Search arXiv⌕ Search

arXiv subjects

Yujia Zhou

Publications and source records attributed to Yujia Zhou.

At least 19 recordsLinked to original sources
arXiv2026

Different Feedback, Different Updates: Selective Self-Learning from User Interactions for Large Language Models

User feedback offers natural supervision for persistent LLM improvement, but a single message may support multiple behavioral changes with different scopes of generalization. We introduce SLIFT, a selective self-learning framework built on a task-relative view of user feedback. SLIFT decomposes each feedback message into atomic components and interprets each component relative to the original task as Fix, Spec, or Null: requirements for task validity, compatible condition-specific refinements, or content with no reliable positive update direction. To incorporate each change at the appropriate scope, SLIFT trains two complementary LoRA adapters on a shared frozen backbone: a Generalist that consolidates Fix requirements into default behavior through feedback-conditioned self-distillation, and a Specialist that observes only the task and Generalist response to supply residual guidance for applicable, unmet Spec refinements. Null components induce no positive update. Across backbones, SLIFT achieves strong performance on both MemoryBench and WildFB, with targeted analyses further examining its underlying mechanisms. We release our code at https://anonymous.4open.science/r/SLIFT.

cs.AI↗
arXiv2026

EnGRICH: Enhancing Generative Reward Modeling with Critiques from Humans

Generative reward models (GRMs) are important for LLM optimization. Unlike scalar reward models, GRMs generate natural-language critiques alongside preference judgments, providing finer-grained evaluation signals. Their effectiveness depends heavily on critique reliability. However, existing GRM training typically uses final preference correctness as outcome supervision. Because the preference outcome space is highly constrained, unreliable critiques can still yield correct outcomes and thus be reinforced. Recent work leverages human critiques for process supervision, but such critiques are scarce and are often reduced to scalar rewards, leaving their fine-grained evaluative information underutilized. We argue that evaluative criteria learned from human critiques can be generalized to broader outcome-only preference data. To this end, we propose \textbf{EnGRICH}, a GRM training framework that pairs the GRM with a training-time MetaCritic learned from a small set of human critiques. MetaCritic constructs response-specific rubrics and uses them to evaluate the evidence coverage and correctness of generated critiques. The resulting signals provide both process rewards for fine-grained credit assignment and structured guidance for exploring better critiques. During GRM training, MetaCritic is further optimized to generalize human-grounded evaluative criteria to outcome-only data. At inference, the trained GRM operates independently. Experiments across seven reward-model benchmarks show that EnGRICH consistently improves over competitive baselines, while further analyses validate the effectiveness of its core mechanisms.

cs.AI↗
arXiv2026

Mitigating Identity Essentialism in LLM Agents with Longitudinal Life Trajectories

Large language models (LLMs) offer a scalable approach to social simulation, but their credibility depends on how agents are constructed. Existing methods can partially reproduce population-level patterns, yet often fail to capture human-like diversity. Our analysis shows that static-profile agents exhibit stronger demographic separation and within-group compression than humans, a pattern consistent with identity essentialism: demographic labels can encourage models to treat group-average tendencies as individual traits, homogenizing responses within groups. We argue that this limitation arises from two related factors: sparse, static agent representations and the limited ability of prompt-only memory to persistently integrate experience. Inspired by complementary memory systems, we propose LifeMem, a longitudinal memory framework that combines structured life-event retrieval with agent-specific parametric memory for experience integration. Experiments on Understanding Society with three LLMs show that LifeMem improves alignment with human data in terms of response distributions, overall and within-group diversity, and patterns of within-person response change across life stages. These findings highlight the value of longitudinal life-event memory for constructing more faithful and dynamically evolving social agents.

cs.CL↗
arXiv2026

Composable Parametric Demographic Injection for Values Survey Simulation

Large language models (LLMs) are increasingly used as simulated respondents in computational social science, yet accurately reproducing population-specific heterogeneous response distributions remains challenging. Existing methods such as demographic prompting are sensitive to prompt design and increase inference overhead, while parameter-based methods struggle to reuse demographic information efficiently, limiting generalization to unseen combinations. In this regard, we propose PARADE, a composable PARAmetric DEmographic injection framework that represents each demographic attribute value with a reusable and composable LoRA module. Specifically, PARADE separates task-common survey capability from demographic-specific value shifts via a shared Task LoRA and attribute-level Demographic LoRAs, with composition calibration to reduce parameter interference. At inference time, target population models can be constructed on demand by recombining the relevant modules, including demographic combinations not observed during training. Extensive experiments on the World Values Survey and SocioBench across three backbone models show that PARADE achieves strong population-level distribution alignment while maintaining competitive predictive performance, reducing KL divergence by up to 52.8% relative to the strongest baseline.

cs.CL↗
arXiv2026

Benchmarking LLM-as-a-Judge for Long-Form Output Evaluation

As large language models (LLMs) are increasingly used for long-form generation, reliably evaluating long-form outputs has become a critical challenge. LLM-as-a-judge offers a scalable alternative to human evaluation, yet its reliability in long-form output evaluation remains underexamined: existing meta-evaluation benchmarks focus mainly on short-form outputs. Compared with short-form evaluation, long-form evaluation is not merely a matter of output length; it often requires judges to make more complex document-level assessments of overall organization, task-relevant coverage and depth, cross-section consistency, and scenario-specific quality criteria. In this work, we introduce LongJudgeBench, a comprehensive benchmark for evaluating LLM judges on long-form outputs across diverse real-world scenarios and judging protocols. We systematically evaluate a broad range of LLM judges, covering multiple base models and judging settings. Our results reveal a substantial reliability gap: current LLM judges remain unstable across scenarios, and rubrics or references are helpful but not always sufficient. We hope LongJudgeBench will support future research on more robust, context-aware, and human-aligned LLM-as-a-judge methods. Our code is available at https://github.com/cjj826/LongJudgeBench.

cs.CL↗
arXiv2026

Toward Federated Large Language Models in Medicine: A Parameter-Efficient Framework for Privacy-Preserving, Multi-Institutional Adaptation

Large language models (LLMs) are increasingly adapted for medical applications, but most are trained using data from a single institution because privacy and governance constraints prevent multi-institutional data sharing. As a result, these models often generalize poorly across heterogeneous healthcare systems. We address this gap by introducing Fed-MedLoRA and Fed-MedLoRA+, a parameter-efficient federated framework for collaborative LLM adaptation across healthcare institutions. Fed-MedLoRA transmits only low-rank adapters rather than full model weights, reducing communication overhead. We also evaluate a privacy-preserving variant that applies Gaussian perturbation to transmitted adapter updates. Fed-MedLoRA+ further incorporates adaptive aggregation to better address cross-site heterogeneity in patient populations, annotation practices, and disease distributions. We evaluate the framework on clinical information extraction across five independent patient cohorts totaling 42,198 entities and 41,570 relations, and compare it with zero-shot and fine-tuned LLMs, domain-specific BERT models, and federated baselines. Across all settings, the proposed methods consistently improve extraction performance and generalize better to heterogeneous cohorts. In a real-world case study using clinical notes from the Yale New Haven Health System, the framework demonstrates strong performance under low-resource new-site deployment. These results suggest that federated, parameter-efficient LLM adaptation is feasible, scalable, and effective for multi-institutional clinical deployment.

cs.CL↗
arXiv2026

Simulating Dispute Mediation with LLM-Based Agents for Legal Research

Legal dispute mediation plays a crucial role in resolving civil disputes, yet its empirical study is limited by privacy constraints and complex multivariate interactions. To address this limitation, we present AgentMediation, the first LLM-based agent framework for simulating dispute mediation. It simulates realistic mediation processes grounded in real-world disputes and enables controlled experimentation on key variables such as disputant strategies, dispute causes, and mediator expertise. Our empirical analysis reveals patterns consistent with sociological theories, including Group Polarization and Surface-level Consensus. As a comprehensive and extensible platform, AgentMediation paves the way for deeper integration of social science and AI in legal research.

cs.CY↗
arXiv2026

MetaSyn: A Benchmark for LLM Agents on Meta-Analysis Articles from Nature Portfolio

Systematic review and meta-analysis is an important method for scientific research. It comprehensively studies target research questions by combining evidence from multiple independent studies following a standard and rigid protocol (i.e., PI/ECO). This is valuable for facilitating reliable and sustainable research across multiple domains, including but not limited to physics, chemistry, psychology, and medical science. Traditional meta-analysis is both mind-intensive and labor-intensive, as it requires professionals to search, screen, and synthesize tens of thousands of studies, which usually takes months or even years. Recent advances in AI, particularly LLM agents, have the potential to significantly automate this process, but whether they can conduct reliable meta-analysis is still unknown. To this end, we introduce MetaSyn, a dataset and evaluation protocol built from 422 expert-curated meta-analyses manually selected from more than 34,000 published articles in Nature Portfolio journals. We collected the research questions with structured eligibility criteria, the studies included by the original reviewers, and a shared PubMed-anchored corpus containing both eligible studies and plausible but ineligible distractors to build a comprehensive benchmark for meta-analysis. Our experiments on multiple LLMs and baseline methods show that existing AI systems are far from perfect. We also conducted stage-wise evaluation and analysis to shed light on why existing AI systems fall short on meta-analysis.

cs.CL↗
arXiv2026

Parametric Social Identity Injection and Diversification in Public Opinion Simulation

Large language models (LLMs) have recently been adopted as synthetic agents for public opinion simulation, offering a promising alternative to costly and slow human surveys. Despite their scalability, current LLM-based simulation methods fail to capture social diversity, producing flattened inter-group differences and overly homogeneous responses across demographic groups. We identify this limitation as a Diversity Collapse phenomenon in LLM hidden representations, where distinct social identities become increasingly indistinguishable across layers. Motivated by this observation, we propose Parametric Social Identity Injection (PSII), a general framework that injects explicit, parametric representations of demographic attributes and value orientations directly into intermediate hidden states of LLMs. Unlike prompt-based persona conditioning, PSII enables fine-grained and controllable identity modulation at the representation level. Extensive experiments on the World Values Survey using multiple open-source LLMs show that PSII significantly improves distributional fidelity and diversity, reducing KL divergence to real-world survey data while enhancing overall diversity. This work provides new insights into representation-level control of LLM agents and advances scalable, diversity-aware public opinion simulation.

cs.CL↗
arXiv2026

MulFeRL: Enhancing Reinforcement Learning with Verbal Feedback in a Multi-turn Loop

Reinforcement Learning with Verifiable Rewards (RLVR) is widely used to improve reasoning across domains, but outcome-only scalar rewards are often sparse and uninformative. This limitation is especially severe for failed samples, where scalar rewards indicate only that a solution is incorrect without explaining why the reasoning breaks down. In this paper, we leverage richer verbal feedback to guide RLVR on failed samples and convert feedback-induced progress into trainable learning signals. We propose MulFeRL (Multi-turn Feedback-guided Reinforcement Learning), a multi-turn, event-triggered RLVR framework that combines progress induction for feedback-guided regeneration of failed samples, progress credit assignment for learning from verifier-confirmed progress, and structured feedback injection for integrating feedback into the model's reasoning process. Trained on sampled OpenR1-Math, MulFeRL outperforms supervised, self-distillation-based, and RLVR baselines in-domain, while also showing strong out-of-domain generalization.

cs.AI↗
arXiv2026

How do Humans Process AI-generated Hallucination Contents: a Neuroimaging Study

While AI-generated hallucinations pose considerable risks, the underlying cognitive mechanisms by which humans can successfully recognize or be misled by these hallucinations remain unclear. To address this problem, this paper explores humans' neural dynamics to characterize how the brain processes hallucinated content. We record EEG signals from 27 participants while they are performing a verification task to judge the correctness of image descriptions generated by a multi-modal large language model (MLLM). Based on an averaged event-related potential (ERP) study, we reveal that multiple cognitive processes, e.g., semantic integration, inferential processing, memory retrieval, and cognitive load, exhibit distinct patterns when humans process hallucinated versus non-hallucinated content. Notably, neural responses to hallucinations that were misjudged versus correctly judged by human participants showed significant differences. This indicates that misjudged AI-generated hallucinations failed to trigger the standard neurocognitive fact verification pathway.

cs.AI↗
arXiv2026

Beyond Exposure: Optimizing Ranking Fairness with Non-linear Time-Income Functions

Ranking systems in web search and recommendation allocate attention among items and providers, and therefore need to balance relevance-based effectiveness with provider fairness. Existing fair-ranking methods commonly focus on exposure fairness, where cumulative exposure is allocated in proportion to item merit. However, exposure is often only an intermediate signal: the actual utility received by a provider may depend on context-dependent conversion from exposure to income, such as clicks, purchases, or advertising value. This paper studies fair ranking under context-dependent provider utility, which we refer to as income. We formalize income fairness by requiring cumulative provider income to be proportional to relevance, and define an income-unfairness metric based on this proportionality condition. We then propose DIDRF, a Dynamic-Income-Derivative-aware Ranking Fairness algorithm for income-fair ranking. DIDRF uses the quadratic structure of income-fairness violations to derive a state-aware scoring rule that jointly considers ranking effectiveness and the marginal effect of each ranking decision on cumulative income fairness. Experiments on standard learning-to-rank datasets with log-calibrated semi-synthetic income environments based on advertising and e-commerce logs show that DIDRF consistently improves income fairness over representative fair-ranking baselines while preserving competitive ranking effectiveness.

cs.IR↗
arXiv2026

Trustworthiness in Retrieval-Augmented Generation Systems: A Survey

Retrieval-Augmented Generation (RAG) has quickly grown into a pivotal paradigm in the development of Large Language Models (LLMs). Although existing research mainly emphasizes accuracy and efficiency, the trustworthiness of RAG systems remains insufficiently explored. RAG can improve LLM reliability by grounding responses in external and up-to-date knowledge, reducing hallucinations. However, unreliable retrieval or improper knowledge utilization may still lead to undesirable outputs. To address these concerns, we propose a unified framework, Trust-RAG Compass, that assesses the trustworthiness of RAG systems across six key dimensions: factuality, robustness, fairness, transparency, accountability, and privacy. Within this framework, we provide a thorough review of the existing literature along each dimension. Furthermore, we introduce an evaluation benchmark, TRC Bench (\underline{T}rust-\underline{R}AG \underline{C}ompass \underline{Bench}mark), regarding the six dimensions and conduct comprehensive evaluations for a variety of proprietary and open-source models. Our results shed light on the performance gaps between different types of LLMs across varying dimensions of trustworthiness. Finally, we identify key challenges and promising directions for future research based on our findings. Through this work, we aim to provide a structured foundation for subsequent investigations and practical guidance for developing trustworthy RAG systems in real-world scenarios.

cs.IR↗
arXiv2026

ECHO: Explainable Co-editing with Human-in-the-loop Operations for Presentation Refinement

Authoring and refining presentation slides is a highly time-consuming core task in academic and business domains. While generative AI tools have lowered the barrier for creating initial drafts, their "black-box, one-way generation" paradigm severely deprives users of fine-grained control. Through a formative study (N=10), we identified "trial-and-error anxiety" and "inconsistent cross-page formatting" as primary bottlenecks in human-AI co-creation. Consequently, we present ECHO, an interactive system based on multimodal intent grounding and explainable operation plans. ECHO enables precise local edits via a "natural language + visual selection" paradigm, utilizing a decoupled "Plan-Confirm-Execute" loop and dynamic memory mechanisms to transform implicit AI intents into highly controllable layout co-creation. To systematically evaluate document refinement, we propose the CoEdit-Eval framework. Objective evaluations across multiple foundation models (e.g., GPT-5, GLM-4.7) demonstrate that while baselines uniformly fail in intent mapping (0% accuracy) and spatial grounding (0% Hit@1), the ECHO architecture boosts Target Hit@1 to 55%--85% depending on the base model. Furthermore, integrating Vision-Language Models (VLMs) effectively resolves spatial ambiguities -- achieving significant win rates in LLM blind evaluations -- and our Undo mechanism guarantees 100% physical file consistency (MD5 hash). Finally, a controlled study with 14 participants shows that ECHO significantly reduces cognitive workload (NASA-TLX scores dropped by 20.8%, from 82.6 to 65.4) and reveals the dynamic evolution of human control allocation across different cognitive tasks.

cs.HC↗
arXiv2026

Foundation Models to Unlock Real-World Evidence from Nationwide Medical Claims

Evidence derived from large-scale real-world data (RWD) is increasingly informing regulatory evaluation and healthcare decision-making. Administrative claims provide population-scale, longitudinal records of healthcare utilization, expenditure, and detailed coding of diagnoses, procedures, and medications, yet their potential as a substrate for healthcare foundation models remains largely unexplored. Here we present ReClaim, a generative transformer trained from scratch on 43.8 billion medical events from more than 200 million enrollees in the MarketScan claims data spanning 2008-2022. ReClaim models longitudinal trajectories across diagnoses, procedures, medications, and expenditure, and was scaled to 140 million, 700 million, and 1.7 billion parameters. Across over 1,000 disease-onset prediction tasks, ReClaim achieved a mean AUC of 75.6%, substantially outperforming disease-specific LightGBM (66.3%) and the transformer-based Delphi model (69.4%), with the largest gains for rare diseases. These advantages held across retrospective and prospective evaluations and in external validation on two independent datasets. Performance improved monotonically with scale, and post-training added 13.8 percentage points over pre-training alone. Beyond disease prediction, ReClaim captured financial outcomes and improved real-world evidence (RWE) analyses: for healthcare expenditure forecasting it increased explained variance from 0.28 to 0.37 relative to LightGBM, and in a target trial emulation it reduced systematic bias by 72% on average relative to Delphi. Together, these results establish administrative claims as a scalable substrate for healthcare foundation models and show that learned representations generalize across time periods and data sources, supporting disease surveillance, expenditure forecasting, and RWE generation.

cs.AI↗
arXiv2026

Beyond Experience Retrieval: Learning to Generate Utility-Optimized Structured Experience for Frozen LLMs

Large language models (LLMs) are largely static and often redo reasoning or repeat mistakes. Prior experience reuse typically relies on external retrieval, which is similarity-based, can introduce noise, and adds latency. We introduce SEAM (Structured Experience Adapter Module), a lightweight, executor-specific plug-in that stores experience in its parameters and generates a structured, instance-tailored experience entry in a single forward pass to guide a frozen LLM executor. SEAM is trained for utility via executor rollouts and GRPO while keeping the executor frozen, and it can be further improved after deployment with supervised fine-tuning on logged successful trajectories. Experiments on mathematical reasoning benchmarks show consistent accuracy gains across executors with low overhead. Extensive ablations and analyses further elucidate the mechanisms underlying SEAM's effectiveness and robustness.

cs.LG↗
arXiv2026

EDU-Net: Retinal Pathological Fluid Segmentation in OCT Images with Multiscale Feature Fusion and Boundary Optimization

Objective: Diabetic macular edema (DME) is the leading cause of severe visual impairment in patients with diabetes. Quantification of retinal fluid, particularly intraretinal fluid (IRF) and subretinal fluid (SRF), plays a critical role in the management of DME. Although optical coherence tomography (OCT) can be used for detection, the variable morphology of fluid accumulation and the blurred boundaries caused by noise interference still limit the accuracy of OCT's automatic segmentation. Methods: Retrospective model development and validation study. This study proposes a novel edge-guided dual-branch encoder-decoder network (EDU-Net) to achieve accurate and efficient automatic segmentation of OCT liquid lesions. The local feature extraction branch is based on the EfficientNet model, which precisely captures tiny lesions by leveraging its lightweight separable convolution and high-resolution feature preservation strategy. The global feature extraction branch is based on the large-kernel efficient convolution (LKEC) module and the downsampling layer design to enhance long-range dependencies and global semantics. EDU-Net applies a multi-category edge-guided attention module to fuse high-frequency boundary detail information to each resolution feature to optimize the boundary segmentation performance. Results: Extensive results on the in-house and public datasets demonstrate that EDU-Net achieves state-of-the-art DSC segmentation performance in terms of efficiency and robustness, especially in the segmentation of IRF lesions. Conclusions: EDU-Net integrates local details with global context and optimizes boundaries, achieving an improvement in the accuracy of automatic segmentation of retinal fluid.

eess.IV↗
arXiv2026

LegalOne: A Family of Foundation Models for Reliable Legal Reasoning

While Large Language Models (LLMs) have demonstrated impressive general capabilities, their direct application in the legal domain is often hindered by a lack of precise domain knowledge and complexity of performing rigorous multi-step judicial reasoning. To address this gap, we present LegalOne, a family of foundational models specifically tailored for the Chinese legal domain. LegalOne is developed through a comprehensive three-phase pipeline designed to master legal reasoning. First, during mid-training phase, we propose Plasticity-Adjusted Sampling (PAS) to address the challenge of domain adaptation. This perplexity-based scheduler strikes a balance between the acquisition of new knowledge and the retention of original capabilities, effectively establishing a robust legal foundation. Second, during supervised fine-tuning, we employ Legal Agentic CoT Distillation (LEAD) to distill explicit reasoning from raw legal texts. Unlike naive distillation, LEAD utilizes an agentic workflow to convert complex judicial processes into structured reasoning trajectories, thereby enforcing factual grounding and logical rigor. Finally, we implement a Curriculum Reinforcement Learning (RL) strategy. Through a progressive reinforcement process spanning memorization, understanding, and reasoning, LegalOne evolves from simple pattern matching to autonomous and reliable legal reasoning. Experimental results demonstrate that LegalOne achieves state-of-the-art performance across a wide range of legal tasks, surpassing general-purpose LLMs with vastly larger parameter counts through enhanced knowledge density and efficiency. We publicly release the LegalOne weights and the LegalKit evaluation framework to advance the field of Legal AI, paving the way for deploying trustworthy and interpretable foundation models in high-stakes judicial applications.

cs.CL↗