arXiv subjects

Hang Jiang

Publications and source records attributed to Hang Jiang.

At least 19 recordsLinked to original sources

arXiv2026

CHI-Bench: Can AI Agents Automate End-to-End, Long-Horizon, Policy-Rich Healthcare Workflows?

End-to-end automation of realistic healthcare operations stresses three capabilities underrepresented in current benchmarks: policy density, decisions must be grounded in a large library of medical, insurance, and operational rules; Multi-role composition: a single task requires the agent to play multiple roles with handoffs; and multilateral interaction: intermediate workflow steps are multi-turn dialogs, such as peer-to-peer review and patient outreach. We introduce $χ$-Bench, a benchmark of long-horizon healthcare workflows across three domains: provider prior authorization, payer utilization management, and care management. Each task hands the agent a clinical case in a high-fidelity simulator of 20 healthcare apps exposed via 87 MCP tools, which it must drive to a terminal status through tool calls and writing the role's artifacts, guided by a 1,290+ document managed-care operations handbook skill. Across 30 agent harness/models configurations, the best agent resolves only 28.0% of tasks, no agent clears 20% on strict pass^3, and executing all tasks in a single session slumps the performance to 3.8%. These results raise the hypothesis that similar gaps are likely to surface in other policy-dense, role-composed, irreversible enterprise domains.

cs.CL↗

arXiv2026

Lost in Translation: Investigating Systematic Discrepancies between Parallel English and Chinese Names of American Chinese Restaurants

Given that the Chinese are one of the oldest ethnic groups to immigrate to the US, their cuisine have become central to the US dining scene and an interesting avenue to study how Chinese immigrants have culturally adapted into American life. In that regard, previous research has focused on analyzing the English names that Chinese restaurants adopt, e.g., finding the use of familiar and typical words. To investigate how Chinese immigrants have culturally integrated in the US depending on social, geographic and demographic contexts, we investigate in this work the under-explored relationship between the Chinese and English names of American Chinese restaurants. Specifically, we conduct a study on 3,172 Chinese restaurants (10% of the total on Google Maps) sampled across the US. We present 8-dimension name frames to capture the underlying meanings behind names and create the NameFrames dataset containing 884 annotated parallel Chinese/English names. We also built an NLP pipeline to analyze the semantic discrepancies between names with both frame-based and embedding-based distance metrics. Our frame analysis shows that English names more often emphasize Location and Specialty, while Chinese names more often emphasize Positivity and Ambiance. Furthermore, we observe that for Chinese restaurants located in urban areas, those in counties with a higher concentration of Chinese population, or those that are relatively new, the discrepancies between the English and Chinese names are noticeably larger. Finally, interviews with 10 Chinese restaurant owners reveal additional interesting insights regarding naming conventions.

cs.CL↗

arXiv2026

ReactionBench: A Human-Anchored Benchmark for Modeling Reactions to Video

Understanding what happens in a video is not sufficient for socially responsive multimodal systems: such systems also aim to relate what a person observes to how that person responds. Existing video benchmarks largely evaluate events, temporal reasoning, or people depicted in the video, while affective and viewer-response datasets often focus on emotion labels, aggregate responses, or prediction from the stimulus alone. This leaves an underexplored question: can current multimodal models ground an observed viewer reaction in the stimulus context associated with it? We introduce ReactionBench, a human-anchored benchmark for reaction-specific video understanding. Built from a candidate pool of 31,834 synchronized stimulus-reaction clips spanning 433 hours and eight domains, ReactionBench evaluates three complementary abilities: ranking the intensity of a viewer's reactions within a video, matching a reaction to its temporally aligned stimulus, and explaining the concrete stimulus cues linked to that reaction. Human annotation provides 14,894 ratings over 3,257 moments, and the frozen evaluation comprises 250 intensity profiles, 112 matching items, and 200 rationale items with 447 blind-written human references. Across seven multimodal models, reaction-specific grounding remains challenging: the best model reaches 50.9% accuracy on four-way stimulus-reaction matching, while GPT-5 shows no detectable loss under reaction substitution. Performance is also sensitive to evaluation protocol. Project page: https://yibozh.github.io/ReactionBench-page/

cs.CV↗

arXiv2026

Knowing Is Not Telling: Identity Ossification in LLM Representations of Trans-border Communities

Ethnic and cultural identities rarely align with political borders, a tension made sharper by migration and long-standing cross-border ties. Communities such as the Sami, the Rohingya, and the Kurds have long lived across more than one state. This tension is especially clear in mainland Southeast Asia, where many communities share history, language, and culture across state lines. We study nine such transborder ethnic communities along China's southwestern border with mainland Southeast Asia, looking at how large language models (LLMs) represent them. We define and study identity ossification: a pattern where LLMs turn a fluid, cross-border ethnic identity into a single, fixed nation-state identity. We introduce the Transborder Identity Ossification Diagnostic Framework (TIODF) that compares direct factual questions with open-ended narrative questions to test whether ossification comes from missing knowledge or from how models frame their answers. We test GPT-5.1 and DeepSeek-V3.2 in English and Chinese. Ossification varies substantially across models and query languages. It appears in only 10.1% of GPT-5.1's English answers, but in 62.6% of DeepSeek-V3.2's Chinese answers. Models often still tell a single-nation story even when they answer the factual question correctly. This decoupling suggests that ossification reflects narrative framing rather than simple knowledge absence, which matters for how we test cultural fairness in multilingual AI systems.

cs.CY↗

arXiv2026

WS-NeRF: A Mamba-Driven World-State-Aware Adaptive Deblurring Neural Radiance Field

Neural Radiance Fields (NeRF) have attracted extensive attention in recent years due to their strong capability for high-quality 3D reconstruction and novel view synthesis from multi-view images. Existing methods usually rely on high-quality sharp inputs, while real-world image acquisition is highly susceptible to blur degradation, which severely affects the reconstruction quality of NeRF. In this paper, we propose a novel Mamba-driven world-state-aware adaptive deblurring neural radiance field, termed WS-NeRF, to address image degradation and 3D inconsistency. We formulate the alternating optimization of radiance fields as a dynamic evolution process with temporal memory, and jointly exploit comprehensive multi-dimensional world states and a mixture-of-experts mechanism to dynamically adjust the confidence of deblurring priors. Experimental results show that WS-NeRF significantly improves blurry radiance field reconstruction quality, achieving better performance on PSNR, SSIM, and LPIPS, while exhibiting more stable iterative recovery behavior.

eess.IV↗

arXiv2026

When Hiring Becomes Agent-Mediated: Evaluating Access and Recurrence in Two-Agent Résumé Screening

Hiring is bilateral: employers assess fit, while candidates present and defend evidence of their qualifications. Yet résumé screening, the first gate, is commonly automated as a static, one-call judgment over a résumé-job pair. We study a two-agent alternative in which employer-side and candidate-side agents represent these roles, exchange evidence, and update their judgments before deciding who advances. We compare procedures on 600 constructed résumé-job pairs using GPT-5.5 and Claude Opus 4.7. Two-agent screening advances more applications (33.3% to 39.3% for GPT-5.5; 34.0% to 35.5% for Opus 4.7). Across three runs on the common 191-pair borderline pool, pass-instance rates rise from 4.5% to 26.2% and from 6.5% to 16.1%, respectively. This is not a uniform relaxation: two-agent screening rejects applications one-call advances, changing decisions in both directions. At similar pass volumes, the procedures advance different applications, and no one-call threshold recovers applications consistently selected by two-agent screening. Among discovery-selected cases re-executed in fresh runs, two-agent-only selections recur less often than shared selections, clearly under GPT-5.5 and less certainly under Opus 4.7, while a separate one-call follow-up shows no comparable decline. As hiring becomes agent-mediated on both sides, the screening procedure, not only the model behind it, shapes who reaches human review and how reliably that access recurs.

cs.AI↗

arXiv2026

HugAgent: A Human Simulation Benchmark for Individual-Level Reasoning

Simulating human reasoning in open-ended tasks has long been a central aspiration in AI and cognitive science. While large language models now approximate human responses at scale, they remain tuned to population-level consensus, often erasing the individuality of reasoning styles and belief trajectories. To advance the vision of more human-like reasoning in machines, we introduce HugAgent (HUman-Grounded AGENT Benchmark), which rethinks human reasoning simulation along three dimensions: (i) from averaged to individualized reasoning, (ii) from behavioral mimicry to cognitive alignment, and (iii) from vignette-based to open-ended data. The benchmark evaluates whether a model can predict a specific person's behavioral responses and the underlying reasoning dynamics in out-of-distribution scenarios, given partial evidence of their prior views. HugAgent combines structured questionnaires with semi-structured think-aloud interviews to collect ecologically valid belief states, belief updates, and reasoning traces from human participants. Our experiments reveal a clear asymmetry: models recover a person's belief state from their own context reasonably well, but struggle to predict belief updates under intervention. Cross-person and cross-domain controls trace this gap to associative matching within a topic rather than identity-consistent reasoning, suggesting that progress requires better-calibrated change detection, not simply more context. We scope the benchmark to self-reported belief reasoning in three policy domains: healthcare, surveillance, and zoning. The benchmark, along with its complete data collection pipeline and companion chatbot, is open-sourced as HugAgent (https://github.com/jajamoa/HugAgent) and TraceYourThinking (https://github.com/jajamoa/trace-your-thinking).

cs.AI↗

arXiv2026

HealMed: Multilingual Evaluation of Large Language Models in Medicine

We present HealMed, an expert-reviewed benchmark for multilingual evaluation of large language models in medicine. HealMed contains 1,000 examples in each of nine languages, drawn from nine datasets and covering three task formats: MCQA, NLI and open-ended QA. The benchmark was developed over two years by 23 physicians and medical experts based across nine countries and regions. Each translation was evaluated and revised by two experts fluent in English and the corresponding target language. On HealMed, performance declined most in low-resource languages, although the size of the gap varied markedly across languages and models. The strongest proprietary models were the most stable across languages, whereas many open-source and medically specialized models showed larger and less consistent gaps. Medical specialization alone did not ensure multilingual robustness. Furthermore, expert revision could either raise or lower measured performance, indicating that translation quality materially affects cross-language evaluation results.

cs.CL↗

arXiv2026

FaciliTrain: Practicing Facilitation Skills through AI-Simulated Group Dialogue

Skilled facilitation supports inclusive small-group dialogue, but deliberate practice is hard to scale: it depends on expert coaches, live practice partners, and iterative feedback. We present FaciliTrain, a voice-based training system in which learners step into the facilitator role of an AI-simulated multi-participant conversation, apply five evidence-based techniques, and receive structured AI feedback to support reflection. We report findings from a mixed-methods study with 24 participants, conducted as a formative study (N = 12) and a controlled pilot (N = 12; 6 treatment, 6 control). Both conditions achieved comparable accuracy on a live evaluation task, though treatment participants' self-rated comfort declined significantly while control participants' comfort improved (p = .018). Reflexive thematic analysis identifies four themes: the taxonomy externalizes implicit facilitation intuitions; Making Connections is the most cognitively demanding technique; voice acts as a deliberate-response forcing function; and participants overwhelmingly preferred AI feedback over self-practice. We discuss design implications for voice-based, AI-supported interpersonal skill training at scale.

cs.HC↗

arXiv2025

An Implementation Relaxation Approach to Principal-Agent Problems

The classic first-order approach (FOA) relaxes the principal-agent problem by replacing the incentive compatibility (IC) constraint with its first-order condition. We show that FOA is not a valid relaxation when the support of the outcome distribution shifts with the agent's effort, as in well-studied additive-noise models. In such cases, the optimal effort may occur at a kink point that the first-order condition cannot capture, causing FOA to miss optimal contracts, including the widely adopted bonus schemes. Motivated by this limitation, we introduce the Implementation Relaxation Approach (IRA), which accommodates nondifferentiable optima and is straightforward to apply across settings. Rather than directly relaxing IC, IRA relaxes the set of implementable agent efforts and utilities, reducing the problem to identifying the effort-utility pair from which the optimal contract can be constructed. This inverse perspective is particularly convenient for analyzing simple contracts. Using IRA, we derive an optimality condition for quota-bonus contracts that is more general than FOA-based conditions, including those established in the literature under fixed-support assumptions. This also fills a gap where the optimality of quota-bonus contracts in shifting-support settings has been examined only under endogenous assumptions, and it highlights the broader applicability of IRA as a methodological tool.

econ.TH↗

arXiv2025

Human-AI Narrative Synthesis to Foster Shared Understanding in Civic Decision-Making

Community engagement processes in representative political contexts, like school districts, generate massive volumes of feedback that overwhelm traditional synthesis methods, creating barriers to shared understanding not only between civic leaders and constituents but also among community members. To address these barriers, we developed StoryBuilder, a human-AI collaborative pipeline that transforms community input into accessible first-person narratives. Using 2,480 community responses from an ongoing school rezoning process, we generated 124 composite stories and deployed them through a mobile-friendly StorySharer interface. Our mixed-methods evaluation combined a four-month field deployment, user studies with 21 community members, and a controlled experiment examining how narrative composition affects participant reactions. Field results demonstrate that narratives helped community members relate across diverse perspectives. In the experiment, experience-grounded narratives generated greater respect and trust than opinion-heavy narratives. We contribute a human-AI narrative synthesis system and insights on its varied acceptance and effectiveness in a real-world civic context.

cs.HC↗

arXiv2025

HealthGenie: Empowering Users with Healthy Dietary Guidance through Knowledge Graph and Large Language Models

Seeking dietary guidance often requires navigating complex professional knowledge while accommodating individual health conditions. Knowledge Graphs (KGs) offer structured and interpretable nutritional information, whereas Large Language Models (LLMs) naturally facilitate conversational recommendation delivery. In this paper, we present HealthGenie, an interactive system that combines the strengths of LLMs and KGs to provide personalized dietary recommendations along with hierarchical information visualization for a quick and intuitive overview. Upon receiving a user query, HealthGenie performs query refinement and retrieves relevant information from a pre-built KG. The system then visualizes and highlights pertinent information, organized by defined categories, while offering detailed, explainable recommendation rationales. Users can further tailor these recommendations by adjusting preferences interactively. Our evaluation, comprising a within-subject comparative experiment and an open-ended discussion, demonstrates that HealthGenie effectively supports users in obtaining personalized dietary guidance based on their health conditions while reducing interaction effort and cognitive load. These findings highlight the potential of LLM-KG integration in supporting decision-making through explainable and visualized information. We examine the system's usefulness and effectiveness with an N=12 within-subject study and provide design considerations for future systems that integrate conversational LLM and KG.

cs.HC↗

arXiv2025

Automatic Detection of Research Values from Scientific Abstracts Across Computer Science Subfields

The field of Computer science (CS) has rapidly evolved over the past few decades, providing computational tools and methodologies to various fields and forming new interdisciplinary communities. This growth in CS has significantly impacted institutional practices and relevant research communities. Therefore, it is crucial to explore what specific research values, known as basic and fundamental beliefs that guide or motivate research attitudes or actions, CS-related research communities promote. Prior research has manually analyzed research values from a small sample of machine learning papers. No prior work has studied the automatic detection of research values in CS from large-scale scientific texts across different research subfields. This paper introduces a detailed annotation scheme featuring ten research values that guide CS-related research. Based on the scheme, we build value classifiers to scale up the analysis and present a systematic study over 226,600 paper abstracts from 32 CS-related subfields and 86 popular publishing venues over ten years.

cs.CL↗

arXiv2024

AudienceView: AI-Assisted Interpretation of Audience Feedback in Journalism

Understanding and making use of audience feedback is important but difficult for journalists, who now face an impractically large volume of audience comments online. We introduce AudienceView, an online tool to help journalists categorize and interpret this feedback by leveraging large language models (LLMs). AudienceView identifies themes and topics, connects them back to specific comments, provides ways to visualize the sentiment and distribution of the comments, and helps users develop ideas for subsequent reporting projects. We consider how such tools can be useful in a journalist's workflow, and emphasize the importance of contextual awareness and human judgment.

cs.HC↗

arXiv2024

Bridging Dictionary: AI-Generated Dictionary of Partisan Language Use

Words often carry different meanings for people from diverse backgrounds. Today's era of social polarization demands that we choose words carefully to prevent miscommunication, especially in political communication and journalism. To address this issue, we introduce the Bridging Dictionary, an interactive tool designed to illuminate how words are perceived by people with different political views. The Bridging Dictionary includes a static, printable document featuring 796 terms with summaries generated by a large language model. These summaries highlight how the terms are used distinctively by Republicans and Democrats. Additionally, the Bridging Dictionary offers an interactive interface that lets users explore selected words, visualizing their frequency, sentiment, summaries, and examples across political divides. We present a use case for journalists and emphasize the importance of human agency and trust in further enhancing this tool. The deployed version of Bridging Dictionary is available at https://dictionary.ccc-mit.org/.

cs.HC↗

arXiv2024

ConGraT: Self-Supervised Contrastive Pretraining for Joint Graph and Text Embeddings

Learning on text-attributed graphs (TAGs), in which nodes are associated with one or more texts, has been the subject of much recent work. However, most approaches tend to make strong assumptions about the downstream task of interest, are reliant on hand-labeled data, or fail to equally balance the importance of both text and graph representations. In this work, we propose Contrastive Graph-Text pretraining (ConGraT), a general, self-supervised approach for jointly learning separate representations of texts and nodes in a TAG. Our method trains a language model (LM) and a graph neural network (GNN) to align their representations in a common latent space using a batch-wise contrastive learning objective inspired by CLIP. We further propose an extension to the CLIP objective that leverages graph structure to incorporate information about inter-node similarity. Extensive experiments demonstrate that ConGraT outperforms baselines on various downstream tasks, including node and text category classification, link prediction, and language modeling. Finally, we present an application of our method to community detection in social graphs, which enables finding more textually grounded communities, rather than purely graph-based ones. Code and certain datasets are available at https://github.com/wwbrannon/congrat.

cs.CL↗

arXiv2024

Leveraging Large Language Models for Learning Complex Legal Concepts through Storytelling

Making legal knowledge accessible to non-experts is crucial for enhancing general legal literacy and encouraging civic participation in democracy. However, legal documents are often challenging to understand for people without legal backgrounds. In this paper, we present a novel application of large language models (LLMs) in legal education to help non-experts learn intricate legal concepts through storytelling, an effective pedagogical tool in conveying complex and abstract concepts. We also introduce a new dataset LegalStories, which consists of 294 complex legal doctrines, each accompanied by a story and a set of multiple-choice questions generated by LLMs. To construct the dataset, we experiment with various LLMs to generate legal stories explaining these concepts. Furthermore, we use an expert-in-the-loop approach to iteratively design multiple-choice questions. Then, we evaluate the effectiveness of storytelling with LLMs through randomized controlled trials (RCTs) with legal novices on 10 samples from the dataset. We find that LLM-generated stories enhance comprehension of legal concepts and interest in law among non-native speakers compared to only definitions. Moreover, stories consistently help participants relate legal concepts to their lives. Finally, we find that learning with stories shows a higher retention rate for non-native speakers in the follow-up assessment. Our work has strong implications for using LLMs in promoting teaching and learning in the legal field and beyond.

cs.CL↗

arXiv2024

Large Language Models on Wikipedia-Style Survey Generation: an Evaluation in NLP Concepts

Educational materials such as survey articles in specialized fields like computer science traditionally require tremendous expert inputs and are therefore expensive to create and update. Recently, Large Language Models (LLMs) have achieved significant success across various general tasks. However, their effectiveness and limitations in the education domain are yet to be fully explored. In this work, we examine the proficiency of LLMs in generating succinct survey articles specific to the niche field of NLP in computer science, focusing on a curated list of 99 topics. Automated benchmarks reveal that GPT-4 surpasses its predecessors, inluding GPT-3.5, PaLM2, and LLaMa2 by margins ranging from 2% to 20% in comparison to the established ground truth. We compare both human and GPT-based evaluation scores and provide in-depth analysis. While our findings suggest that GPT-created surveys are more contemporary and accessible than human-authored ones, certain limitations were observed. Notably, GPT-4, despite often delivering outstanding content, occasionally exhibited lapses like missing details or factual errors. At last, we compared the rating behavior between humans and GPT-4 and found systematic bias in using GPT evaluation.

cs.CL↗