Pengyuan Liu

Zhongyang Lin, Ziran Zhao, Feifei Zhai et al.

Large language models remain vulnerable to jailbreak attacks that hide harmful intent behind seemingly ordinary requests such as role-play, translation, encoding, adversarial suffixes, and multi-turn buildup. Existing defenses still struggle to handle these attacks without over-blocking benign but sensitive requests, partly because they often apply the same action to every prompt and therefore fail to balance safety and helpfulness. We propose NeuroArmor, a white-box runtime defense that uses prompt-specific safe variants as a local safety reference for deciding when intervention is needed and, once triggered, as safe targets for intervention. For each prompt, NeuroArmor builds K safe variants, compares the prompt state against this local safe reference in hidden-state space, and routes anomalies either to a refusal branch for malicious prompts or to a helpful recovery branch for borderline benign prompts. On Llama-3-8B-Instruct, NeuroArmor reduces malicious attack success rate (ASR) from 41.56% to 1.57% while lowering benign false positive rate (FPR) on the shared benign pool from 30.26% to 22.05%; matched baselines remain substantially weaker on this trade-off. External-judge and manual behavioral evaluations further show that the remaining non-blocked outputs are much less likely to be operationally harmful. Overall, NeuroArmor provides a more effective runtime strategy for jailbreak defense by combining prompt-specific consistency checking, routing, and selective intervention.

Zhiqing Ma, Zhonghao Xu, Dong Yu et al.

Multi-turn jailbreak attacks pose a growing threat to LLMs by exploiting conversational dynamics such as gradual escalation and cross-turn coordination. Existing defenses either rely on costly retraining -- often degrading model utility -- or apply single-turn analysis independently at each turn, failing to capture how risk accumulates along interaction trajectories. We observe that safety behavior in multi-turn interaction is trajectory-dependent: dialogue history continuously reshapes the model's conditioning context, making it insufficient to evaluate each turn in isolation. Motivated by this insight, we present THRD, the first training-free framework that explicitly models temporal risk accumulation for multi-turn jailbreak defense. THRD integrates four modules: a Turn-level Risk Assessor (TRA) for instantaneous risk estimation, a Historical Context Analyzer (HCA) for cross-turn intent escalation detection, a Response Evaluator (RE) for identifying facilitative outputs, and a Decision Module that combines these signals through a time-evolving scoring mechanism with attenuation-based modulation and trend-aware adjustment. Experiments against state-of-the-art multi-turn attacks -- including tree-search-based and multi-agent collaborative methods -- across two target models show that THRD reduces ASR to 0.2--4.0% while preserving model utility within 1.5% degradation on MMLU and GSM8K. Ablation studies confirm non-redundant module contributions and stable cross-architecture generalization. Analysis of first rejection triggers reveals that over 70% of multi-turn attacks require Turn~2 or later to detect, validating the necessity of explicit temporal aggregation.

Yangyang Liu, Dong Yu, Pengyuan Liu

Large language models are increasingly used in value-sensitive decision settings, where irrelevant demographic cues should not alter judgments. We construct the Realistic Value Decision Benchmark (RVDB), a controlled benchmark that varies only the role-gender configuration while holding the scenario, ordered value pair, roles, candidate decisions, Value Distance, and Decision Severity fixed. Using a position-balanced evaluation across seven models, we test whether models preserve decision invariance under gender perturbations and whether their self-attributions reflect observed behavioral changes. We find that explicit gender cues induce bounded but systematic decision flips, including under an explicit gender-attribution prompt that asks models to report whether gender influenced their choice. Cross-gender role swaps reveal a consistent female-proposed-decision asymmetry, while models often attribute flipped decisions to No Influence or other non-gender factors. Further analysis shows that gender effects concentrate near less determinate value boundaries and under more severe decision contexts, suggesting that gender cues act as local boundary-shifting factors rather than global overrides of value reasoning. Value rankings remain largely stable, but ordered value-pair trade-offs shift unevenly across role-gender configurations. These results show that gender can enter LLM value trade-offs behaviorally while remaining obscured in self-attribution, motivating controlled behavioral audits beyond explanation-based evaluation.

Yuan Wang, Shengao Yi, Xiaojiang Li et al.

Heat exposure connects the built environment and public health, directly shaping the livability and sustainability of urban areas. Understanding the spatial heterogeneity of heat exposure and its drivers is vital for climate-adaptive urban planning. However, most planning-oriented studies rely on land surface temperature (LST), and whether LST adequately represents human heat exposure and how it differs from physiologically relevant heat stress remains insufficiently examined. Here, adopting Landsat-retrieved 30-m LST and GPU-accelerated 1-m universal thermal climate index (UTCI) in Singapore, this study establishes a comprehensive "Modeling-Comparing-Assessing" framework to systematically evaluate the spatial and mechanistic discrepancies between the two metrics. We further investigate pronounced non-stationary and threshold-based quantitative relationships of the two metrics with urban factors by employing a novel geographically weighted XGBoost (GW-XGBoost) and generalized additive model (GAM) workflow. Our results demonstrate notable discrepancies in spatial patterns of LST and UTCI, along with substantial spatial heterogeneity in how 2D and 3D urban factors impact these two thermal metrics, as revealed by explainable GW-XGBoost models (global out-of-bag R2 = 0.855 for LST and 0.905 for UTCI, respectively). Crucially, spatially explicit SHAP interprets that sky view factor plays a central role in explaining UTCI variability but exhibits a comparatively marginal independent contribution to LST, indicating that LST inadequately captures shading-driven and radiative processes governing actual human heat stress. Notably, SHAP-GAM analysis indicates that higher albedo is associated with increased UTCI. These novel findings provide evidence for integrating physiologically relevant thermal indices to inform targeted heat risk management and climate-adaptive urban planning.

Conghui Niu, Mengyang Hu, Lin Bo et al.

Existing propositions often rely on logical constants for classification. Compared with Western languages that lean towards hypotaxis such as English, Chinese often relies on semantic or logical understanding rather than logical connectives in daily expressions, exhibiting the characteristics of parataxis. However, existing research has rarely paid attention to this issue. And accurately classifying these propositions is crucial for natural language understanding and reasoning. In this paper, we put forward the concepts of explicit and implicit propositions and propose a comprehensive multi-level proposition classification system based on linguistics and logic. Correspondingly, we create a large-scale Chinese proposition dataset PEACE from multiple domains, covering all categories related to propositions. To evaluate the Chinese proposition classification ability of existing models and explore their limitations, We conduct evaluations on PEACE using several different methods including the Rule-based method, SVM, BERT, RoBERTA, and ChatGPT. Results show the importance of properly modeling the semantic features of propositions. BERT has relatively good proposition classification capability, but lacks cross-domain transferability. ChatGPT performs poorly, but its classification ability can be improved by providing more proposition information. Many issues are still far from being resolved and require further study.

Zhiyu Yang, Zihan Zhou, Shuo Wang et al.

Scientific data visualization plays a crucial role in research by enabling the direct display of complex information and assisting researchers in identifying implicit patterns. Despite its importance, the use of Large Language Models (LLMs) for scientific data visualization remains rather unexplored. In this study, we introduce MatPlotAgent, an efficient model-agnostic LLM agent framework designed to automate scientific data visualization tasks. Leveraging the capabilities of both code LLMs and multi-modal LLMs, MatPlotAgent consists of three core modules: query understanding, code generation with iterative debugging, and a visual feedback mechanism for error correction. To address the lack of benchmarks in this field, we present MatPlotBench, a high-quality benchmark consisting of 100 human-verified test cases. Additionally, we introduce a scoring approach that utilizes GPT-4V for automatic evaluation. Experimental results demonstrate that MatPlotAgent can improve the performance of various LLMs, including both commercial and open-source models. Furthermore, the proposed evaluation method shows a strong correlation with human-annotated scores.

Haoran Ma, Yan Zhang, Pengyuan Liu et al.

The Attention Restoration Theory (ART) presents a theoretical framework with four essential indicators (being away, extent, fascinating, and compatibility) for comprehending urban and natural restoration quality. However, previous studies relied on non-sequential data and non-spatial dependent methods, which overlooks the impact of spatial structure defined here as the positional relationships between scene entities on restoration quality. The past methods also make it challenging to measure restoration quality on an urban scale. In this work, a spatial-dependent graph neural networks (GNNs) approach is proposed to reveal the relation between spatial structure and restoration quality on an urban scale. Specifically, we constructed two different types of graphs at the street and city levels. The street-level graphs, using sequential street view images (SVIs) of road segments to capture position relationships between entities, were used to represent spatial structure. The city-level graph, modeling the topological relationships of roads as non-Euclidean data structures and embedding urban features (including Perception-features, Spatial-features, and Socioeconomic-features), was used to measure restoration quality. The results demonstrate that: 1) spatial-dependent GNNs model outperforms traditional methods (Acc = 0.735, F1 = 0.732); 2) spatial structure portrayed through sequential SVIs data significantly influences restoration quality; 3) spaces with the same restoration quality exhibited distinct spatial structures patterns. This study clarifies the association between spatial structure and restoration quality, providing a new perspective to improve urban well-being in the future.

Yunlong Liu, Shuyang Li, Pengyuan Liu et al.

Perception research is increasingly modelled using streetscapes, yet many approaches still rely on pixel features or object co-occurrence statistics, overlooking the explicit relations that shape human perception. This study proposes a three stage pipeline that transforms street view imagery (SVI) into structured representations for predicting six perceptual indicators. In the first stage, each image is parsed using an open-set Panoptic Scene Graph model (OpenPSG) to extract object predicate object triplets. In the second stage, compact scene-level embeddings are learned through a heterogeneous graph autoencoder (GraphMAE). In the third stage, a neural network predicts perception scores from these embeddings. We evaluate the proposed approach against image-only baselines in terms of accuracy, precision, and cross-city generalization. Results indicate that (i) our approach improves perception prediction accuracy by an average of 26% over baseline models, and (ii) maintains strong generalization performance in cross-city prediction tasks. Additionally, the structured representation clarifies which relational patterns contribute to lower perception scores in urban scenes, such as graffiti on wall and car parked on sidewalk. Overall, this study demonstrates that graph-based structure provides expressive, generalizable, and interpretable signals for modelling urban perception, advancing human-centric and context-aware urban analytics.

Binxian Su, Haoye Lou, Shucheng Zhu et al.

Large language models (LLMs) are being increasingly used in urban planning, but since gendered space theory highlights how gender hierarchies are embedded in spatial organization, there is concern that LLMs may reproduce or amplify such biases. We introduce SPAGBias - the first systematic framework to evaluate spatial gender bias in LLMs. It combines a taxonomy of 62 urban micro-spaces, a prompt library, and three diagnostic layers: explicit (forced-choice resampling), probabilistic (token-level asymmetry), and constructional (semantic and narrative role analysis). Testing six representative models, we identify structured gender-space associations that go beyond the public-private divide, forming nuanced micro-level mappings. Story generation reveals how emotion, wording, and social roles jointly shape "spatial gender narratives". We also examine how prompt design, temperature, and model scale influence bias expression. Tracing experiments indicate that these patterns are embedded and reinforced across the model pipeline (pre-training, instruction tuning, and reward modeling), with model associations found to substantially exceed real-world distributions. Downstream experiments further reveal that such biases produce concrete failures in both normative and descriptive application settings. This work connects sociological theory with computational analysis, extending bias research into the spatial domain and uncovering how LLMs encode social gender cognition through language.

Xuelin Liu, Yanfei Zhu, Shucheng Zhu et al.

Proper moral beliefs are fundamental for language models, yet assessing these beliefs poses a significant challenge. This study introduces a novel three-module framework to evaluate the moral beliefs of four prominent large language models. Initially, we constructed a dataset containing 472 moral choice scenarios in Chinese, derived from moral words. The decision-making process of the models in these scenarios reveals their moral principle preferences. By ranking these moral choices, we discern the varying moral beliefs held by different language models. Additionally, through moral debates, we investigate the firmness of these models to their moral choices. Our findings indicate that English language models, namely ChatGPT and Gemini, closely mirror moral decisions of the sample of Chinese university students, demonstrating strong adherence to their choices and a preference for individualistic moral beliefs. In contrast, Chinese models such as Ernie and ChatGLM lean towards collectivist moral beliefs, exhibiting ambiguity in their moral choices and debates. This study also uncovers gender bias embedded within the moral beliefs of all examined language models. Our methodology offers an innovative means to assess moral beliefs in both artificial and human intelligence, facilitating a comparison of moral values across different cultures.

Qing Dong, Pengyuan Liu, Dong Yu et al.

Generative agents have made significant progress in simulating human behavior, but existing frameworks often simplify emotional modeling and focus primarily on specific tasks, limiting the authenticity of the simulation. Our work proposes the Psychological-mechanism Agent (PSYA) framework, based on the Cognitive Triangle (Feeling-Thought-Action), designed to more accurately simulate human behavior. The PSYA consists of three core modules: the Feeling module (using a layer model of affect to simulate changes in short-term, medium-term, and long-term emotions), the Thought module (based on the Triple Network Model to support goal-directed and spontaneous thinking), and the Action module (optimizing agent behavior through the integration of emotions, needs and plans). To evaluate the framework's effectiveness, we conducted daily life simulations and extended the evaluation metrics to self-influence, one-influence, and group-influence, selection five classic psychological experiments for simulation. The results show that the PSYA framework generates more natural, consistent, diverse, and credible behaviors, successfully replicating human experimental outcomes. Our work provides a richer and more accurate emotional and cognitive modeling approach for generative agents and offers an alternative to human participants in psychological experiments.

Zicheng Fan, Kunihiko Fujiwara, Pengyuan Liu et al.

Visibility analysis is one of the fundamental analytics methods in urban planning and landscape research, traditionally conducted through computational simulations based on the Line-of-Sight (LoS) principle. However, when assessing the visibility of named urban objects such as landmarks, geometric intersection alone fails to capture the contextual and perceptual dimensions of visibility as experienced in the real world. The study challenges the traditional LoS-based approaches by introducing a new, image-based visibility analysis method. Specifically, a Vision Language Model (VLM) is applied to detect the target object within a direction-zoomed Street View Image (SVI). Successful detection represents the object's visibility at the corresponding SVI location. Further, a heterogeneous visibility graph is constructed to address the complex interaction between observers and target objects. In the first case study, the method proves its reliability in detecting the visibility of six tall landmark constructions in global cities, with an overall accuracy of 87%. Furthermore, it reveals broader contextual differences when the landmarks are perceived and experienced. In the second case, the proposed visibility graph uncovers the form and strength of connections for multiple landmarks along the River Thames in London, as well as the places where these connections occur. Notably, bridges on the River Thames account for approximately 30% of total connections. Our method complements and enhances traditional LoS-based visibility analysis, and showcases the possibility of revealing the prevalent connection of any visual objects in the urban environment. It opens up new research perspectives for urban planning, heritage conservation, and computational social science.

Hongliang Bi, Pengyuan Liu

Emotion cause analysis such as emotion cause extraction (ECE) and emotion-cause pair extraction (ECPE) have gradually attracted the attention of many researchers. However, there are still two shortcomings in the existing research: 1) In most cases, emotion expression and cause are not the whole clause, but the span in the clause, so extracting the clause-pair rather than the span-pair greatly limits its applications in real-world scenarios; 2) It is not enough to extract the emotion expression clause without identifying the emotion categories, the presence of emotion clause does not necessarily convey emotional information explicitly due to different possible causes. In this paper, we propose a new task: Emotion-Cause Span-Pair extraction and classification (ECSP), which aims to extract the potential span-pair of emotion and corresponding causes in a document, and make emotion classification for each pair. In the new ECSP task, ECE and ECPE can be regarded as two special cases at the clause-level. We propose a span-based extract-then-classify (ETC) model, where emotion and cause are directly extracted and paired from the document under the supervision of target span boundaries, and corresponding categories are then classified using their pair representations and localized context. Experiments show that our proposed ETC model outperforms the SOTA model of ECE and ECPE task respectively and gets a fair-enough results on ECSP task.

Pengyuan Liu, Yuning Deng, Chenghao Zhu et al.

We present XCMRC, the first public cross-lingual language understanding (XLU) benchmark which aims to test machines on their cross-lingual reading comprehension ability. To be specific, XCMRC is a Cross-lingual Cloze-style Machine Reading Comprehension task which requires the reader to fill in a missing word (we additionally provide ten noun candidates) in a sentence written in target language (English / Chinese) by reading a given passage written in source language (Chinese / English). Chinese and English are rich-resource language pairs, in order to study low-resource cross-lingual machine reading comprehension (XMRC), besides defining the common XCMRC task which has no restrictions on use of external language resources, we also define the pseudo low-resource XCMRC task by limiting the language resources to be used. In addition, we provide two baselines for common XCMRC task and two for pseudo XCMRC task respectively. We also provide an upper bound baseline for both tasks. We found that for common XCMRC task, translation-based method and multilingual sentence encoder-based method can obtain reasonable performance but still have much room for improvement. As for pseudo low-resource XCMRC task, due to strict restrictions on the use of language resources, our two approaches are far below the upper bound so there are many challenges ahead.

Pengyuan Liu, Chengyu Du, Shuofeng Zhao et al.

Many Natural Language Processing works on emotion analysis only focus on simple emotion classification without exploring the potentials of putting emotion into "event context", and ignore the analysis of emotion-related events. One main reason is the lack of this kind of corpus. Here we present Cause-Emotion-Action Corpus, which manually annotates not only emotion, but also cause events and action events. We propose two new tasks based on the data-set: emotion causality and emotion inference. The first task is to extract a triple (cause, emotion, action). The second task is to infer the probable emotion. We are currently releasing the data-set with 10,603 samples and 15,892 events, basic statistic analysis and baseline on both emotion causality and emotion inference tasks. Baseline performance demonstrates that there is much room for both tasks to be improved.