论文检索

Hangyu Ye, Liyao Xiang, Naixuan Huang, Dongyue Yu, Lijun Zhang, Gang Wang

A vast amount of user-generated content is uploaded on social media everyday, potentially being collected as training data for large language models, and thus poses severe threats to individual privacy. Existing approaches for protecting user-generated content often fail to detect implicit privacy leaks which are not directly given but could be inferred from the contextual text (clues). The precise detection of leaks and clues is difficult but critical in text sanitization. We propose a graph-based model for the user-generated content and build a privacy leakage detector PrivSniffer which integrates the inference capability of language models with the precise graph search, to capture the contextual privacy leakage (CPL). To evaluate the effectiveness of the framework, we create SynthLeak, a dataset of dialogues containing human-labeled implicit leaks, while featuring diversity and naturalness. Our experimental results on SynthLeak and several other benchmarks reveal PrivSniffer's superior capability in detecting implicit leaks and CPLs. Particularly in CPL detection, the state-of-the-art approach achieves only an F1 Score of 0.36, whereas PrivSniffer attains 0.59 on SynthLeak, showing great promise in real-world text sanitization.

Yongkang Guo, Zhihuan Huang, Yuqing Kong

High dialogue engagement is a crucial indicator of an effective conversation. A reliable measure of engagement could help benchmark large language models, enhance the effectiveness of human-computer interactions, or improve personal communication skills. However, quantifying engagement is challenging, since it is subjective and lacks a ''gold standard''. This paper proposes PMIScore, an efficient unsupervised approach to quantify dialogue engagement. It uses pointwise mutual information (PMI), which is the probability of generating a response conditioning on the conversation history. Thus, PMIScore offers a clear interpretation of engagement. As directly computing PMI is intractable due to the complexity of dialogues, PMIScore learned it through a dual form of divergence. The algorithm includes generating positive and negative dialogue pairs, extracting embeddings by large language models (LLMs), and training a small neural network using a mutual information loss function. We validated PMIScore on both synthetic and real-world datasets. Our results demonstrate the effectiveness of PMIScore in PMI estimation and the reasonableness of the PMI metric itself.

Daniil Sherki, Daniil Merkulov, Aleksandra Savina, Dzhantemir Kikov, Dmitry Parpulov, Alexander Ivanov, Artem Abakumov, Ekaterina Muravleva

We present PERELMAN (PipEline foR sciEntific Literature Meta-ANalysis), an agentic framework designed to extract specific information from a large corpus of scientific articles to support large-scale literature reviews and meta-analyses. Our central goal is to reliably transform heterogeneous article content into a unified, machine-readable representation. PERELMAN first elicits domain knowledge-including target variables, inclusion criteria, units, and normalization rules-through a structured dialogue with a subject-matter expert. This domain knowledge is then reused across multiple stages of the pipeline and guides coordinated agents in extracting evidence from narrative text, tables, and figures, enabling consistent aggregation across studies. In order to assess reproducibility and validate our implementation, we evaluate the system on the task of reproducing the meta-analysis of layered Li-ion cathode properties LiNi0.8Mn0.1Co0.1O2 (NMC811). We describe our solution, which has the potential to reduce the time required to prepare meta-analyses from months to minutes.

Yanyue Zhang, Zihao Wang, Xin Zhang, Deyu Zhou

Persuasive dialogue aims to alter people's attitudes or behaviors through conversation. While LLMs can generate emotional responses, they tend to use a uniform approach across varied scenarios, limiting their persuasive effectiveness. Diverse demands need varied persuasion strategies, which challenge both LLMs and human efforts. To address this, this paper incorporates the idea of meta-learning and proposes PersuHMM, an iterative learning approach for constructing the Hierarchical Meta-strategy Memory to generate Persuasive dialogue. Through the interaction between Meta‑layer and Task‑layer, the approach continuously accumulates automated meta‑strategies from generated outcomes and data labels, forming a persuasive meta‑strategy memory that balances efficiency and generalizability. To facilitate model retrieval and use, the meta-strategy memory is hierarchically organized via clustering for a clearer and more logical storage structure. Experimental results show that the hierarchical meta-strategy memory enhances both the persuasiveness and generalizability of the persuasion model, and even enables cross-model performance improvement.

Zhiqiang Gao, Jing Han, Zhuochu Wang, Shihao Gao, Cheng Zhu, Kehan Wang, Huan Zhao, Zixing Zhang

Affective computing has achieved notable success in recognizing explicit emotions from short, isolated dialogue segments. However, human emotions are often implicitly expressed, internally regulated, and dynamically evolve over extended interactions. Existing models struggle to disentangle internal emotional states from external expressions, and fail to capture the emotional inconsistency that emerges across long-horizon dialogues. To address this limitation, we introduce Emotional Inconsistency Analysis (EIA), a novel task that aims to identify and reason about discrepancies between implicit and explicit emotions over long-term conversational contexts. To support this task, we construct the MaskDialog dataset carefully curated from television drama and large language models (LLMs). We further propose two LLM-based baseline approaches, i.e., One-shot Self-consistent Inference and Cascaded Multi-step Inference, and conduct comprehensive analyses on dialogue construction strategies and inference behaviors. Extensive experiments across multiple mainstream LLMs reveal that EIA remains highly challenging, particularly in modeling implicit emotional trajectories and cross-turn inconsistency. Overall, EIA reframes emotion understanding from short-term recognition to longitudinal, implicit emotion tracking, with implications for dialogue systems and human–computer interaction.

Zhenhua Yang, Xiachong Feng, Weihong Zhong, Lunjun Liu, Xiaocheng Feng, Bing Qin

Building upon powerful Large Visual Language Models, recent GUI agents have revolutionized autonomous GUI interaction. Given the high information density and structural complexity of GUI layouts, a critical challenge lies in accurately identifying where to focus, i.e., precise GUI grounding. To ensure grounding accuracy, prior approaches predominantly rely on processing inputs at native high resolutions. However, this paradigm inevitably introduces excessive visual redundancy, resulting in increased computational cost and dispersed attention. In our preliminary analysis, we observe that while high-resolution inputs are indispensable for recognizing fine-grained visual details, they paradoxically impair the model’s ability to attend to the correct regions. In contrast, low-resolution inputs, which suppress high-frequency details while preserving global layout structure through downsampling, produce significantly more robust and coherent attention patterns that better guide the model toward relevant regions. Interestingly, this observation mirrors the human visual system, which first leverages low-resolution peripheral vision to identify salient areas before conducting a detailed examination via high-resolution foveal focus. Motivated by this insight, we propose a coarse-to-fine GUI grounding framework termed FastFocus. Our approach first exploits the stability of low-resolution attention to efficiently generate candidate grounding regions. These candidates are then evaluated by a Parallel Verification module, which selectively zooms into high-resolution views to resolve fine details and filter out false positives. Experiments on ScreenSpot-Pro demonstrate state-of-the-art performance, validating that a hierarchical integration of low-resolution guidance and high-resolution verification constitutes an effective and robust paradigm for GUI grounding.

Yunhe Xie, Yang Li

Modeling emotional dynamics in multi-turn dialogues remains challenging due to emotion shifts, where emotional states evolve gradually rather than change abruptly. Existing methods often rely on one-hot supervision, which fails to reflect the progressive nature of human emotions, particularly for neutral-valence emotions with subtle trajectories. To address this limitation, we propose a pseudo soft-label guided Progressive Hybrid-Distributional (PHD) learning framework. PHD reconstructs discrete labels into hybrid distributional representations that encode inter-emotion relations and mixed emotional tendencies. Based on these representations, a progressive training strategy is introduced to guide the model from learning blended emotional states toward the standard one-to-one prediction objective. Furthermore, we design a Graded Contrastive Learning mechanism that replaces rigid binary allocation with graded supervision to alleviate label conflicts. Experiments on benchmark datasets demonstrate PHD consistently improves diverse baseline models, yielding average w-F1 gains of 1.29%. Our framework highlights the critical importance of modeling emotional dynamics as a gradual, distributional process.

Zhenfei Yang, Beiming Yu, Peiqin Lin, Yongkang Liu, Deyi Xiong

Low-Rank Adaptation (LoRA) has become a standard paradigm for parameter-efficient fine-tuning (PEFT). However, its low-rank constraint can limit its capacity to express complex weight updates, leaving a performance gap compared with full fine-tuning. Existing extensions improve expressivity, but they often sacrifice parameter mergeability or rely on sparse, block-diagonal updates that restrict global information flow. We propose SeMi-LoRA (Separation and Mixing LoRA), a novel framework that enables complete high-rank updates while preserving mergeability. SeMi-LoRA decomposes adaptation into channel-wise compression followed by two-stage latent mixing, namely Rank Mix and Channel Mix. Our structural analysis shows that, under a fixed base rank, the rank capacity of the update increases with the number of channels and supports complete updates rather than partial sparse ones. Extensive experiments on commonsense reasoning, mathematical reasoning, natural language understanding, and dialogue generation benchmarks demonstrate that SeMi-LoRA consistently outperforms strong PEFT baselines with favorable parameter efficiency.

Jiaxuan Liu, Yang Xiang, Han Zhao, Xiangang Li, Zhenhua Ling

Movie dubbing is the task of synthesizing speech from scripts conditioned on video scenes, requiring accurate lip sync, faithful timbre transfer, and proper modeling of character identity and emotion. However, existing methods face two major limitations: (1) high-quality multimodal dubbing datasets are limited in scale, suffer from high word error rates, contain sparse annotations, rely on costly manual labeling, and are restricted to monologue scenes, all of which hinder effective model training; (2) existing dubbing models rely solely on the lip region to learn audio-visual alignment, which limits their applicability to complex live-action cinematic scenes, and exhibit suboptimal performance in lip sync, speech quality, and emotional expressiveness. To address these issues, we propose FunCineForge, which comprises an end-to-end production pipeline for large-scale dubbing datasets and an MLLM-based dubbing model designed for diverse cinematic scenes. The pipeline enables the construction of the first television dubbing dataset, CineDub, which serves as a high-quality foundation for training and evaluation. Building on this, our dubbing model effectively captures multimodal cues and supports complex dubbing scenarios, including monologue, narration, dialogue, and multi-speaker settings. Experiments demonstrate that our approach consistently outperforms state-of-the-art methods in audio quality, word error rate, lip sync, temporal alignment, timbre transfer, and instruction following. Code and demos are available at https://funcineforge.github.io/.

Xinran Li, Xinze Che, Yifan Lyu, Zhiqi Huang, Xiujuan Xu

Conversational Aspect-based Sentiment Quadruple Analysis (DiaASQ) needs to capture the complex interrelationships in multiple rounds of dialogues. Existing methods usually employ simple Graph Convolutional Networks (GCN), which introduce structural noise and fail to consider the temporal sequence of the dialogues, or use standard RoPE, which implicitly captures relative distances in a flat sequence but cannot clearly separate the token-level syntactic order from the utterance-level progression, and may suffer from the Distance Dilution problem. To address these issues, we propose a new framework that combines Thread-Constrained Directed Acyclic Graph (TC-DAG) and Discourse-Aware Rotary Position Embedding (D-RoPE). Specifically, TC-DAG filters out cross-thread noise based on thread constraints, maintains global connectivity through root anchoring, and incorporates the temporal sequence of the dialogues. D-RoPE aligns multi-layer semantics using dual-stream projection and multi-scale frequency signals, captures thread dependencies using tree-like distances, and alleviates the token-level Distance Dilution problem by incorporating utterance-level progressions. Experimental results on two benchmark datasets demonstrate that our framework achieves state-of-the-art performance.

Hui Zhang, Guangchen Ruan, Hui Xiao

We present Magnol.AI Copilot, an extension of the Magnol.AI digital biomarker platform that integrates multimodal large language models (LLMs) to transform digital health technology (DHT) trial dashboards into conversational systems. Copilot augments the platform with a multi-agent orchestration layer and vision-enabled LLMs that interpret visualizations, tabular summaries, and textual metadata. The system enables natural language queries and automatic generation of contextual insights, allowing researchers to interact with wearable data through dialogue rather than static inspection. A case study with an actigraphy device demonstrates Copilot’s ability to identify nightly compliance gaps and provide contextual explanations, reducing cognitive load compared to manual dashboard review. This work presents a novel integration of IoMT infrastructure with multimodal LLMs, advancing digital biomarker research toward conversational and accessible DHT trial platforms.

You-Teng Lin, Li-Yang Zhang, Yi-Tang Chen, Jen-Tzung Chien

This work presented a web-based system which introduces an active-listening strategy in a spoken dialogue for self-disclosure to support mental health of a campus user. To enhance the system usability and safety, this demo is developed to conduct the bilingual (Mandarin/English) spoken dialogue where a high-risk dialogue detection during speech interaction is reliably augmented. In particular, a prompt-driven GPT classifier identifies the utterances indicating self-harm or suicide intent and triggers safety alerts with help center and counselor notification. We also integrate a TTS module for Taiwanese Mandarin and standard English, and redesign the user interface to automatically pop up alert messages when high-risk dialogue is detected. In addition, we collect speech data under diverse mental dialogue scenarios with bilingual speech to enable system analysis, evaluation and refinement. Overall, these extensions build a framework that promotes empathetic interactions, enables timely alert in critical cases, and improves the accessibility for diverse users.

Rongyu Zhang, Dingyuan Zhang, Haopeng Li

Proactive dialogue systems, which are designed to guide conversations toward predetermined goals. However, contemporary LLMs predominantly function as passive assistants, mechanically executing human instructions. A key challenge contributing to this limitation is the inherent difficulty in acquiring and annotating high-quality training data for proactive dialogue. Consequently, the scarcity of such data results in a notable deficiency in the proactive conversational capabilities of current LLMs.In this paper, we introduce PANDA (Proactive Agent-based Negotiation Dialogue Augmentation), a method designed to generate accurate, complex, and diverse proactive dialogue data for a challenging task—financial dispute mediation—where a LLM acts as the mediator. PANDA leverages a novel self-evolving synthesis process to manage a pool of user profiles and generate dialogues through structured interactions between multiple LLM-driven agents. To ensure data fidelity, we propose a comprehensive evaluation framework and build a two-level validation system combining automated and expert human verification. Our experiments demonstrate that an 8B-parameter model, trained on our synthesized dataset, achieves state-of-the-art results in the task's evaluation framework. Its performance rivals top closed-source models guided by heavily engineered prompts, even when provided with only essential information.

Mrigendra Agrawal, Yunze Xiao

We present AniTales, a system designed to generate multimodal visual novels from natural language prompts. Our system integrates large language models for story generation, diffusion models for character art, and text-to-speech for voice acting. This paper describes the system's architecture and presents findings from a pilot user study. We evaluated the system with general users (n=10) and domain experts (n=5), focusing on usability, coherence, and visual consistency. General users reported high usability (SUS: 84/100) and strong character-dialogue consistency (4.2/5), along with an average score of 82/100 for their intention to continue using the platform. These initial results suggest AniTales is a promising approach for bridging the gap between text-based AI storytelling and end-to-end multimedia content creation.

Van-Khanh Tran, Van-Khai Dang, Duc-Huy Nguyen

While AI can simulate virtual classrooms, effective collaborative learning requires both dynamic interaction and a well-structured pedagogical plan. To address this, we introduce SAGE (Scaffolded Agent-Guided Education), a novel, compositional two-phase framework. First, a planning module automatically generates an optimized pedagogical scenario using a dedicated team of agents. Second, this scenario is used to configure a conversation module, where autonomous agents engage a student in a structured, real-time dialogue. This approach ensures that dynamic, multi-agent interactions are grounded in a pedagogically sound foundation. We evaluate SAGE through simulation and a study with real students. Results show improved performance against a next-speaker prediction baseline (achieving a 72.13% win rate) and demonstrate effective group dynamics. Specifically, our study with students reveals high role adherence from AI agents, a balanced progression between task-oriented and socio-emotional interactions, and a clear scaffolding effect where instructional support fades as learner autonomy increases. Our findings highlight the significant potential of synergizing automated instructional design with autonomous conversational execution for collaborative learning.

Yeo Jin Kim, Daeun Hong, Tianshu Wang, Wookhee Min, Snigdha Chaturvedi, Cindy E. Hmelo-Silver, James Lester

In computer-supported collaborative learning environments, analyzing student dialogue is essential for understanding collaborative problem-solving behaviors and supporting effective learning. Prior work often treats all dialogue interactions uniformly, failing to capture how specific dialogue interaction differentially impact learning experiences and outcomes. To address this limitation, we introduce a dialogue-based learning analytics framework that integrates weighted temporal clustering of dialogue with large language model-based interpretation. Our framework identifies student interaction patterns most predictive of group learning gains and uses these insights to enable early prediction of learning outcomes and generate pedagogically meaningful interpretations. We evaluate our framework on collaborative dialogue from middle school students engaged in a collaborative game-based learning environment. Our results show that our framework achieves 83.1% accuracy in learning outcome prediction. In addition, expert evaluations and case studies demonstrate that the identified weighted dialogue patterns reflect key collaborative problem-solving behaviors recognized as important in collaborative learning. By surfacing high-impact interaction patterns and enabling prioritized interpretation generation, our framework provides a promising approach for accurately analyzing students’ collaborative dialogue.

Junhua Liu, Yong Keat Tan, Bin Fu, Kwan Hui Lim

Accurate multi-turn intent classification is critical for advancing conversational AI systems but remains challenging due to limited datasets and complex contextual dependencies across dialogue turns. This paper presents two novel approaches leveraging Large Language Models (LLMs) to enhance scalability and reduce latency in production dialogue systems. First, we introduce Symbol Tuning, which simplifies intent labels to reduce task complexity and improve performance in multi-turn dialogues. Second, we propose Consistency-aware, Linguistics Adaptive Retrieval Augmentation (CLARA), a framework that employs LLMs for data augmentation and pseudo-labeling to generate synthetic multi-turn dialogues. These enriched datasets are used to fine-tune a small, efficient model suitable for deployment. Experiments on multilingual dialogue datasets show that our methods result in notable gains in both accuracy and resource efficiency, with improvements of 5.09% in classification accuracy, a 40% reduction in annotation costs, and effective deployment in low-resource multilingual industrial settings.

Zonghai Yao, Talha Chafekar, Junda Wang, Shuo Han, Feiyun Ouyang, Junhui Qian, Lingxi Li, Hong Yu

Real-world adoption of closed-loop insulin delivery systems (CLIDS) in type 1 diabetes remains low, driven not by technical failure, but by diverse behavioral, psychosocial, and social barriers. We introduce ChatCLIDS, the first benchmark to rigorously evaluate LLM–driven persuasive dialogue for health behavior change. Our framework features a library of expert-validated virtual patients, each with clinically grounded, heterogeneous profiles and realistic adoption barriers, and simulates multi-turn interactions with nurse agents equipped with a diverse set of evidence-based persuasive strategies. ChatCLIDS uniquely supports longitudinal counseling and adversarial social influence scenarios, enabling robust, multi-dimensional evaluation. Our findings reveal that while larger and more reflective LLMs adapt strategies over time, all models struggle to overcome resistance, especially under realistic social pressure. These results highlight critical limitations of current LLMs for behavior change, and offer a high-fidelity, scalable testbed for advancing trustworthy persuasive AI in healthcare and beyond.

Rishu Kumar Singh, Navneet Shreya, Sarmistha Das, Apoorva Singh, Sriparna Saha

Existing approaches to complaint analysis largely rely on unimodal, short-form content such as tweets or product reviews. This work advances the field by leveraging multimodal, multi-turn customer support dialogues—where users often share both textual complaints and visual evidence (e.g., screenshots, product photos)—to enable fine-grained classification of complaint aspects and severity. We introduce VALOR, a Validation-Aware Learner with Expert Routing, tailored for this multimodal setting. It employs a multi-expert reasoning setup using large-scale generative models with Chain-of-Thought (CoT) prompting for nuanced decision-making. To ensure coherence between modalities, a semantic alignment score is computed and integrated into the final classification through a meta-fusion strategy. In alignment with the United Nations Sustainable Development Goals (UN SDGs), the proposed framework supports SDG 9 (Industry, Innovation and Infrastructure) by advancing AI-driven tools for robust, scalable, and context-aware service infrastructure. Further, by enabling structured analysis of complaint narratives and visual context, it contributes to SDG 12 (Responsible Consumption and Production) by promoting more responsive product design and improved accountability in consumer services. We evaluate VALOR on a curated multimodal complaint dataset annotated with fine-grained aspect and severity labels, showing that it consistently outperforms baseline models, especially in complex complaint scenarios where information is distributed across text and images. This study underscores the value of multimodal interaction and expert validation in practical complaint understanding systems.

Jianrong Lu, Junwei Liu, Xingyun Zheng, Minghui Yang, Jian Wang, Ping Wang, Yechao Zhang

The integration of Large Language Models (LLMs) into clinical applications presents transformative potential but is undermined by the critical risk of hallucination, the generation of plausible but factually incorrect information. Such failures pose a direct threat to patient safety and the integrity of clinical decision-making. To address this challenge, we introduce MHB, a novel and comprehensive benchmark framework designed to evaluate LLM reliability in two complex, high-stakes clinical contexts: multi-turn medical dialogues and clinical case report analysis. The core of our contribution is a systematic methodology for generating adversarial test cases by injecting ``hallucination traps" into realistic medical data, guided by a fine-grained taxonomy of clinical errors. MHB, comprising 4,695 samples and 20,288 evaluation rubrics, underwent a rigorous, two-stage validation by a panel of 60 licensed physicians from top-tier hospitals, ensuring high clinical realism and consistency. This comprehensive assessment of leading LLMs revealed significant, clinically relevant shortcomings across the board. Even the best-performing model, Claude-4-Sonnet, exhibited a hallucination rate of 29.1%, with some open-source models exceeding 57.0%. All models struggled with specific traps, like fabricated medical data or non-existent guidelines, highlighting prevalent systemic weaknesses.