arXiv subjects

Shijie Chen

Publications and source records attributed to Shijie Chen.

At least 19 recordsLinked to original sources

arXiv2026

Lost at the End: Primacy Bias in Multimodal Retrieval-Augmented Question Answering

Knowledge-based visual question answering (KB-VQA) lets vision-language systems answer questions that exceed their parametric knowledge by conditioning a reader on passages retrieved from a Wikipedia-scale knowledge base. In pure-text long-context LLMs, retrieved-context use follows the U-shaped "lost-in-the-middle" effect of Liu et al. (2024): information at the start and end of context is used, the middle is lost. Whether this transfers to deployed multimodal KB-VQA is open. To close this gap, we design the first controlled probe of reader-side position dependence in multimodal KB-VQA: a gold-position protocol in which only the gold passage's prompt slot varies within question. We run it on three open-source 7B/8B VLM readers and two KB-VQA benchmarks at k up to 20. The shape flips from U to primacy: gold-at-first beats gold-at-last by 16 to 26 points on every reader-by-benchmark cell, an effect we call "Lost at the End". Three targeted ablations narrow the cause: a text-only control shows the multimodal setting amplifies an already-present text-mode primacy 2.2 to 4.5 times, and image-position and distractor-shuffle ablations together pin the locus to prompt slot 0 of the instruction-tuned reader. On a frozen reader, three retrieval-side fixes (MMR, oracle reranking, rank-based reordering) all leave the gap intact (no separable improvement). Our findings indicate that recall@k is the wrong metric for deployed KB-VQA and that closing the gap requires reader-side intervention; we release our protocol as a controlled instrument for evaluating such interventions.

cs.CL↗

arXiv2026

Can Post-Training Turn LLMs into Good Medical Coders? An Empirical Study of Generative ICD Coding

Automated International Classification of Diseases (ICD) coding is a core medical-coding task for billing, epidemiology, and clinical decision support. Generative large language models (LLMs) are often reported as weak medical coders, but this finding mainly comes from inference-time settings such as prompting, retrieval, reranking, or tool use, leaving the role of task-specific post-training underexplored. We present a controlled empirical study of post-training for generative ICD coding, comparing discriminative baselines with LLM coders across prompting, supervised fine-tuning, and reinforcement learning under a common protocol and metric set. To our knowledge, this is the first study to evaluate RL-based post-training for generative LLM coders in ICD coding. We further introduce PHI, a diagnostic curriculum that extends GRPO to refine missed-code cases. Our results show that prompting-only evaluation substantially underestimates the potential of LLMs for ICD coding. SFT provides the main capability jump, GRPO further improves code-set prediction beyond SFT, and PHI provides targeted gains on macro-level performance. These findings suggest that the main bottleneck is not the generative formulation alone, but how the model is adapted and optimized for full-taxonomy recall. We release our code, data splits, and checkpoints at https://github.com/AlexandreWANG915/LLM4ICD.

cs.CL↗

arXiv2026

QUEST: Training Frontier Deep Research Agents with Fully Synthetic Tasks

Deep research agents extend the role of search engines from retrieving keyword-matched pages to synthesizing knowledge, fundamentally changing how humans interact with information. However, frontier systems remain proprietary, while existing open agents often generalize poorly across different task types, leaving unclear how to train a broadly capable deep research agent. We release QUEST, a family of open models (ranging from 2B to 35B) that serve as general-purpose deep research agents designed to handle a wide range of long-horizon search tasks, with strong capabilities in fact seeking, citation grounding, and report synthesis. To build QUEST, we propose an effective training recipe combining mid-training, supervised fine-tuning, and reinforcement learning. Central to this recipe is a curated data synthesis pipeline based on unified rubric trees, which applies to different task types and enables synthesizing training data with verifiable rewards without human annotation. In addition, QUEST incorporates a built-in context management mechanism that enables effective long-horizon reasoning and knowledge synthesis. Using only 8K synthesized tasks, QUEST approaches or even surpasses frontier closed-source agents across eight deep research benchmarks spanning diverse task types, and achieves the best overall performance among recent open-weight agents. We released everything: models, data, and training scripts.

cs.CL↗

arXiv2026

A Rolling-Horizon Stochastic Optimization Framework for NBA Franchise Management with Distributionally Robust Risk Constraints

NBA franchise management is not a sequence of independent tasks, but a single dynamic control problem in which roster construction, cash-flow discipline, media strategy, external market shocks, and player-health uncertainty interact over time. Using the New York Knicks as a case study, this paper develops a unified decision architecture for franchise management under competitive, financial, and regulatory constraints. The core layer is formulated as a rolling-horizon stochastic mixed-integer program augmented with distributionally robust optimization and conditional value-at-risk constraints, so that long-run franchise value can be optimized while downside exposure remains explicitly controlled. On top of this core layer, we construct coordinated modules for transaction execution, league-expansion shock transmission, media-rights regime transition, and injury-triggered re-optimization. This integrated design reframes multiple managerial mechanisms inside one research problem: how should an NBA franchise allocate resources and update decisions when performance objectives and commercial objectives are jointly determined under uncertainty? The manuscript is organized around problem formulation, model architecture, empirical validation, robustness analysis, and managerial interpretation.

cs.CE↗

arXiv2026

ECGomics: An Open Platform for AI-ECG Digital Biomarker Discovery

Background: Conventional electrocardiogram (ECG) analysis faces a persistent dichotomy: expert-driven features ensure interpretability but lack sensitivity to latent patterns, while deep learning offers high accuracy but functions as a black box with high data dependency. We introduce ECGomics, a systematic paradigm and open-source platform for the multidimensional deconstruction of cardiac signals into digital biomarker. Methods: Inspired by the taxonomic rigor of genomics, ECGomics deconstructs cardiac activity across four dimensions: Structural, Intensity, Functional, and Comparative. This taxonomy synergizes expert-defined morphological rules with data-driven latent representations, effectively bridging the gap between handcrafted features and deep learning embeddings. Results: We operationalized this framework into a scalable ecosystem consisting of a web-based research platform and a mobile-integrated solution (https://github.com/PKUDigitalHealth/ECGomics). The web platform facilitates high-throughput analysis via precision parameter configuration, high-fidelity data ingestion, and 12-lead visualization, allowing for the systematic extraction of biomarkers across the four ECGomics dimensions. Complementarily, the mobile interface, integrated with portable sensors and a cloud-based engine, enables real-time signal acquisition and near-instantaneous delivery of structured diagnostic reports. This dual-interface architecture successfully transitions ECGomics from theoretical discovery to decentralized, real-world health management, ensuring professional-grade monitoring in diverse clinical and home-based settings. Conclusion: ECGomics harmonizes diagnostic precision, interpretability, and data efficiency. By providing a deployable software ecosystem, this paradigm establishes a robust foundation for digital biomarker discovery and personalized cardiovascular medicine.

q-bio.QM↗

arXiv2025

FreeGen: Feed-Forward Reconstruction-Generation Co-Training for Free-Viewpoint Driving Scene Synthesis

Closed-loop simulation and scalable pre-training for autonomous driving require synthesizing free-viewpoint driving scenes. However, existing datasets and generative pipelines rarely provide consistent off-trajectory observations, limiting large-scale evaluation and training. While recent generative models demonstrate strong visual realism, they struggle to jointly achieve interpolation consistency and extrapolation realism without per-scene optimization. To address this, we propose FreeGen, a feed-forward reconstruction-generation co-training framework for free-viewpoint driving scene synthesis. The reconstruction model provides stable geometric representations to ensure interpolation consistency, while the generation model performs geometry-aware enhancement to improve realism at unseen viewpoints. Through co-training, generative priors are distilled into the reconstruction model to improve off-trajectory rendering, and the refined geometry in turn offers stronger structural guidance for generation. Experiments demonstrate that FreeGen achieves state-of-the-art performance for free-viewpoint driving scene synthesis.

cs.CV↗

arXiv2025

GeoAnalystBench: A GeoAI benchmark for assessing large language models for spatial analysis workflow and code generation

Recent advances in large language models (LLMs) have fueled growing interest in automating geospatial analysis and GIS workflows, yet their actual capabilities remain uncertain. In this work, we call for rigorous evaluation of LLMs on well-defined geoprocessing tasks before making claims about full GIS automation. To this end, we present GeoAnalystBench, a benchmark of 50 Python-based tasks derived from real-world geospatial problems and carefully validated by GIS experts. Each task is paired with a minimum deliverable product, and evaluation covers workflow validity, structural alignment, semantic similarity, and code quality (CodeBLEU). Using this benchmark, we assess both proprietary and open source models. Results reveal a clear gap: proprietary models such as ChatGPT-4o-mini achieve high validity 95% and stronger code alignment (CodeBLEU 0.39), while smaller open source models like DeepSeek-R1-7B often generate incomplete or inconsistent workflows (48.5% validity, 0.272 CodeBLEU). Tasks requiring deeper spatial reasoning, such as spatial relationship detection or optimal site selection, remain the most challenging across all models. These findings demonstrate both the promise and limitations of current LLMs in GIS automation and provide a reproducible framework to advance GeoAI research with human-in-the-loop support.

cs.SE↗

arXiv2025

Mind2Web 2: Evaluating Agentic Search with Agent-as-a-Judge

Agentic search such as Deep Research systems-where agents autonomously browse the web, synthesize information, and return comprehensive citation-backed answers-represents a major shift in how users interact with web-scale information. While promising greater efficiency and cognitive offloading, the growing complexity and open-endedness of agentic search have outpaced existing evaluation benchmarks and methodologies, which largely assume short search horizons and static answers. In this paper, we introduce Mind2Web 2, a benchmark of 130 realistic, high-quality, and long-horizon tasks that require real-time web browsing and extensive information synthesis, constructed with over 1000 hours of human labor. To address the challenge of evaluating time-varying and complex answers, we propose a novel Agent-as-a-Judge framework. Our method constructs task-specific judge agents based on a tree-structured rubric design to automatically assess both answer correctness and source attribution. We conduct a comprehensive evaluation of ten frontier agentic search systems and human performance, along with a detailed error analysis to draw insights for future development. The best-performing system, OpenAI Deep Research, can already achieve 50-70% of human performance while spending half the time, highlighting its great potential. Altogether, Mind2Web 2 provides a rigorous foundation for developing and benchmarking the next generation of agentic search systems.

cs.AI↗

arXiv2025

AutoSDT: Scaling Data-Driven Discovery Tasks Toward Open Co-Scientists

Despite long-standing efforts in accelerating scientific discovery with AI, building AI co-scientists remains challenging due to limited high-quality data for training and evaluation. To tackle this data scarcity issue, we present AutoSDT, an automatic pipeline that collects high-quality coding tasks in real-world data-driven discovery workflows. AutoSDT leverages the coding capabilities and parametric knowledge of LLMs to search for diverse sources, select ecologically valid tasks, and synthesize accurate task instructions and code solutions. Using our pipeline, we construct AutoSDT-5K, a dataset of 5,404 coding tasks for data-driven discovery that covers four scientific disciplines and 756 unique Python packages. To the best of our knowledge, AutoSDT-5K is the only automatically collected and the largest open dataset for data-driven scientific discovery. Expert feedback on a subset of 256 tasks shows the effectiveness of AutoSDT: 93% of the collected tasks are ecologically valid, and 92.2% of the synthesized programs are functionally correct. Trained on AutoSDT-5K, the Qwen2.5-Coder-Instruct LLM series, dubbed AutoSDT-Coder, show substantial improvement on two challenging data-driven discovery benchmarks, ScienceAgentBench and DiscoveryBench. Most notably, AutoSDT-Coder-32B reaches the same level of performance as GPT-4o on ScienceAgentBench with a success rate of 7.8%, doubling the performance of its base model. On DiscoveryBench, it lifts the hypothesis matching score to 8.1, bringing a 17.4% relative improvement and closing the gap between open-weight models and GPT-4o.

cs.LG↗

arXiv2025

Completing A Systematic Review in Hours instead of Months with Interactive AI Agents

Systematic reviews (SRs) are vital for evidence-based practice in high stakes disciplines, such as healthcare, but are often impeded by intensive labors and lengthy processes that can take months to complete. Due to the high demand for domain expertise, existing automatic summarization methods fail to accurately identify relevant studies and generate high-quality summaries. To that end, we introduce InsightAgent, a human-centered interactive AI agent powered by large language models that revolutionize this workflow. InsightAgent partitions a large literature corpus based on semantics and employs a multi-agent design for more focused processing of literature, leading to significant improvement in the quality of generated SRs. InsightAgent also provides intuitive visualizations of the corpus and agent trajectories, allowing users to effortlessly monitor the actions of the agent and provide real-time feedback based on their expertise. Our user studies with 9 medical professionals demonstrate that the visualization and interaction mechanisms can effectively improve the quality of synthesized SRs by 27.2%, reaching 79.7% of human-written quality. At the same time, user satisfaction is improved by 34.4%. With InsightAgent, it only takes a clinician about 1.5 hours, rather than months, to complete a high-quality systematic review.

cs.HC↗

arXiv2025

Interlaced R2D2 DNN Series for Scalable Non-Cartesian MRI with Sensitivity Self-calibration

We introduce interlaced R2D2 (iR2D2), a DNN series paradigm for scalable image reconstruction from accelerated non-Cartesian k-space acquisitions in MRI with sensitivity map self-calibration. While unrolled DNN architectures provide robust image formation, embedding non-uniform fast Fourier transform operators within the backpropagation graph becomes impractical to train at large scale, e.g., in 2D MRI with a large number of coils, or for higher-dimensional imaging. To address this scalability challenge, we leverage the R2D2 paradigm as a learned version of the Matching Pursuit algorithm that was recently introduced in radio astronomy for fast large-scale Fourier imaging. R2D2's reconstruction is formed as a series of residual images iteratively estimated as outputs of DNN modules taking the previous iteration's data residual as input. Specific to MRI, precomputed sensitivity maps derived from undersampled data can yield an inaccurate measurement operator, which may adversely affect the performance of iterative algorithms such as R2D2. Thus, we extend the R2D2 framework to iR2D2 by introducing a bespoke interlaced architecture that alternates between two R2D2 DNN series to jointly self-calibrate sensitivity maps and form the MR image. We further enhance iR2D2 to operate as an adaptive solver governed by an error-controlled update condition that enforces a sufficient residual energy descent, a dynamic capability fundamentally incompatible with the predefined forward passes of unrolled architectures. Extensive experiments in simulation and on real data, targeting undersampled radial k-space sampling, demonstrate that iR2D2 significantly improves upon R2D2 and outperforms state-of-the-art benchmarks, delivering scalable, high-fidelity imaging with corrected sensitivity profiles.

eess.IV↗

arXiv2024

ScienceAgentBench: Toward Rigorous Assessment of Language Agents for Data-Driven Scientific Discovery

The advancements of large language models (LLMs) have piqued growing interest in developing LLM-based language agents to automate scientific discovery end-to-end, which has sparked both excitement and skepticism about their true capabilities. In this work, we call for rigorous assessment of agents on individual tasks in a scientific workflow before making bold claims on end-to-end automation. To this end, we present ScienceAgentBench, a new benchmark for evaluating language agents for data-driven scientific discovery. To ensure the scientific authenticity and real-world relevance of our benchmark, we extract 102 tasks from 44 peer-reviewed publications in four disciplines and engage nine subject matter experts to validate them. We unify the target output for every task to a self-contained Python program file and employ an array of evaluation metrics to examine the generated programs, execution results, and costs. Each task goes through multiple rounds of manual validation by annotators and subject matter experts to ensure its annotation quality and scientific plausibility. We also propose two effective strategies to mitigate data contamination concerns. Using ScienceAgentBench, we evaluate five open-weight and proprietary LLMs, each with three frameworks: direct prompting, OpenHands CodeAct, and self-debug. Given three attempts for each task, the best-performing agent can only solve 32.4% of the tasks independently and 34.3% with expert-provided knowledge. In addition, we evaluate OpenAI o1-preview with direct prompting and self-debug, which can boost the performance to 42.2%, demonstrating the effectiveness of increasing inference-time compute but with more than 10 times the cost of other LLMs. Still, our results underscore the limitations of current language agents in generating code for data-driven discovery, let alone end-to-end automation for scientific research.

cs.CL↗

arXiv2024

Attention in Large Language Models Yields Efficient Zero-Shot Re-Rankers

Information retrieval (IR) systems have played a vital role in modern digital life and have cemented their continued usefulness in this new era of generative AI via retrieval-augmented generation. With strong language processing capabilities and remarkable versatility, large language models (LLMs) have become popular choices for zero-shot re-ranking in IR systems. So far, LLM-based re-ranking methods rely on strong generative capabilities, which restricts their use to either specialized or powerful proprietary models. Given these restrictions, we ask: is autoregressive generation necessary and optimal for LLMs to perform re-ranking? We hypothesize that there are abundant signals relevant to re-ranking within LLMs that might not be used to their full potential via generation. To more directly leverage such signals, we propose in-context re-ranking (ICR), a novel method that leverages the change in attention pattern caused by the search query for accurate and efficient re-ranking. To mitigate the intrinsic biases in LLMs, we propose a calibration method using a content-free query. Due to the absence of generation, ICR only requires two ($O(1)$) forward passes to re-rank $N$ documents, making it substantially more efficient than generative re-ranking methods that require at least $O(N)$ forward passes. Our novel design also enables ICR to be applied to any LLM without specialized training while guaranteeing a well-formed ranking. Extensive experiments with two popular open-weight LLMs on standard single-hop and multi-hop information retrieval benchmarks show that ICR outperforms RankGPT while cutting the latency by more than 60% in practice. Through detailed analyses, we show that ICR's performance is specially strong on tasks that require more complex re-ranking signals. Our findings call for further exploration on novel ways of utilizing open-weight LLMs beyond text generation.

cs.CL↗

arXiv2024

Mean Squared Prediction Error Estimators of EBLUP of a Small Area Mean Under a Semi-Parametric Fay-Herriot Model

In this paper we derive a second-order unbiased (or nearly unbiased) mean squared prediction error (MSPE) estimator of the empirical best linear unbiased predictor (EBLUP) of a small area mean for a semi-parametric extension to the well-known Fay-Herriot model. Specifically, we derive our MSPE estimator essentially assuming certain moment conditions on both the sampling errors and random effects distributions. The normality-based Prasad-Rao MSPE estimator has a surprising robustness property in that it remains second-order unbiased under the non-normality of random effects when a simple Prasad-Rao method-of-moments estimator is used for the variance component and the sampling error distribution is normal. We show that the normality-based MSPE estimator is no longer second-order unbiased when the sampling error distribution has non-zero kurtosis or when the Fay-Herriot moment method is used to estimate the variance component, even when the sampling error distribution is normal. It is interesting to note that when the simple method-of moments estimator is used for the variance component, our proposed MSPE estimator does not require the estimation of kurtosis of the random effects. Results of a simulation study on the accuracy of the proposed MSPE estimator, under non-normality of both sampling and random effects distributions, are also presented.

stat.ME↗

arXiv2024

Multi-Task Learning in Natural Language Processing: An Overview

Deep learning approaches have achieved great success in the field of Natural Language Processing (NLP). However, directly training deep neural models often suffer from overfitting and data scarcity problems that are pervasive in NLP tasks. In recent years, Multi-Task Learning (MTL), which can leverage useful information of related tasks to achieve simultaneous performance improvement on these tasks, has been used to handle these problems. In this paper, we give an overview of the use of MTL in NLP tasks. We first review MTL architectures used in NLP tasks and categorize them into four classes, including parallel architecture, hierarchical architecture, modular architecture, and generative adversarial architecture. Then we present optimization techniques on loss construction, gradient regularization, data sampling, and task scheduling to properly train a multi-task model. After presenting applications of MTL in a variety of NLP tasks, we introduce some benchmark datasets. Finally, we make a conclusion and discuss several possible research directions in this field.

cs.AI↗

arXiv2023

Mind2Web: Towards a Generalist Agent for the Web

We introduce Mind2Web, the first dataset for developing and evaluating generalist agents for the web that can follow language instructions to complete complex tasks on any website. Existing datasets for web agents either use simulated websites or only cover a limited set of websites and tasks, thus not suitable for generalist web agents. With over 2,000 open-ended tasks collected from 137 websites spanning 31 domains and crowdsourced action sequences for the tasks, Mind2Web provides three necessary ingredients for building generalist web agents: 1) diverse domains, websites, and tasks, 2) use of real-world websites instead of simulated and simplified ones, and 3) a broad spectrum of user interaction patterns. Based on Mind2Web, we conduct an initial exploration of using large language models (LLMs) for building generalist web agents. While the raw HTML of real-world websites are often too large to be fed to LLMs, we show that first filtering it with a small LM significantly improves the effectiveness and efficiency of LLMs. Our solution demonstrates a decent level of performance, even on websites or entire domains the model has never seen before, but there is still a substantial room to improve towards truly generalizable agents. We open-source our dataset, model implementation, and trained models (https://osu-nlp-group.github.io/Mind2Web) to facilitate further research on building a generalist agent for the web.

cs.CL↗

arXiv2023

Error Detection for Text-to-SQL Semantic Parsing

Despite remarkable progress in text-to-SQL semantic parsing in recent years, the performance of existing parsers is still far from perfect. Specifically, modern text-to-SQL parsers based on deep learning are often over-confident, thus casting doubt on their trustworthiness when deployed for real use. In this paper, we propose a parser-independent error detection model for text-to-SQL semantic parsing. Using a language model of code as its bedrock, we enhance our error detection model with graph neural networks that learn structural features of both natural language questions and SQL queries. We train our model on realistic parsing errors collected from a cross-domain setting, which leads to stronger generalization ability. Experiments with three strong text-to-SQL parsers featuring different decoding mechanisms show that our approach outperforms parser-dependent uncertainty metrics. Our model could also effectively improve the performance and usability of text-to-SQL semantic parsers regardless of their architectures. (Our implementation is available at https://github.com/OSU-NLP-Group/Text2SQL-Error-Detection)

cs.CL↗

arXiv2023

Roll Up Your Sleeves: Working with a Collaborative and Engaging Task-Oriented Dialogue System

We introduce TacoBot, a user-centered task-oriented digital assistant designed to guide users through complex real-world tasks with multiple steps. Covering a wide range of cooking and how-to tasks, we aim to deliver a collaborative and engaging dialogue experience. Equipped with language understanding, dialogue management, and response generation components supported by a robust search engine, TacoBot ensures efficient task assistance. To enhance the dialogue experience, we explore a series of data augmentation strategies using LLMs to train advanced neural models continuously. TacoBot builds upon our successful participation in the inaugural Alexa Prize TaskBot Challenge, where our team secured third place among ten competing teams. We offer TacoBot as an open-source framework that serves as a practical example for deploying task-oriented dialogue systems.

cs.CL↗