Search arXiv⌕ Search

arXiv subjects

Ziqi Xu

Publications and source records attributed to Ziqi Xu.

At least 19 recordsLinked to original sources
arXiv2026

Conditional Information Flow and Neural Representability of One-Dimensional Rotated Cluster States

I study how measurement outcomes can remain conditionally dependent over long distances while the underlying state carries only a small internal memory, using one-dimensional rotated cluster states, whose exact matrix product state (MPS) bond dimension is $D=2$ at every rotation angle. Using exact MPS contraction, I compute the conditional mutual information (CMI) of two readout protocols: the entanglement-swapping endpoint CMI decreases from one bit at $θ=0$ to zero at $θ=π/2$, whereas a stationary bulk readout of the locally equivalent conventional cluster state vanishes at both limits. As an exact control, the spin-1 AKLT chain obeys $I_m=(4/9)\,3^{-m}$, so its CMI length equals its two-point correlation length, for an identifiable but non-generic reason. I then compare learners on the same $N=64$, $θ=0.35$ target. A positive autoregressive GRU learns the computational-basis Born distribution from a few thousand samples, but an exactly computable Bell-basis readout shows that this distribution does not fix the phases. A complex RBM reaches the $N=8$ ground state under an exact objective, while a short generic recurrent variational Monte Carlo pilot is still improving when its runs end. As a positive control, an MPS-induced recurrent model whose hidden state is the bond vector reaches the ground state to near machine precision at $χ=2$, whereas a $χ=1$ control fails. These results show that long CMI does not require a large bond dimension, and that building the small virtual memory into the architecture greatly eases optimization.

quant-ph↗
arXiv2026

Why Are LLMs Confidently Wrong? Correcting Overconfident Errors via Causal Head Intervention

Modern large language models (LLMs) often exhibit overconfident errors, assigning high confidence to incorrect predictions and thereby undermining reliability in real-world use. Existing calibration methods typically rely on post-hoc adjustment or retraining, operating at the output level without addressing the underlying causes of miscalibration. We propose CoCHI, (Class-oriented Causal Head Intervention), a framework that improves calibration by identifying and intervening on internal components responsible for distinct confidence behaviours. By analysing predictions through correctness-confidence patterns, CoCHI enables targeted intervention on model internals, reducing overconfident errors while preserving correct predictions. Our approach provides a mechanistic perspective on calibration, linking reliability to identifiable structures within the model rather than treating it as an output-level issue. Experiments across multiple LLMs show consistent improvements in calibration metrics, including Expected Calibration Error, Negative Log-Likelihood, and Brier Score, while maintaining accuracy on five multiple-choice question answering benchmarks. These results suggest that effective calibration requires not only adjusting outputs, but also addressing the underlying causal mechanisms within the model.

cs.AI↗
arXiv2026

Decouple to Forget: Semantic Mediation for Sensitive Unlearning in Large Language Models

Machine unlearning for large language models seeks to remove specified knowledge while preserving general capability, yet current methods often treat an entire response as the unit of forgetting. This coarse granularity causes unnecessary utility loss when the forget target is only a small set of sensitive facts embedded within otherwise benign explanations. In this paper, we introduce Decouple to Forget (D2F), a targeted unlearning method inspired by semantic mediation that separates sensitive factual content from non-sensitive meaning and surface expression. For each example to be forgotten, D2F extracts a fact-level "mediator" representation from the answer, identifies which parts are sensitive, and removes only those parts while leaving the rest of the structure intact. We then generate counterfactual answers grounded in this mediator that preserve non-sensitive content but exclude sensitive facts, employing preference-based contrastive optimization to reduce the likelihood of information leakage while maintaining helpfulness and fluency. Experiments across various benchmark datasets show that D2F achieves a better balance between forgetting and retention than strong baseline methods. Our code is available at https://github.com/JingyueCong/D2F.

cs.CL↗
arXiv2026

The Commit-Abstain Circuit: Why Language Models Hallucinate Instead of Abstaining

Language models (LMs) often hallucinate by committing to confident answers rather than abstaining, even when they do not have enough information to answer reliably. A large body of existing work mitigates hallucination through detection or abstention mechanisms, but leaves open how models internally arrive at the decision to commit or abstain in the first place. We study this decision through mechanistic analysis, framing hallucination as unsupported commitment: the model commits despite exhibiting signals of unanswerability. Using causal gating, we identify a Commit-Abstain Circuit (CAC), a sparse, causally localised subset of attention heads and MLP sublayers underlying this decision. Across ten LMs (3B-14B) from five families and three benchmarks, the CAC exhibits a recurring accumulate-yet-undercorrect pattern: commitment-promoting components build up commitment in earlier layers, while abstention-promoting components act later as corrective signals that are often insufficient to overturn the accumulated commitment. Building on this finding, a lightweight policy trained on CAC activations improves decision accuracy by 12.2 points over the model's intrinsic commit-abstain margin, reduces false abstentions by 2.5 times, transfers to unseen benchmarks, and extends to larger models (27B-35B). The CAC is both diagnostic, clarifying how models overcommit, and practical, enabling improved abstention decisions.

cs.AI↗
arXiv2026

The "Curse of Knowledge" in LLM Query Simulation: Concept Provenance for Tracing Answer-Side Intrusion

LLM-generated search queries are widely used to augment IR evaluation, yet they may contain concepts that presuppose answer-side document knowledge, violating the information-access boundary of pre-search users. Existing validation metrics, including overlap, diversity, and effectiveness, cannot distinguish rare human-tail variation from candidate answer-side intrusion. We introduce concept provenance, a framework that assigns query concepts to backstory-supported, human-central, human-tail, and candidate answer-side zones, operationalizing a boundary that retrieval metrics alone cannot detect. Applying concept provenance to 77,004 queries across 100 UQV100 topics, 8 LLMs, and 5 prompt conditions with two extraction pipelines, we obtain a cross-pipeline token-HCIR Spearman rho of 1.0 over five condition means. Candidate answer-side concepts constitute 7.40 percent of non-generic concepts and appear in 97 of 100 topics, with topic explaining approximately 67 percent of variance. Human validation yields 68.2 percent relaxed precision, revealing two mechanisms: knowledge intrusion at 45.5 percent and deployment intrusion at 45.0 percent. Diagnostic probes show disproportionate localized retrieval effects, with deletion effect size d = -0.47 compared with d = -0.34 for random deletion, but these concepts explain less than 2 percent of aggregate evaluation variance. Concept provenance therefore serves as a boundary-compliance diagnostic rather than an evaluation-shift predictor. Under the tested conditions, no prompt condition eliminates intrusion; post-generation concept-provenance selection achieves 99 percent elimination.

cs.IR↗
arXiv2026

Condensed PIPG Sequential Convex Optimization for Reusable-Rocket Powered Landing with Strong Aerodynamics

Reusable-rocket powered landing under strong aerodynamics couples variable mass, free final time, and bounded aerodynamic controls through nonlinear velocity-frame dynamics. This paper develops a condensed proportional--integral projected-gradient (PIPG) sequential-convex method whose principal contribution is an exact reduced-space inner architecture. Because the problem contains only six terminal hard equalities and no state path constraints, 217 nodal-state variables and 210 trapezoidal dynamics equalities are eliminated from the 31-node convex subproblem, leaving 101 primal variables and six terminal equalities. Row-orthogonal preconditioning, fixed-size matrix--vector products, and nodewise circular-epigraph projections then yield a customized PIPG kernel. Physical consistency of the angle-dependent axial force is maintained by gradually releasing drag sensitivity between the reference squared angle and an epigraph variable $A$, together with a convex tightness term. A pointwise Hamiltonian argument shows that the fully released limiting subproblem admits a tight optimum satisfying $A=α^2+β^2$. Deterministic annealing, two-stage inner accuracy, and a rejected-on-failure threefold extrapolation are secondary outer-loop accelerators.

math.OC↗
arXiv2026

Twin Worlds: Equivariance-Based Abstention for Evidence-Grounded Reasoning

Knowledge-intensive reasoning requires Large Language Models (LLMs) to ground answers in provided evidence. When evidence is insufficient, it is desirable that models abstain rather than confidently generating unsupported answers. Existing abstention methods rely on uncertainty estimation or evidence sufficiency checks, but neither tests whether the reasoning process for generation, driven by the interaction of provided evidence and the model's internal memory parameters, is actually grounded in the evidence. A key contributing factor is that entity mentions in context activate memorised associations, causing models to generate plausible responses ungrounded in evidence. We propose Twin Worlds (TW), a framework for improving reliability in knowledge-intensive reasoning through equivariance-based abstention: unlike invariance, which requires outputs to remain unchanged, equivariance requires outputs to transform correspondingly under entity substitutions. A model grounded in the evidence should produce answers that shift consistently when entities are substituted while their relations are preserved. TW constructs multiple worlds via typed substitutions of the original input that preserve relational structure while reducing parametric priors, and uses equivariance violations as an abstention signal. Across four benchmarks and three model backbones, TW identifies when answers are not reliably grounded in the provided evidence and outperforms uncertainty- and sufficiency-based baselines.

cs.CL↗
arXiv2026

Submillisecond Sequential Convex Optimization for Powered Landing via Dynamics Condensation and xPIPG

Powered landing with variable mass, free final time, and quadratic aerodynamic drag requires the repeated solution of local convex subproblems, whose main online cost lies in the long dynamics-equality chain and the inner iterations. This paper develops a condensed sequential convex approximation designed for low latency. Exact block elimination removes 217 intermediate-state components and 210 interval equations from a 31-node model, leaving 100 primal variables coupled by six terminal equalities. A low-weight energy term and fixed quadratic proximal regularization make the ideal surrogate strongly convex with predictable curvature. The inner solver is an extrapolated proportional--integral projected gradient (xPIPG) implemented with fixed-size arrays, $3\times3$ interval solves, and a fused one-pass node map. The one-pass map is a deliberate low-cost approximation, not the exact joint proximal operator. We therefore evaluate the timed code by nonlinear trajectory residuals and independent physical checks rather than by a claim of exact KKT convergence. The single-precision C implementation completes one plan in four outer updates and 336 xPIPG updates. On an Intel Core i7-10875H, the median end-to-end solve time is \SI{374}{\micro\second} and the P99 value is \SI{512}{\micro\second}. All 100 common initial-state perturbations pass validation, and the median remains below \SI{0.7}{\milli\second} for 15--51 nodes. An independent high-accuracy first-order-hold integration gives a terminal position error of \SI{0.183}{\meter}. Within the stated model, hardware, stopping rule, and timing boundary, this is, to the authors' knowledge, the first submillisecond end-to-end sequential-convex solve for a single powered-landing trajectory.

math.OC↗
arXiv2026

Fairness in Augmented Graph Learning: A Survey

Graph learning has evolved into Augmented Graph Learning (AGL) by integrating specialized machine learning (ML) techniques. Examples include federated learning, graph transformers, and graph condensation. While enhancing model utility, AGL introduces unique intersectional fairness challenges that traditional GNN debiasing frameworks, which primarily focus on message-passing regulations, fail to address. This paper provides a systematic investigation into this emerging field, termed FairGX. We first delineate the shift from conventional fairness-aware graph learning to the FairGX paradigm, identifying novel bias sources inherent in ML augmentations, such as dual-side disparities in federated aggregation and attention-head skewness. A structured taxonomy is established to categorize existing literature based on their technical integration and fairness objectives. Furthermore, we analyze the impact of diverse ML paradigms on algorithmic equity, emphasizing the unique challenges in human-centered applications and the absence of a unified framework. We conclude by identifying five critical future directions, including novel metrics for AGL, fairness-privacy synergy, and Fairness-aware LLM4Graph/Graph4LLM. This survey serves as a foundational roadmap for developing robust and equitable graph systems in complex ML environments.

cs.LG↗
arXiv2026

Microsecond-Class Powered-Descent Optimization via Exact Condensation and Strong Convex Regularization

Fuel-dominant powered descent can be written as a convex program, but the usual full-state epigraph formulation still carries many state variables, fuel epigraph variables, and dynamics equalities. In addition, the pure-fuel objective provides no strong-convexity curvature. This paper combines three structural reductions. First, a dimensionally consistent low-weight energy term makes the control solution unique. Second, a terminal-state sensitivity recursion eliminates every intermediate state exactly; invertible row normalization turns the 30-node baseline with 300 primal variables and 174 equality multipliers into a problem with 90 control variables and six terminal multipliers. Third, the shared radial structure of the fuel norm and thrust ball gives an exact closed-form proximal operator consisting of group shrinkage followed by magnitude clipping. The condensed problem is solved with a fixed-budget extrapolated proportional--integral projected-gradient iteration implemented in fixed-size C17 arrays. In a Mars powered-descent case with energy weight 0.02 and relative reference-solution tolerance $10^{-3}$, the iteration count decreases from 2744 for the pure-fuel full-state epigraph baseline to 93, while the fuel metric increases by only 0.033\%. The mean end-to-end solve time is \SI{68.2}{\micro\second}, and P99 is \SI{128.1}{\micro\second}, on an Intel i7-10875H. Because the thrust set in this test case is already a convex ball, the contribution is fast solution of the convex core rather than a new lossless-convexification theorem.

math.OC↗
arXiv2026

The Missing Adapter Layer for Research Computing

Higher Degree by Research (HDR) candidates increasingly depend on cloud-provisioned virtual machines and local GPU hardware for their computational experiments, yet a persistent and under-addressed gap separates having compute resources from using them productively. Cloud and infrastructure teams can provision a virtual machine in minutes, but the path from a raw VM to a reproducible, GPU-ready research environment remains a significant barrier for researchers who are domain experts, not systems engineers. We argue that this gap is not a shortcoming of any particular tool but a missing architectural layer: an adapter layer that bridges cloud provisioning and interactive research work. We present a lightweight, open-source implementation of this layer, built on k3s and Coder and already in active use in our research workspace environment. A CI/CD pipeline connects GitHub directly to the local cluster, carrying a research project from commit to a running, accessible workspace in under five minutes. We then define a concrete metrics framework for evaluating any adapter layer covering deployment latency, environment reproducibility, onboarding friction, and resource utilisation and establish baselines against which improvements can be measured.

cs.CE↗
arXiv2026

MCLMR: A Model-Agnostic Causal Learning Framework for Multi-Behavior Recommendation

Multi-Behavior Recommendation (MBR) leverages multiple user interaction types (e.g., views, clicks, purchases) to enrich preference modeling and alleviate data sparsity issues in traditional single-behavior approaches. However, existing MBR methods face fundamental challenges: they lack principled frameworks to model complex confounding effects from user behavioral habits and item multi-behavior distributions, struggle with effective aggregation of heterogeneous auxiliary behaviors, and fail to align behavioral representations across semantic gaps while accounting for bias distortions. To address these limitations, we propose MCLMR, a novel model-agnostic causal learning framework that can be seamlessly integrated into various MBR architectures. MCLMR first constructs a causal graph to model confounding effects and performs interventions for unbiased preference estimation. Under this causal framework, it employs an Adaptive Aggregation module based on Mixture-of-Experts to dynamically fuse auxiliary behavior information and a Bias-aware Contrastive Learning module to align cross-behavior representations in a bias-aware manner. Extensive experiments on three real-world datasets demonstrate that MCLMR achieves significant performance improvements across various baseline models, validating its effectiveness and generality. All data and code will be made publicly available. For anonymous review, our code is available at the following the link: https://github.com/gitrxh/MCLMR.

cs.IR↗
arXiv2026

Verifiable User Simulation for Search and Recommendation Systems

Large-language-model (LLM) based user simulation is increasingly adopted for evaluating search engines, recommender systems, and retrieval-augmented generation pipelines, yet most simulators remain opaque: it is difficult to determine why a simulated user made a particular choice or whether that choice is consistent with the intended user profile. Compounding this, recent research shows that LLMs can produce biased or discriminatory responses depending on user background characteristics such as language, education level, and cultural context, raising concerns about the equitable treatment of minority and disadvantaged groups. This half-day, in-person tutorial introduces a proposed design-and-audit framework that treats a user simulator as a verifiable engineering artefact composed of seven auditable components - structured Persona, task-aware Contract, matched human-vs-agent Execution, auditable Trace, persona-aligned Verification, structured Feedback, and a Refinement loop that updates personas and contracts. Through two hands-on mini-labs on recommendation-list evaluation and search-query formulation, participants will inspect simulator behaviour end-to-end, distinguish diagnostic discrepancy analysis from statistical validation, and apply checks for fidelity, credibility, and demographic bias. The tutorial targets information retrieval and recommender systems researchers and practitioners interested in user behaviour simulation and responsible AI.

cs.IR↗
arXiv2026

Seeing Time: Benchmarking Chronological Reasoning and Shortcut Biases in Vision-Language Models

Recent advancements in Vision-Language Models (VLMs) have significantly enhanced their ability to interpret complex visual semantics, yet their capacity for chronological reasoning remains under-explored. In this paper, we introduce a novel benchmark specifically designed to evaluate how VLMs perceive and reason about chronological information within and across images. Unlike existing video-based benchmarks that focus on frame sequencing, our work delves into the underlying logic of chronological judgment and the expansion toward multimodal integration. To facilitate this, we construct three specialized datasets: one containing visually similar objects spanning long historical durations, another categorized by diverse event and object types, and a third pairing images with time-sensitive news text for cross-modal alignment. Through extensive experiments, we analyze whether models exhibit performance disparities across categories and, crucially, explore whether they rely on ``incorrect shortcuts'', such as image color rather than genuine chronological features. Our results reveal that while VLMs show promise, they frequently exploit superficial cues like grayscale versus color filters to bypass authentic chronological reasoning. By providing these high-quality datasets and a rigorous evaluation framework, we offer a diagnostic tool to identify current limitations and guide the development of more robust, logically grounded multimodal models. The source code is shown in https://github.com/LuoRenqiang/ChronoVision.

cs.AI↗
arXiv2026

TERGAD: Structure-Aware Text-Enhanced Representations for Graph Anomaly Detection

Graph Anomaly Detection (GAD) aims to identify atypical graph entities, such as nodes, edges, or substructures, that deviate significantly from the majority. While existing text-rich approaches typically integrate structural context into the data representation pipeline using raw textual features, they often neglect the structural context of nodes. This limitation hinders their ability to detect sophisticated anomalies arising from inconsistencies between a node's inherent content and its topological role. To bridge this gap, we propose TERGAD (Structure-aware Text-enhanced Representations for Graph Anomaly Detection), A novel data augmentation framework that enriches structural semantics for GAD via the semantic reasoning capabilities of Large Language Models (LLMs). Specifically, TERGAD translates node-level topological properties into descriptive natural language narratives, which are subsequently processed by an LLM to derive high-level semantic embeddings. These embeddings are then adaptively fused with original node attributes through a gated dual-branch autoencoder to jointly reconstruct both graph structure and node features. The anomaly score is computed based on the integrated reconstruction error, effectively capturing deviations in both observable attributes and LLM-informed semantic expectations. Extensive experiments on six real-world datasets demonstrate that TERGAD consistently outperforms state-of-the-art baselines. Furthermore, our ablation studies validate the indispensable role of structural semantic guidance and the efficacy of the gated fusion mechanism. Code is available at https://github.com/Kantorakitty/TERGAD-main.

cs.CL↗
arXiv2026

Task-Aware Automated User Profile Generation for Recommendation Simulation Using Large Language Models

Large Language Model (LLM)-based agent simulation has emerged as a promising approach to meet the increasing demand for real-time and rigorous evaluation in modern recommender systems. A typical LLM-driven simulation framework comprises three essential components: the profile module, memory module, and action module. However, existing studies have primarily concentrated on enhancing the memory and action modules, with limited attention to profile generation, which plays a pivotal role in ensuring realistic agent behaviours and aligning simulated interactions with real user dynamics. Moreover, the scarcity of datasets specifically designed for recommendation simulations has led to heavy reliance on manually crafted profiles, significantly limiting the scalability and generalisability of simulation frameworks across different datasets. To address these challenges, this work proposes an Automated Profile Generation Framework for Recommendation Simulation, APG4RecSim, that constructs realistic, coherent, and robust user profiles with minimal supervision. Extensive experiments on three benchmark datasets demonstrate that APG4RecSim achieves the best overall performance on discrimination, ranking, and rating tasks, improving ranking quality by up to 7% in nDCG@10 and reducing rating distribution divergence by 8% in JSD compared to existing profile-generation baselines. Beyond overall performance gains, our results show that profiles generated by APG4RecSim are resilient to popularity- and position-induced biases and maintain stable performance across datasets and different LLMs.

cs.IR↗
arXiv2026

UFO: A Unified Flow-Oriented Framework for Robust Continual Graph Learning

Graph learning research has increasingly shifted toward continual graph learning (CGL), which better reflects real-world scenarios where graphs evolve over time. However, existing CGL methods largely assume clean supervision and overlook a critical challenge: the newly arriving portions of the graph are often noisy, due to annotation errors or adversarial corruption. This mismatch limits their applicability in practice. In this work, we study robust continual graph learning, where models must simultaneously handle catastrophic forgetting and noisy supervision in evolving graph data. We show that label noise introduces a new failure mode, catastrophic remembering, where models persistently reinforce corrupted knowledge across tasks. To address these challenges, we propose a Unified Flow-Oriented framework (UFO). First, UFO models conditional feature distributions via flow-based generative modeling and produces replay representations, mitigating forgetting without storing historical data. Second, UFO estimates instance-level reliability scores to distinguish clean from noisy nodes, reducing the impact of corrupted supervision and alleviating catastrophic remembering. Extensive experiments on four benchmark graph datasets under varying noise ratios demonstrate that UFO consistently outperforms existing methods in both accuracy and forgetting metrics. Code is available at: https://anonymous.4open.science/r/UFO.

cs.LG↗
arXiv2026

CMKL: Modality-Aware Continual Learning for Evolving Biomedical Knowledge Graphs

Biomedical knowledge graphs are increasingly large, dynamic, and multimodal, driven by rapid advances in biotechnology such as high-throughput sequencing. Machine learning models can infer previously unobserved biomedical relationships and characterize biomedical entities in these graphs, but existing knowledge graph embedding methods and their continual learning extensions either assume static graph structure or fail to exploit multimodal information under evolving data distributions. They also apply uniform regularization across all model parameters, ignoring that different modalities may exhibit distinct forgetting dynamics as the graph evolves. We propose the Continual Multimodal Knowledge Graph Learner (CMKL), a CL framework for biomedical KGs that natively encodes structure, text, and molecules, fuses them through a Mixture-of-Experts (MoE) router, and protects previously learned knowledge with standard EWC regularization and a K-means-diverse multimodal replay buffer. We evaluate CMKL on a 129K-entity biomedical continual benchmark with 10 tasks. On continual biomedical entity classification, CMKL reaches AP 0.591 versus 0.370 for the strongest structural baseline, a 60% gain that is driven by access to multimodal features and preserved across the sequence with near-zero forgetting (AF 0.008). On continual relationship prediction, CMKL reaches AP $0.062$, matching Naive Sequential and EWC (0.058) within seed noise and outperforming Joint Training (0.047, p=0.045) and LKGE (0.039). A frozen-text ablation reaches AP 0.136, more than double any jointly trained model, yet that signal is unreachable by margin-ranking gradients: the greedy-modality asymmetry lives at the representation level, not the fusion level, and MoE routing manages it by suppressing the unreachable modality without forcing it through a learned bottleneck. Code: github.com/yradwan147/cmkl-neurips2026

cs.LG↗