Searcharxiv⌕ Search

arXiv subjects

Xue Li

Publications and source records attributed to Xue Li.

At least 19 recordsLinked to original sources
arXiv2026

Liouville Theorems for Semilinear Parabolic Equations Involving the Nonlinear Gradient Term

In this paper, we prove the Liouville-type theorem for equation $u_t-Δu=u^p+M|\nabla u|^q$ via the integral Bernstein method, where $q=2p/(p+1)$ is critical and $M<0$. As an application, we can establish a universal priori estimate for this equation by using the doubling lemma. These results generalize the previous work of Liang and Zhang. We can also prove the Liouville-type theorem for equation $u_t-Δu=u^p+M|\nabla u|^2$, which corresponds to the supercritical case.

math.AP↗
arXiv2026

Identify, Classify, Act: Per-Instruction Controlled Compliance for LLMs over External Data

LLMs over external data face a per-instruction tension: a single document or tool return often interleaves legitimate directives with adversarial prompt injections, and the model must follow the former while rejecting the latter. Existing defenses suppress or trust all external instructions, collapsing the safety-utility frontier and forcing a choice between over-refusal and over-compliance. We argue the missing capability is \textbf{per-instruction credit attribution} and formalize it as External-Data Instruction Classification, an identify-classify-act decision over each embedded directive. We propose \textbf{EDIC}, a decomposed reward framework for per-instruction compliance. A scene-grounded pipeline injects mixed beneficial and harmful instructions with counterfactual filtering, while a generative judge is initialized by SFT and refined with GRPO to attribute compliance at the instruction level. The judge then produces a reward that separately encourages beneficial compliance and penalizes harmful compliance for RL training. Across two backbones and five benchmarks, EDIC improves both safety and utility over the strongest prior defense, lifting harmful-rejection by up to 7.7\% and Arena-Hard-Auto utility by 12.5\% on Qwen3-4B. The code repository is hosted at https://github.com/yingyingxia666/EDIC.

cs.CL↗
arXiv2026

Density Functional Theory for 2D Transition-Metal Dichalcogenides with Extended Hubbard Parameters

Accurate modelling of the band-edge electronic structure of transition metal dichalcogenides (TMDs), such as MoS$_2$, is essential for understanding their optical, electronic and spintronic properties and enabling future applications. Here, we supplement the standard PBE exchange-correlation functional with on-metal ($U$) and metal--chalcogen ($V$) Hubbard corrections, which can control the orbital composition of band-edge states and consequently improve the quantitative accuracy of various properties. For MoS$_2$, MoSe$_2$, WS$_2$, and WSe$_2$, we optimise the $U$ and $V$ parameters by comparison with experimentally measured spin--orbit splittings at the conduction and valence band edges, and show that these optimal choices also improve agreement of the computed band gap, and ferroelectric potential drop in rhombohedral bilayers, with experimentally measured values. This provides a highly efficient, scalable framework for quantitatively accurate, high-throughput calculations of monolayer and multilayer TMDs, suitable for implementation in 2D-materials databases, as well as large-scale electronic and spintronic device modelling.

cond-mat.mes-hall↗
arXiv2026

The Silent Failures in Agentic Data Science

Large language models have significantly lowered the barrier to writing code. Naturally, this has also led to the development of data science agents that promise automating the design and execution of data science from task formulation to model development. Existing evaluations of agentic data science (agentic DS) assess downstream predictive performance and code correctness, providing preliminary insight in agentic DS capabilities. We argue that these evaluations overlook the fundamental principles of data science: methodological data science- and domain knowledge. As such, only assessing downstream performance masks methodological failures such as data leakage and inappropriate validation, limiting the development of robust agentic DS systems. In this paper, we evaluate agentic DS beyond accuracy from three different angles: 1) a large-scale analysis of failure modes in common agentic DS frameworks and models across 220 data science tasks, 2) a reusable and extensible test suite with curated data science tasks that test for six specific failures in a controlled manner, and 3) a qualitative assessment of agentic DS pipelines against expert solutions on Kaggle competitions. We find that the majority of agentic solutions contain at least one failure mode despite the complexity of agentic harness or model capacity. Moreover, we identify a positive correlation between the occurrence of data leakage failures and predictive performance, confirming the necessity to evaluate agents beyond accuracy. Our qualitative analysis shows that DS agents generally lack problem solving creativity and domain knowledge, compared to competition-winning data scientists. We believe that principled failure mode analysis, as presented here, should be integral part of agentic DS evaluations, and that the insights we surface will be key in developing trustworthy agentic DS pipelines.

cs.AI↗
arXiv2026

Seeing Is No Longer Believing: Frontier Image Generation Models, Synthetic Visual Evidence, and Real-World Risk

Image generation systems can produce plausible photographs, readable documents, and consistent depictions of people and places. When these artifacts are presented as records of real events, they can influence decisions in news, finance, identity verification, medicine, and law. This narrative review examines selected public model documentation, incident reports, research, and governance sources available through 1 October 2026, with English and Chinese community material providing illustrative context. We distinguish vendor capability claims, documented incidents, experimental findings, and prospective harm pathways. The analysis connects realism, text rendering, reference consistency, editing, grounding, and production cost to the conditions under which synthetic images acquire evidentiary authority. Historical incidents illustrate these pathways; they do not establish misuse rates for current models. We compare provider restrictions, provenance systems, watermarking, platform labeling, and policy obligations, and explain how their functions differ from independent verification of a depicted event or transaction. The framework links artifact types and decision contexts to the functions of available controls. High-stakes decisions call for authenticated source records, corroboration through trusted channels, and proportionate review before action.

cs.CL↗
arXiv2026

An Inspectable LLM Council for Multi-Model Research Answer Aggregation

Long-form research questions often require answers that combine complementary details, reconcile conflicting estimates, and retain qualifications across several large language model (LLM) outputs. We present an inspectable LLM Council with two synthesis stages: an analyst organizes three independent candidate answers into a structured textual state, and a separately invoked writer composes the final response from the question and that state. We evaluate the workflow on 100 closed-book tasks from the Deep Research Accuracy, Completeness, and Objectivity (DRACO) benchmark, retaining 600 final answers, 100 analyst states, and 720 whole-answer judgments. Under the primary rubric judge, Council scores 70.98, exceeding GPT and Gemini by 6.18 and 8.34 points; its 0.47-point difference from Claude has a 95% paired interval of $[-0.69,1.61]$. In the four-arm fusion comparison, Council scores 1.87 points above direct fusion (95% paired interval $[0.33,3.48]$) and covers 51.1% of positive criteria covered by exactly one candidate, compared with 43.7% for direct fusion. On an exploratory 68-task subset with matching returned model labels, direct fusion scores higher. The full comparison characterizes workflows that differ in structure and generation budget; estimating the analyst stage's effect requires a controlled component study. Traced cases show how selected estimates, provenance qualifications, and selection decisions pass through the saved state into final answers.

cs.CL↗
arXiv2026

ReCoVR: Closing the Loop in Interactive Composed Video Retrieval

Composed video retrieval (CoVR) searches for target videos using a reference video and a modification text, but existing methods are restricted to a single interaction round and cannot support the progressive nature of real-world visual search. To bridge this gap, we first formalize interactive composed video retrieval, a multi-turn extension of CoVR, where users progressively refine their search intent through natural-language feedback across turns. Adapting existing interactive retrieval methods to this setting reveals two structural weaknesses: reliance on a single retrieval channel and an open-loop retrieval design that consumes user feedback but does not diagnose whether its own retrieval trajectory is drifting or stagnating. To address these limitations, we propose ReCoVR (Reflexive Composed Video Retrieval), a dual-pathway architecture built on reflexive perception, where the system treats its retrieval history as diagnostic evidence alongside user feedback. Specifically, an Intent Pathway routes heterogeneous feedback to complementary retrieval channels, while a Reflection Pathway performs trajectory-level reflection to monitor result evolution and correct retrieval errors across turns. Experiments on multiple benchmarks show that ReCoVR consistently outperforms interactive baselines, notably achieving 74.30% R@1 after just one interactive round on the WebVid-CoVR-Test dataset.

cs.IR↗
arXiv2026

BVI: Lightweight, Data-Centric Blockchain-Based Verification of Identity Claims

A person who answers an unexpected call claiming to come from a bank has no way to check the claim. Australian text messaging has labelled a message as unverified when the sender identifier is not registered since 1 July 2026, but a voice call still arrives with nothing behind it, and voice cloning has removed the last cue recipients relied on. We present BVI, which answers one question for the recipient: did the calling party prove it holds a credential a registered organisation issued for this call? BVI keeps the organisational record, its authorised channels and its revocation state on a public ledger in a directly queryable form, and puts all decision logic in the handset, which performs eleven checks, pays no transaction fee and holds no full-chain state. We define ten attack classes plus the case in which revocation cannot be resolved, compare them in a 10-by-4 coverage matrix spanning BBCA, the content digest, the detector and composed BVI, and run 27 automated scenario tests against isolated Hardhat fixture states of the BVI contract; all 27 pass. For media substitution and synthetic speech, the contract tests validate commitment and gating properties rather than claiming detector accuracy. The mandatory per-session anchor costs about 91.5k gas and is invariant in call duration and hop count; each participating intermediary additionally contributes one optional attestation write. In a 20,000-session-per-cell path simulation, at one quarter carrier participation BVI detects 20.6 per cent of randomly located in-path rewrites versus 0.1 per cent for the every-hop comparison, while identity and content evidence remain available even when path evidence is indeterminate. We also quantify the throughput ceiling of the anchoring design.

cs.CR↗
arXiv2026

The Answer-Basin Representation Hypothesis: We Are Not Probing or Steering Concepts

Linear probing and activation steering use linear directions to predict and control behavior-level concepts such as correctness, safety, and social bias in question answering. We call these \emph{behavior-level concept directions}. Drawing on the Linear Representation Hypothesis (LRH) and circuit studies, these directions are often interpreted as concept representations. Yet controlled evidence for linear concept structure and local mechanisms does not establish that these directions represent the intended behavioral concepts, leaving probing and steering without a unified theoretical account. We propose the \emph{Answer-Basin Representation Hypothesis} (ABRH): the model's own answer measure organizes the linear structure of these directions. For each question, all continuations yielding the same answer form an answer basin, whose mass is their total probability; these masses define the model's answer distribution. ABRH posits that its concentration before generation and the relative mass of each answer after generation are represented along linear directions shared across questions. Experiments span four Qwen2.5 and Gemma-3 models on correctness, social bias, and safety tasks. Decoupling concept labels from basin mass shows that probing and steering exhibit concept-consistent effects when labels align with mass orderings, weaken as mass gaps shrink, and reverse under conflict. Probes trained solely on mass orderings among wrong answers still select correct answers; a fixed steering vector can instead favor wrong answers when labels conflict with mass orderings. These results support an answer-measure account of behavior-level concept directions and of when probing and steering succeed, fail, or reverse.

cs.CL↗
arXiv2026

Verbal tics in frontier language models: A critical review of current releases, research evidence, and public discussion

Repeated praise, canned reassurance, familiar contrasts, and conspicuous vocabulary are recurring subjects in discussions of large language models. Their interpretation depends on context: a conventional phrase may be useful, while a fluent answer may reinforce a false belief. This critical review examines linguistic habits and sycophancy across eight developer families: OpenAI, Anthropic, Google DeepMind, xAI, ByteDance, Moonshot AI, DeepSeek, and Xiaomi. We verify current public offerings against official release and API documentation, with an evidence cutoff of 1 October 2026. We synthesize research on lexical overrepresentation, stylistic variation, social warmth, and agreement, alongside benchmark methods and dated English and Chinese public discussions. The research reviewed documents recurring linguistic patterns and agreement that distorts judgment; comparable measurements of the newest releases are sparse in the retrieved set. Current user reports include both complaints and improved writing, with experiences varying by task and prompting. We propose separate measures of recurrence, contextual appropriateness, and belief distortion, with precise service records and language-specific annotation. This framework makes claims about writing quality and conversational reliability testable as model services change.

cs.CL↗
arXiv2026

From language-model stock rankings to testable economic rules: A computational audit

We test the stability, reproducibility and investment outcomes of language-model stock rankings. Four models and five numerical comparators share a portfolio engine over 72 monthly holding periods in the Shanghai Stock Exchange (SSE) 50, China Securities Index (CSI) 300 and CSI 500. Rankings use nine characteristics, and five repeated SSE 50 runs measure variation under identical inputs. Linear rules fitted to development-period model preferences are frozen before unseen-month, larger-pool and controlled-intervention tests. Their mean Spearman agreement with model rankings is 0.923-0.984 in the SSE 50 and 0.795-0.985 after transfer. Aggregate rank-change error falls relative to a zero-change prediction in twelve archived feature-group comparisons and eight matched single-feature comparisons, with Holm adjustments applied in separate nine-plus-three and six-plus-two families. Prediction of individual entries and exits remains weak (event Jaccard 0.000-0.125). Historical mean model compound annual growth rates range from 6.26% to 11.17%. At 10 basis points per side and six-month blocks, the twelve-comparison model-minus-rule return family and factor-controlled associations yield no adjusted finding. Three higher-cost, twelve-month-block comparisons favor a Terra rule within their twelve-test slices, with no adjusted finding across the full 144-test sensitivity grid. Two input-intervention batches totaling 5,184 responses supply paired intervention-return tests. The three-model batch has no bootstrap-adjusted finding at the primary block length; a Luna row-order effect appears under heteroskedasticity- and autocorrelation-consistent (HAC) adjustment within its three-test family but not in a pooled 24-test adjustment. Compact rules approximate aggregate rankings; return conclusions depend on comparison families, uncertainty methods and tie priorities.

cs.CE↗
arXiv2026

When Parallel Drafter Meets Parallel Speculative Decoding

DSpark-style parallel drafters have made speculative decoding highly effective, yet their draft phase remains serialized on the critical path of every round. Parallel speculative decoding (PSD) overlaps drafting with verification, yet existing methods must guess the accepted prefix and bonus token in advance: a wrong guess reverts the whole batch to serial drafting. We present DPara, a PSD framework that reuses effective parallel drafters yet guarantees backbone--verification overlap in every round, thereby eliminating this probabilistic fallback altogether. While the target verifies, DPara's diffusion backbone precomputes draft representations for every acceptance boundary with the bonus left unspecified; a lightweight autoregressive head then combines the revealed verification outcome with the matching precomputed representation to emit the next round's draft tokens almost instantly---fully parallelizing the dominant backbone forward with verification and leaving only the negligible head cost serial. Experiments on Qwen3-8B and Qwen3-14B across seven math, coding, and chat benchmarks show that DPara achieves average speedups of $3.21\times$ and $3.52\times$ over autoregressive decoding, surpassing the strongest serial and parallel speculative decoding baselines alike.

cs.CL↗
arXiv2026

Cassette: Case-to-Case Structural Distillation for Efficient Legal Case Retrieval

Legal case retrieval (LCR) is an essential tool for not only assisting legal practitioners to efficiently retrieve precedents but also enabling ordinary individuals to find valuable legal case information without relying on expensive professional legal services. Our previous work CaseLink demonstrated the effectiveness of using case to case graph structures to improve retrieval accuracy. However, its high computational cost during inference on large-scale legal databases limits its practical use in real-world settings. The main inefficiency comes from constructing test time graphs and computing pairwise term frequency similarities of cases. This process has O(n^2) complexity for n legal cases, making the runtime prohibitive as the number of candidates grows. For example, the retrieval time for one query on a database (COLIEE2022) with 1,563 candidate cases is more than 500 milliseconds, while the runtime would increase drastically to more than 3,500 seconds for a database (LeCaRDv2) with 55,192 candidate cases. To further enhance the retrieval performance while achieving a significant speed-up, in this extension paper, Cassette framework is proposed with a distillation strategy involving ranking objective and eigen-matching objective for an effective transfer of knowledge from a powerful and well-trained heavy teacher retriever to a lightweight and efficient hybrid student dual encoder. Specifically, the student query encoder is implemented as a multilayer perceptron model designed for fast online processing, whereas the student candidate encoder adopts a GNN architecture, suitable for an offline manner within the case database. Extensive experiments are conducted on three benchmark datasets, and the results verify the effectiveness of the ranking distillation while achieving high efficiency. The code has been released on https://github.com/yanran-tang/Cassette/.

cs.IR↗
arXiv2026

DSE-VTG: Dual-Side Enhancement for Training-Free Video Temporal Grounding

Text-guided Video Temporal Grounding (VTG) aims to localize the relevant segments in an untrimmed video based on text queries, yet collecting dense temporal annotations and training task-specific models remain costly and brittle under distribution shift. Recent training-free VTG approaches mitigate this issue by directly matching pretrained vision-language representations, but they still face two fundamental information bottlenecks: frame-wise visual encoding overlooks temporal dynamics, while fixed query embeddings cannot resolve query ambiguity. To address these issues, we propose DSE-VTG, a \underline{D}ual-\underline{S}ide \underline{E}nhancement framework that addresses both without any task-specific training. On the visual side, Multi-scale Similarity Fusion (MSF) combines frame- and clip-level similarities into a unified, temporally aware similarity profile. On the textual side, Query-level Test-Time Adaptation (Q-TTA) optimizes a lightweight additive offset to adapt the query embedding to the video at test time, without finetuning the backbone or calling external large language models. Extensive experiments on three standard and two OOD benchmarks show that DSE-VTG achieves state-of-the-art performance among training-free methods. On Charades-STA, it improves mIoU over the strongest prior training-free method by 5.61 points. Under distribution shift, DSE-VTG reaches 50.86 mIoU on Charades-CG Novel-Word, surpassing the strongest supervised baseline by 2.76 mIoU. Our code will be released upon acceptance.

cs.CV↗
arXiv2026

Evolution of Stellar Activity and Habitable Zone (EATEN): III. X-ray Activity of Dwarfs in Open Clusters and Field Stars

Stellar X-ray emission serves as a direct diagnostic of coronal activity, which is fundamentally linked to coronal heating processes. It also strongly influences the atmospheres and long-term habitability of orbiting exoplanets. Investigating how this high-energy emission evolves is therefore essential for understanding the evolution of stellar magnetic dynamos and planetary atmospheres and habitability. In this work, we investigate the evolution of X-ray activity and XUV irradiation for a sample of F-M dwarf stars based on Chandra and XMM-Newton observations. We find that F- and G-type stars broadly follow the traditional evolutionary picture of an early saturated (or weakly declining) phase followed by a modest decline, whereas K- and M-type stars exhibit a clear three-phase evolution of a saturated phase, an intermediate phase of rapid decay, and a final modest decline phase. By combining X-ray, ultraviolet, and Ca II H&K bands, we show that coronal emission becomes increasingly dominant toward lower-mass stars. Based on the cumulative XUV emission calculated from our fitted relation, planets around F- and G-type stars experience relatively moderate XUV environments, while those around K- and M-type stars may exceed the empirical cosmic shoreline shortly after reaching the main sequence, though this conclusion depends on the adopted shoreline value.

astro-ph.SR↗
arXiv2026

Flare waiting time as a novel proxy of stellar magnetic activity

Stellar flares have long served as stellar magnetic activity tracers. The flare waiting time, defined as the interval between two consecutive flares, provides a valuable diagnostic for probing underlying mechanisms of energy storage and release in stellar atmospheres. In this work, utilizing flaring M dwarfs observed by the Kepler satellite, we establish a simple yet effective activity proxy, i.e., median flare waiting time ($t_{\rm{w, med}}$). Our results show that the $t_{\rm{w, med}}$ can trace long-term activity levels similar to the flare rate. However, $t_{\rm{w, med}}$ corresponding to different waiting time percentiles may encode richer physical insights than flare rate. In addition, for the first time we construct a clear relation between $t_{\rm{w, med}}$ and stellar rotation period, which is quite similar to the canonical activity--rotation relation. More intriguingly, this relation exhibits a more notable supersaturation effect (i.e., below a critical rotation period, $t_{\rm{w, med}}$ begins to increase instead of keeping constant) compared to other activity proxies. The filling factor--rotation period relation favors poleward migration of active regions as the explanation for supersaturation, rather than coronal stripping. With the dramatic increase in stellar flares detected by missions like TESS and the upcoming Earth 2.0 satellite, $t_{\rm{w, med}}$ will become a powerful diagnostic for probing stellar magnetic activity and underlying physics.

astro-ph.SR↗
arXiv2026

GeoExplain: Multimodal Reasoning based on Hierarchy of Visual Information in Street View

Multimodal reasoning is a process of understanding, integrating and inferring information across different data modalities. It has recently attracted surging academic attention. Although there are various tasks for evaluating multimodal reasoning ability, they still have limitations. Reasoning on hierarchical visual clues at different levels of granularity, i.e., local details and global context, is of little discussion, despite its frequent involvement in human reasoning. To bridge the gap, we introduce a challenging dataset, namely GeoExplain, which evaluates explainable geo-localization. Given a street view image, the task is to predict its location and provide a detailed explanation. GeoExplain consists of 40350 panoramas-location-explanation tuples. Each instance contains a set of street-view panoramas, a location on street level, and human-expert explanations describing how the location can be inferred from the visual content of panoramas. Additionally, we present a multimodal and multilevel reasoning method, namely SightSense which can make predictions and generate a comprehensive explanation. Our analysis and experiments demonstrate its outstanding performance in GeoExplain.

cs.CL↗
arXiv2026

Beyond Scale and Generation: Understanding Language Model-based Entity Matching

Entity matching identifies records that refer to the same real-world entity. Language models can be adapted to this task through bi-encoder, cross-encoder, and generative matcher architectures. However, prior studies often conflate matcher architecture with differences in model backbone, model variant(reflecting different pretraining objectives), and model size, making it difficult to isolate the sources of performance gains. We address this issue through a controlled factorial study spanning three matcher architectures, three model variants and three model sizes from the Qwen3 family, and nine datasets, totaling 1,215 fine-tuning runs. We also evaluate cross-dataset transferability and computational cost. Our results show that model variant is critical for bi-encoders: embedding-oriented variants provide stronger initialization and more favorable representation geometry predictive of downstream matching performance. Cross-encoders retain a consistent advantage over bi-encoders because they jointly encode record pairs rather than representing each record independently, although larger models partially narrow this gap. Generative matchers do not universally outperform cross-encoders. Instead, their advantages concentrate under distribution shift, including subtle unseen differences in record schemas and cross-dataset transfer. We further find that larger models rely more heavily on shortcut learning and therefore do not necessarily perform better. These findings clarify the factors underlying performance differences across matcher architectures and motivate future research and benchmark designs that better disentangle architectural choices from model-level factors while explicitly evaluating distribution shift and cross-dataset transferability. We release our experimental results, code, training scripts, and evaluation data at https://github.com/Jantory/llm-trained-matcher.

cs.DB↗