arXiv subjects

Yilin Jiang

Publications and source records attributed to Yilin Jiang.

11 recordsLinked to original sources

arXiv2026

A Co-Simulation Platform Coupling Land Use, Transportation, and Building Energy: Development and Case Study

Land use, transportation, and building energy shape one another, yet urban-scale studies typically model each sector in isolation. We present a co-simulation platform that couples the UrbanSim land-use model, the POLARIS agent-based transportation model, and the CityBES urban building energy model into a single integrated workflow, with POLARIS travel skims driving land use and POLARIS agent activities driving dynamic building occupancy. We demonstrate the platform with forecasts through 2045 for the Chicago metropolitan area under a business-as-usual case, a high-telecommuting scenario, and a mileage-based user fee scenario. Both policies produced expected-direction responses that emerged from the model feedbacks rather than being imposed. Telecommuting decentralized activity toward outlying areas and cut 2045 vehicle miles traveled by 12.5%, whereas the mileage fee recentralized activity toward the urban core and cut it by 2.9%. Comparing coupled runs against uncoupled runs that hold land use fixed shows that the land-use feedback contributes over one percentage point to the county-level travel effect in several counties, large relative to the policy effect itself since the mileage fee's county-level effects are only about three percent, so a transportation-only study would materially misstate the sub-regional impact. Both policies raised citywide building energy by about 1%. This is the first platform to integrate land use, transportation, and building energy simultaneously, replacing predefined occupancy schedules and static building stocks with endogenous agent-based occupancy and a forecast-driven building stock. It lets planners evaluate transportation and pricing policies for their joint land use, travel, and energy consequences, and its component models rely on nationally available data, making the approach transferable given local building-stock and calibration data.

cs.CE↗

arXiv2026

ADE: Agentic Data Evolution Framework for Human-Centered Objectives

Aligning large language models to human-centered objectives is difficult when targets are non-executable and context-dependent, limiting reliable verification and scalable supervision. Although synthetic data expands coverage, weak verification shifts the bottleneck from generation to selection. Noisy signals destabilize iterative refinement and can cause silent regressions. We propose Agentic Data Evolution (ADE), a data-centric framework that organizes synthetic supervision as evolving data snapshots. ADE improves data snapshots through a closed-loop Observation-Variation-Selection (OVS) procedure, where a steady-state admission mechanism acts as a quality ratchet that conservatively gates updates for sustained cross-round improvement. We validate these improvements through complementary intrinsic trend tracking and extrinsic post-training evaluation. On DEV300, ADE raises the intrinsic win rate from 50% to 75.81% and the extrinsic win rate from 55.20% to 68.86%, consistent performance gains across diverse benchmarks. Blind expert evaluation further confirms this, with a 66.11% preference for evolved answers. These gains extend across post-training methods, model scales, and tasks beyond the target weakly verifiable educational objectives. Resources are available at https://github.com/ZeroLoss-Lab/Agentic-Data-Evolution.

cs.CL↗

arXiv2026

ELBench: A Multi-Dimensional Benchmark for Education-Facing Large Language Models

Large language models are increasingly deployed in education as tutors, teaching assistants, and content generators. These roles place demands that ordinary question answering does not: a usable education-facing model is supposed to be accurate, safe under sensitive prompts, instructionally useful, and aligned with pedagogical goals at the same time. Existing benchmarks evaluate these requirements largely in isolation, so none assesses education-facing suitability as an integrated profile. We introduce ELBench, the first benchmark to evaluate all four requirements (General Capability, Safety and Trustworthiness, Basic Education, and High-Level Cultivation) on the same models under a common protocol, combining curated public sources with newly synthesized safety and cultivation data. We evaluate nine models, seven frontier general-purpose systems and two education-specialized variants, and report three findings. First, module-level profiles are more informative than a single aggregate: the top six models are statistically indistinguishable on overall score, yet their module leaders differ substantially, and safety is anti-correlated with practical teaching (r = -0.83). Second, the Chinese-developed models lead the safety module, the most discriminative in the suite; this advantage is largest on region-specific normative content and narrows, but does not vanish, on universal-harm content. Third, the two education-specialized models lead neither education module, and on High-Level Cultivation all models share a systematic blind spot: on the structured judgment task they converge on the same non-reference option, favoring pedagogical style over fit to the stated goal, so the module scores uniformly low and does not separate models. This raises, but does not resolve, whether domain post-training keeps pace with frontier systems on education tasks.

cs.CL↗

arXiv2026

DoubtProbe: Black-Box Jailbreak Defense via Structural Verification and Semantic Auditing

As large language models (LLMs) are increasingly deployed in user-facing systems, black-box jailbreak defense has become an important practical problem. Existing defenses often rely on known-attack coverage, prompt-level semantic judgment, or local runtime control, yet these paths can become unstable under evolving prompt packaging, expression rewriting, and structure manipulation. We observe that many black-box jailbreaks do not remove the harmful goal, but reorganize the information needed to express and execute it, thereby evading safety alignment while remaining recoverable during generation. Motivated by this observation, we propose DoubtProbe, a dual-branch inference-time defense framework that combines structural verification with semantic auditing and formulates black-box jailbreak defense as consistency checking under controlled transformation. The structural branch extracts a structured representation from the original request, reconstructs the request under representation constraints, and detects information-preservation failures between the original and reconstructed requests; the semantic branch audits the original prompt directly. We evaluate DoubtProbe against representative black-box defenses on jailbreak and benign-request benchmarks, and further test backbone transfer from Qwen2.5-72B to Llama-3.1-70B. Results show that DoubtProbe achieves a stronger and more stable defense-utility trade-off: on Qwen2.5-72B, it reduces the JBB attack success rate from 0.293 to 0.100 and the CodeAttack attack success rate from 0.152 to 0.001, while maintaining false positive rates of 0.022 and 0.016 on AlpacaEval and OR-Bench; the same pattern remains stable on Llama-3.1-70B. These findings show that structural inconsistency signals provide a practical and generalizable basis for black-box jailbreak defense, especially when combined with semantic auditing.

cs.CR↗

arXiv2026

HACHIMI: Scalable and Controllable Student Persona Generation via Orchestrated Agents

Student Personas (SPs) are emerging as infrastructure for educational LLMs, yet prior work often relies on ad-hoc prompting or hand-crafted profiles with limited control over educational theory and population distributions. We formalize this as Theory-Aligned and Distribution-Controllable Persona Generation (TAD-PG) and introduce HACHIMI, a multi-agent Propose-Validate-Revise framework that generates theory-aligned, quota-controlled personas. HACHIMI factorizes each persona into a theory-anchored educational schema, enforces developmental and psychological constraints via a neuro-symbolic validator, and combines stratified sampling with semantic deduplication to reduce mode collapse. The resulting HACHIMI-1M corpus comprises 1 million personas for Grades 1-12. Intrinsic evaluation shows near-perfect schema validity, accurate quotas, and substantial diversity, while external evaluation instantiates personas as student agents answering CEPS and PISA 2022 surveys; across 16 cohorts, math and curiosity/growth constructs align strongly between humans and agents, whereas classroom-climate and well-being constructs are only moderately aligned, revealing a fidelity gradient. All personas are generated with Qwen2.5-72B, and HACHIMI provides a standardized synthetic student population for group-level benchmarking and social-science simulations. Resources available at https://github.com/ZeroLoss-Lab/HACHIMI

cs.CL↗

arXiv2025

MiMo-Audio: Audio Language Models are Few-Shot Learners

Existing audio language models typically rely on task-specific fine-tuning to accomplish particular audio tasks. In contrast, humans are able to generalize to new audio tasks with only a few examples or simple instructions. GPT-3 has shown that scaling next-token prediction pretraining enables strong generalization capabilities in text, and we believe this paradigm is equally applicable to the audio domain. By scaling MiMo-Audio's pretraining data to over one hundred million of hours, we observe the emergence of few-shot learning capabilities across a diverse set of audio tasks. We develop a systematic evaluation of these capabilities and find that MiMo-Audio-7B-Base achieves SOTA performance on both speech intelligence and audio understanding benchmarks among open-source models. Beyond standard metrics, MiMo-Audio-7B-Base generalizes to tasks absent from its training data, such as voice conversion, style transfer, and speech editing. MiMo-Audio-7B-Base also demonstrates powerful speech continuation capabilities, capable of generating highly realistic talk shows, recitations, livestreaming and debates. At the post-training stage, we curate a diverse instruction-tuning corpus and introduce thinking mechanisms into both audio understanding and generation. MiMo-Audio-7B-Instruct achieves open-source SOTA on audio understanding benchmarks (MMSU, MMAU, MMAR, MMAU-Pro), spoken dialogue benchmarks (Big Bench Audio, MultiChallenge Audio) and instruct-TTS evaluations, approaching or surpassing closed-source models. Model checkpoints and full evaluation suite are available at https://github.com/XiaomiMiMo/MiMo-Audio.

cs.CL↗

arXiv2025

EduGuardBench: A Holistic Benchmark for Evaluating the Pedagogical Fidelity and Adversarial Safety of LLMs as Simulated Teachers

Large Language Models for Simulating Professions (SP-LLMs), particularly as teachers, are pivotal for personalized education. However, ensuring their professional competence and ethical safety is a critical challenge, as existing benchmarks fail to measure role-playing fidelity or address the unique teaching harms inherent in educational scenarios. To address this, we propose EduGuardBench, a dual-component benchmark. It assesses professional fidelity using a Role-playing Fidelity Score (RFS) while diagnosing harms specific to the teaching profession. It also probes safety vulnerabilities using persona-based adversarial prompts targeting both general harms and, particularly, academic misconduct, evaluated with metrics including Attack Success Rate (ASR) and a three-tier Refusal Quality assessment. Our extensive experiments on 14 leading models reveal a stark polarization in performance. While reasoning-oriented models generally show superior fidelity, incompetence remains the dominant failure mode across most models. The adversarial tests uncovered a counterintuitive scaling paradox, where mid-sized models can be the most vulnerable, challenging monotonic safety assumptions. Critically, we identified a powerful Educational Transformation Effect: the safest models excel at converting harmful requests into teachable moments by providing ideal Educational Refusals. This capacity is strongly negatively correlated with ASR, revealing a new dimension of advanced AI safety. EduGuardBench thus provides a reproducible framework that moves beyond siloed knowledge tests toward a holistic assessment of professional, ethical, and pedagogical alignment, uncovering complex dynamics essential for deploying trustworthy AI in education. See https://github.com/YL1N/EduGuardBench for Materials.

cs.CL↗

arXiv2025

EMNLP: Educator-role Moral and Normative Large Language Models Profiling

Simulating Professions (SP) enables Large Language Models (LLMs) to emulate professional roles. However, comprehensive psychological and ethical evaluation in these contexts remains lacking. This paper introduces EMNLP, an Educator-role Moral and Normative LLMs Profiling framework for personality profiling, moral development stage measurement, and ethical risk under soft prompt injection. EMNLP extends existing scales and constructs 88 teacher-specific moral dilemmas, enabling profession-oriented comparison with human teachers. A targeted soft prompt injection set evaluates compliance and vulnerability in teacher SP. Experiments on 14 LLMs show teacher-role LLMs exhibit more idealized and polarized personalities than human teachers, excel in abstract moral reasoning, but struggle with emotionally complex situations. Models with stronger reasoning are more vulnerable to harmful prompt injection, revealing a paradox between capability and safety. The model temperature and other hyperparameters have limited influence except in some risk behaviors. This paper presents the first benchmark to assess ethical and psychological alignment of teacher-role LLMs for educational AI. Resources are available at https://e-m-n-l-p.github.io/.

cs.CL↗

arXiv2025

ArtMentor: AI-Assisted Evaluation of Artworks to Explore Multimodal Large Language Models Capabilities

Can Multimodal Large Language Models (MLLMs), with capabilities in perception, recognition, understanding, and reasoning, function as independent assistants in art evaluation dialogues? Current MLLM evaluation methods, which rely on subjective human scoring or costly interviews, lack comprehensive coverage of various scenarios. This paper proposes a process-oriented Human-Computer Interaction (HCI) space design to facilitate more accurate MLLM assessment and development. This approach aids teachers in efficient art evaluation while also recording interactions for MLLM capability assessment. We introduce ArtMentor, a comprehensive space that integrates a dataset and three systems to optimize MLLM evaluation. The dataset consists of 380 sessions conducted by five art teachers across nine critical dimensions. The modular system includes agents for entity recognition, review generation, and suggestion generation, enabling iterative upgrades. Machine learning and natural language processing techniques ensure the reliability of evaluations. The results confirm GPT-4o's effectiveness in assisting teachers in art evaluation dialogues. Our contributions are available at https://artmentor.github.io/.

cs.HC↗

arXiv2024

A general approach to fitting multistate cure models based on an extended-long-format data structure

A multistate cure model is a statistical framework used to analyze and represent the transitions individuals undergo between different states over time, accounting for the possibility of being cured by initial treatment. This model is particularly useful in pediatric oncology where a proportion of the patient population achieves cure through treatment and therefore will never experience certain events. Despite its importance, no universal consensus exists on the structure of multistate cure models. Our study provides a novel framework for defining such models through a set of non-cure states. We develops a generalized algorithm based on the extended long data format, an extension of the traditional long data format, where a transition can be divided into two rows, each with a weight assigned reflecting the posterior probability of its cure status. The multistate cure model is built upon the current framework of multistate model and mixture cure model. The proposed algorithm makes use of the Expectation-Maximization (EM) algorithm and weighted likelihood representation such that it is easy to implement with standard packages. Additionally, it facilitates dynamic prediction. The algorithm is applied on data from the European Society for Blood and Marrow Transplantation (EBMT). Standard errors of the estimated parameters in the EM algorithm are obtained via a non-parametric bootstrap procedure, while the method involving the calculation of the second-derivative matrix of the observed log-likelihood is also presented.

stat.ME↗

arXiv2024

Fast High-Quality Enhanced Imaging Algorithm for Layered Dielectric Targets Based on MMW MIMO-SAR System

Millimeter-wave (MMW) multiple-input multiple-output synthetic aperture radar (MIMO-SAR) system is a technology that can achieve high resolution, high frame rate, and all-weather imaging and has received extensive attention in the non-destructive testing and internal imaging applications of layered dielectric targets. However, the non-ideal scattering effect caused by dielectric materials can significantly deteriorate the imaging quality when using the existing MIMO-SAR fast algorithms. This paper proposes a rapid, high-quality dielectric target-enhanced imaging algorithm for a new universal non-uniform MIMO-SAR system. The algorithm builds on the existing non-uniform MIMO-SAR dielectric target frequency-domain algorithm (DT-FDA) by constructing a forward sensing operator and incorporating it into the alternating direction method of multipliers (ADMM) framework. This approach avoids large matrix operations while maintaining computational efficiency. By integrating an optimal regularization parameter search, the algorithm enhances the image reconstruction quality of dielectric internal structures or defects. Experimental results show the proposed algorithm outperforms IBP and DT-FDA, achieving better focusing, sidelobe suppression, and 3D imaging accuracy. It yields the lowest image entropy (8.864) and significantly improves efficiency (imaging time: 15.29 s vs. 23295.3 s for IBP).

eess.SP↗