narrator Mode significantly outperforms traditional refusal-based strategies by reducing hallucinations, enhancing fidelity to character roles and queries, and improving overall narrative coherence.

Empathy improves human-machine dialogue systems by enhancing the user’s experience. While traditional models have aimed to detect and express users’ emotions from dialogue history, they neglect the crucial and complex interactions among emotion, emotion causes, and commonsense. To address this, we introduce the ECC (Emotion, Cause, and Commonsense) framework, which leverages specialized encoders to capture the key features of emotion, cause, and commonsense and collaboratively models these through a Conditional Variational Auto-Encoder. ECC further employs novel loss functions to refine the interplay of three factors and generates empathetic responses using an energy-based model supported by ODE sampling. Empirical results on the EmpatheticDialogues dataset demonstrate that ECC outperforms existing baselines, offering a robust solution for empathetic dialogue generation.

High-quality prompts are crucial for eliciting outstanding performance from large language models (LLMs) on complex tasks.Existing research has explored model-driven strategies for prompt optimization.However, these methods often suffer from high computational overhead or require strong optimization capabilities from the model itself, which limits their broad applicability.To address these challenges, we propose ORPP, a framework that enhances model performance by optimizing and generating roleplaying prompts.The core idea of ORPP is to confine the prompt search space to role-playing scenarios, thereby fully activating the model's intrinsic capabilities through carefully crafted, high-quality role-playing prompts.Specifically, ORPP first performs iterative optimization on a small subset of training samples to generate high-quality role-playing prompts.Then, leveraging the model's few-shot learning capability, it transfers the optimization experience to efficiently generate suitable prompts for the remaining samples.Our experimental results show that ORPP not only matches but in most cases surpasses existing mainstream prompt optimization methods in terms of performance.Notably, ORPP suggests great "plug-and-play" capability.In most cases, it can be integrated with various other prompt methods and further enhance their effectiveness.

The advancement of Large Language Models (LLMs) has spurred significant interest in Role-Playing Agents (RPAs) for applications such as emotional companionship and virtual interaction. However, recent RPAs are often built on explicit dialogue data, lacking deep, human-like internal thought processes, resulting in superficial knowledge and style expression. While Large Reasoning Models (LRMs) can be employed to simulate character thought, their direct application is hindered by attention diversion (i.e., RPAs forget their role) and style drift (i.e., overly formal and rigid reasoning rather than character-consistent reasoning). To address these challenges, this paper introduces a novel Role-Aware Reasoning (RAR) method, which consists of two important stages: Role Identity Activation (RIA) and Reasoning Style Optimization (RSO). RIA explicitly guides the model with character profiles during reasoning to counteract attention diversion, and then RSO aligns reasoning style with the character and scene via LRM distillation to mitigate style drift. Extensive experiments demonstrate that the proposed RAR significantly enhances the performance of RPAs by effectively addressing attention diversion and style drift.

Instruction fine-tuning is crucial in NLP tasks, enhancing pretrained models' instruction-following capabilities and task-specific performance. However, obtaining high-quality fine-tuning data for large models is challenging due to data collection difficulties and high production costs. To address this, we propose MASTER, a novel data augmentation method that enriches original data through interactions among multiple agents with varying cognitive levels. We simulate three pedagogically grounded teaching scenarios, leveraging multi-agent conversations to generate high-quality teacher-student interaction data. Utilizing MASTER, we construct BOOST-QA, a fine-tuning dataset augmented from existing datasets like Orca-Math-200k, ProcQA, and OpenHermes2.5. Experiments show that models fine-tuned with BOOST-QA perform excellently across multiple benchmarks, demonstrating strong multitask generalization. Notably, MASTER significantly improves models' reasoning abilities in complex tasks, providing valuable insights for future research.

Human mobility prediction is a fundamental task essential for various applications in urban planning, location-based services and intelligent transportation systems. Existing methods often ignore activity information crucial for reasoning human preferences and routines, or adopt a simplified representation of the dependencies between time, activities and locations. To address these issues, we present Hierarchical Graph Attention Recurrent Network (Hgarn) for human mobility prediction. Specifically, we construct a hierarchical graph based on past mobility records and employ a Hierarchical Graph Attention Module to capture complex time-activity-location dependencies. This way, Hgarn can learn representations with rich human travel semantics to model user preferences at the global level. We also propose a model-agnostic history-enhanced confidence (MaHec) label to incorporate each user’s individual-level preferences. Finally, we introduce a Temporal Module, which employs recurrent structures to jointly predict users’ next activities and their associated locations, with the former used as an auxiliary task to enhance the latter prediction. For model evaluation, we test the performance of Hgarn against existing state-of-the-art methods in both the recurring (i.e., returning to a previously visited location) and explorative (i.e., visiting a new location) settings. Overall, Hgarn outperforms other baselines significantly in all settings based on two real-world human mobility data benchmarks. These findings confirm the important role that human activities play in determining mobility decisions, illustrating the need to develop activity-aware intelligent transportation systems. Source codes of this study are available athttps://github.com/YihongT/HGARN

Short-term route prediction on road networks allows us to anticipate the future trajectories of road users, enabling various applications ranging from dynamic traffic control to personalized navigation. Despite recent advances in this area, existing methods focus primarily on learning sequential transition patterns, neglecting the inherent spatial relations in road networks that can affect human routing decisions. To fill this gap, this paper introduces RouteKG, a novel Knowledge Graph-based framework for route prediction. Specifically, we construct a Knowledge Graph on the road network to encode spatial relations, especially moving directions that are crucial for human navigation. Moreover, an n-ary tree-based algorithm is introduced to efficiently generate top-K routes in batch mode, enhancing computational efficiency. To further optimize prediction performance, a rank refinement module is incorporated to fine-tune candidate route rankings. The model performance is evaluated using two real-world vehicle trajectory datasets from two Chinese cities under various practical scenarios. The results demonstrate a significant improvement in accuracy over the baseline methods. We further validate the proposed method by utilizing the pre-trained model as a simulator for real-time traffic flow estimation at the link level. RouteKG has great potential to transform vehicle navigation, traffic management, and a variety of intelligent transportation tasks, playing a crucial role in advancing the core foundation of intelligent and connected urban systems. The source codes of RouteKG are available athttps://github.com/YihongT/RouteKG

Personalized Dialogue Generation (PDG) aims to create coherent responses according to roles or personas.Traditional PDG relies on external role data, which can be scarce and raise privacy concerns.Approaches address these issues by extracting role information from dialogue history, which often fail to generically model roles in continuous space.To overcome these limitations, we introduce a novel framework MOdels Roles from Personalized Dialogue History by Exploring and Utilizing Latent Space (MOR-PHEUS) through a three-stage training process.Specifically, we create a persona codebook to represent roles in latent space compactly, and this codebook is used to construct a posterior distribution of role information.This method enables the model to generalize across roles, allowing the generation of personalized dialogues even for unseen roles.Experiments on both Chinese and English datasets demonstrate that MORPHEUS enhances the extraction of role information, and improves response generation without external role data.Additionally, MORPHEUS can be considered an efficient fine-tuning for large language models.* Morpheus excels at imitating others' forms, effortlessly embodying their physicality, posture, facial expressions, and vocal tone.He flawlessly embodies every intricate detail, including attire and unique mannerisms.

Jiao Ou, Junda Lu, Che Liu, Yihong Tang, Fuzheng Zhang, Di Zhang, Kun Gai. Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers). 2024.

Yihong Tang, Bo Wang, Miao Fang, Dongming Zhao, Kun Huang, Ruifang He, Yuexian Hou. Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2023.

The rapid advancements of Internet of Things (IoT) and Artificial Intelligence (AI) have catalyzed the development of adaptive traffic control systems (ATCS) for smart cities. In particular, deep reinforcement learning (DRL) models produce state-of-the-art performance and have great potential for practical applications. In the existing DRL-based ATCS, the controlled signals collect traffic state information from nearby vehicles, and then optimal actions (e.g., switching phases) can be determined based on the collected information. The DRL models fully “trust” that vehicles are sending the true information to the traffic signals, making the ATCS vulnerable to adversarial attacks with falsified information. In view of this, this article first time formulates a novel task in which a group of vehicles can cooperatively send falsified information to “cheat” DRL-based ATCS in order to save their total travel time. To solve the proposed task, we develop CollusionVeh , a generic and effective vehicle-colluding framework composed of a road situation encoder, a vehicle interpreter, and a communication mechanism. We employ our framework to attack established DRL-based ATCS and demonstrate that the total travel time for the colluding vehicles can be significantly reduced with a reasonable number of learning episodes, and the colluding effect will decrease if the number of colluding vehicles increases. Additionally, insights and suggestions for the real-world deployment of DRL-based ATCS are provided. The research outcomes could help improve the reliability and robustness of the ATCS and better protect the smart mobility systems.

Accurate short-term traffic prediction plays a pivotal role in various smart mobility operation and management systems. Currently, most of the state-of-the-art prediction models are based on graph neural networks (Gnns), and the required training samples are proportional to the size of the traffic network. In many cities, the available amount of traffic data is substantially below the minimum requirement due to the data collection expense. It is still an open question to develop traffic prediction models with a small size of training data on large-scale networks. We notice that the traffic states of a node for the near future only depend on the traffic states of its localized neighborhoods, which can be represented using the graph relational inductive biases. In view of this, this paper develops a graph network (Gn)-based deep learning model LocaleGn that depicts the traffic dynamics using localized data aggregating and updating functions, as well as the node-wise recurrent neural networks. LocaleGn is a light-weighted model designed for training on few samples without over-fitting, and hence it can solve the problem of few-sample traffic prediction. The proposed model is examined on predicting both traffic speed and flow with six datasets, and the experimental results demonstrate that LocaleGn outperforms existing state-of-the-art baseline models. It is also demonstrated that the learned knowledge from LocaleGn can be transferred across cities. The research outcomes can help to develop light-weighted traffic prediction systems, especially for cities lacking historically archived traffic data.

Accurate real-time traffic forecast is critical for intelligent transportation systems (ITS) and it serves as the cornerstone of various smart mobility applications. Though this research area is dominated by deep learning, recent studies indicate that the accuracy improvement by developing new model structures is becoming marginal. Instead, we envision that the improvement can be achieved by transferring the ''forecasting-related knowledge" across cities with different data distributions and network topologies. To this end, this paper aims to propose a novel transferable traffic forecasting framework: Domain Adversarial Spatial-Temporal Network (DASTNet). DASTNet is pre-trained on multiple source networks and fine-tuned with the target network's traffic data. Specifically, we leverage the graph representation learning and adversarial domain adaptation techniques to learn the domain-invariant node embeddings, which are further incorporated to model the temporal traffic data. To the best of our knowledge, we are the first to employ adversarial multi-domain adaptation for network-wide traffic forecasting problems. DASTNet consistently outperforms all state-of-the-art baseline methods on three benchmark datasets. The trained DASTNet is applied to Hong Kong's new traffic detectors, and accurate traffic predictions can be delivered immediately (within one day) when the detector is available. Overall, this study suggests an alternative to enhance the traffic forecasting methods and provides practical implications for cities lacking historical traffic data. Source codes of DASTNet are available at https://github.com/YihongT/DASTNet.