Searcharxiv⌕ Search

arXiv subjects

Chen Shen

Publications and source records attributed to Chen Shen.

At least 19 recordsLinked to original sources

IFRS Compliance Verification: An Open Multi-LLM Benchmark and Content-Conditioned Ensemble Classifier

Verifying corporate financial disclosures against the International Financial Reporting Standards (IFRS) is a core auditing task in which experts cross-reference disclosures with hundreds of fine-grained regulatory paragraphs: a laborious, costly, and error-prone process that motivates growing interest in large language models (LLMs) as compliance assistants. Yet single-model accuracy remains insufficient for high-stakes use, and naive ensembling is vulnerable to systematic per-model biases that can drag aggregate accuracy below that of the strongest individual annotator. This gap is addressed with a multi-stage framework, supported by a new benchmark of 19,998 IFRS regulation-disclosure pairs comprising 11,161 unanimous multi-LLM labels and 8,837 human annotations on items where the LLMs disagreed. The framework couples a three-stage domain-adapted sentence embedding pipeline (BERT masked language modeling on SEC EDGAR filings, unsupervised TSDAE and SimCSE adaptation, and supervised contrastive alignment) with a learned ensemble classifier that fuses frozen embeddings and LLM probability features from GPT-4.1, Claude Sonnet 4, and Gemini 2.5 Pro via Tree-structured Parzen Estimator (TPE) optimized gradient-boosted trees. On the disagreement set, the ensemble achieves 81.7% weighted F1, exceeding the strongest single LLM by 10.4 points and majority voting by 14.6 points, and outperforms eleven unsupervised aggregation baselines; the retrieval pipeline attains Recall@15 of 45.3% on unseen regulations. The dataset, model checkpoints, annotation platform, and classifier implementation will be publicly released.

cs.CL↗

Anharmonicity Driven by Vacancy Ordering Unlocks High-performance Thermoelectric Conversion in Defective Chalcopyrites II-III$_2$-VI$_4$

Defective chalcopyrites have recently emerged as promising thermoelectric materials because their ordered intrinsic vacancies can profoundly reshape both lattice dynamics and electronic structure. Here, we present a comprehensive theoretical investigation of the lattice thermal and carrier transport properties of II-III$_2$-VI$_4$ defective chalcopyrites by combining first-principles calculations with machine-learning interatomic potentials. We show that vacancy ordering enhances lattice distortion, leading to strong anharmonicity and metavalent bonding. The interplay of soft low-frequency phonons, strongly negative Grüneisen parameters, and a substantially enlarged four-phonon scattering phase space results in four-phonon-scattering-dominated heat transport, yielding ultralow lattice thermal conductivity. Meanwhile, systematic anion substitution at the VI-site provides an effective route to tune the electronic structure: reduced anion electronegativity weakens metal-anion hybridization, shifts anion $p$ states upward, narrows the band gap, and thereby improves electrical transport. Benefiting from this synergy between vacancy-induced phonon suppression and anion-regulated electronic optimization, CdGa$_2$Te$_4$ exhibits an ultralow lattice thermal conductivity of 0.19 W$\cdot$m$^{-1}$K$^{-1}$ and a high room-temperature $ZT$ of 0.957. This work not only predicts defective chalcopyrites as a promising platform for high-performance thermoelectrics but also provides a practical design strategy by integrating vacancy ordering, higher-order phonon scattering, and anion-dependent band engineering.

cond-mat.mtrl-sci↗

Evaluating Wi-Fi HaLow for Next-Generation Capsule Endoscopy

Capsule endoscopy is limited by its wireless link: insufficient throughput restricts image resolution and frame rate, whereas high-rate radios typically use higher carrier frequencies that experience greater attenuation through tissue. This work evaluates Wi-Fi HaLow (IEEE 802.11ah), a sub-GHz Wi-Fi standard, as an image link for capsule endoscopy. Across all tested combinations of modulation and coding scheme and bandwidth, the saturation TCP throughput reached 15.55 Mbps, and the fastest configuration also achieved the lowest energy per bit. Through power optimization strategies, the combined power consumption of the HaLow module and microcontroller at 1 frame per second (FPS) was reduced from 101.70 to 14.00 mW, which is comparable to that of Bluetooth Low Energy systems. In a simulated in vivo setting, the default rate control selected the highest tested MCS and bandwidth, indicating sufficient link quality; this configuration also had the lowest measured power in both the 1 FPS mode (13.59 mW) and the 30 FPS mode (174.21 mW). The capsule-to-receiver latency was 20.68 ms for a 24 KB frame, while the receiver-to-capsule latency was 4.77 ms for a command; this low-latency bidirectional communication supports real-time detection and manipulation for next-generation capsule endoscopy.

eess.SY↗

InfoQuant: Shaping Activation Distributions for Low-Bit LLM Quantization

Low-bit activation quantization remains a major bottleneck in efficient large language model (LLM) deployment. The difficulty is not only that activations contain outliers, but that their distributions are often poorly matched to a low-bit uniform quantizer. Existing post-training quantization (PTQ) methods suppress peaks, balance channels, or minimize reconstruction error, yet they rarely specify what activation distribution is actually easy to discretize. As a result, activations may appear numerically smoother while still incurring large quantization error because the quantization range remains wide or most values collapse into a few levels near the mean. We recast activation transformation as quantizer-facing distribution design and analyze quantization error from an information-theoretic perspective. Our analysis shows that quantization-friendly activations should jointly have a smaller numerical range and sufficient dispersion within that range. Guided by this analysis, we propose InfoQuant, a train-free method that employs Peak Suppression Orthogonal Transformation (PSOT) to shape activations into more quantization-friendly distributions. We further introduce adaptive outlier-token selection to improve the robustness of PSOT during optimization. Across multiple LLM families, InfoQuant consistently outperforms prior PTQ and end-to-end training baselines. Under W4A4KV4, it preserves 97% of floating-point accuracy on average and reduces the LLaMA-2 13B performance gap by 42% over the previous state of the art. Code is available at [https://github.com/LLIKKE/InfoQuant](https://github.com/LLIKKE/InfoQuant)

cs.LG↗

Coexistence of Altermagnetic and Compensated Ferrimagnetic Motifs in a Noncollinear Multiferroic

Collinear compensated magnets with nonrelativistic spin splitting comprise altermagnets (ALMs), whose rotation- or mirror-related opposite-spin sublattices produce momentum-selective splitting that vanishes at $Γ$, and compensated ferrimagnets (CFIMs), whose symmetry-inequivalent sublattices allow splitting throughout the Brillouin zone, including at $Γ$. Here, we show that the coplanar noncollinear magnetic state of multiferroic boracite Ni$_3$B$_7$O$_{13}$Cl hosts both motifs on distinct Ni sublattices in real space. The electronic structure and spin texture exhibit coexisting $d$-wave-like and $s$-wave-like spin-polarization components associated with the ALM and CFIM motifs, respectively. Opposite ferroelectric states exhibit reversed band-resolved spin polarizations, indicating magnetoelectric coupling, and sign reversals of linear shift and circular injection currents.

cond-mat.mtrl-sci↗

A photonic integrated comb engine for ultracold quantum gases

Cold atoms underpin quantum sensing, simulation and computation, but their coherent control demands highly stable optical fields whose generation, referencing and power scaling remain formidable integration challenges. While photonic integrated circuits have yielded compact visible lasers and high-$Q$ microresonators have enabled chip-scale optical frequency combs, these crucial technologies have largely remained functionally fragmented. Consequently, the coherent manipulation of ultracold quantum gases using a fully integrated laser-comb source has yet to be realized. Here we demonstrate a scalable, hybrid-integrated microcomb engine at 780 nm that seamlessly bridges frequency synthesis, atomic referencing and power amplification to achieve quantum state control of a Bose--Einstein condensate. By self-injection locking of electrically driven III--V lasers to high-$Q$ Si$_3$N$_4$ microresonators, we generate coherent platicon microcombs featuring 20- and 100-GHz mode spacings. Absolute referencing of the microcomb to an $^{85}$Rb transition actively suppresses long-term frequency drift from over 200 MHz to the 100-kHz level across 2,000 s. A selected comb tooth is subsequently injection-amplified to 102 mW, entirely preserving the microcomb's pristine coherence and stability. We utilize this synthesized field to construct an optical lattice, drive coherent two-photon Raman transitions, and prepare stationary spin--orbit-coupled and Raman-lattice states within an $^{87}$Rb condensate. By providing a synchronized optical grid, this atom-referenced microcomb can allow multiple optical-control channels to scale without a proportional multiplication of independent frequency references. Our work establishes a fully integrated frequency-synthesis architecture essential for realizing deployable, large-scale atomic quantum systems.

physics.optics↗

Towards Probabilistic Question Answering Over Tabular Data

Progress in question answering (QA) over tabular data has enabled reliable factual retrieval from relational tables. However, many real-world questions are probabilistic, requiring reasoning under uncertainty and latent conditional dependencies that are not directly stored in individual cells. We introduce LUCARIO, a large-scale benchmark for probabilistic QA over real-world tabular datasets, covering diverse domains, dependency patterns, and natural language variations. We propose Auto-BN, a fully automatic neuro-symbolic framework that induces a Bayesian Network from raw tables, translates natural-language questions into formal probabilistic queries, and performs exact inference. Experiments across multiple LLM backbones show that Auto-BN consistently outperforms NL2SQL, retrieval-based, and premise-based baselines, while maintaining a near-zero error rate. LUCARIO fills a relevant gap and provides a practical and scalable testbed for advancing probabilistic reasoning over structured data.

cs.CL↗

Magnetic-Order-Driven Nonlinear Photocurrents in PT-Broken Antiferromagnetic MnS2 and Altermagnetic MnSe2

Nonlinear photocurrent responses generally require inversion-symmetry breaking, but its origin can be magnetic rather than structural. In this study, we investigate the bulk photovoltaic effect in antiferromagnetic MnS2 and altermagnetic MnSe2, two pyrite-type semiconductors whose magnetic ordering breaks inversion symmetry P and its combination with time reversal PT, while the accompanying lattice distortion is minute. We calculate the shift current (SC) and injection current (IC) responses under linearly and circularly polarized light with and without spin-orbit coupling (SOC) and identify their symmetry-allowed tensor components using the corresponding magnetic and spin point groups, respectively. Linear SC and circular IC are symmetry-allowed in both MnS2 and MnSe2 irrespective of SOC, whereas linear IC and circular SC remain forbidden in MnS2 but become allowed in MnSe2 only when SOC is included. These results highlight the importance of SOC and the corresponding MPG analysis for a complete description of nonlinear charge photocurrents in magnetic materials. Beyond charge responses, MnSe2 supports linear shift and circular injection spin photocurrents in the nonrelativistic limit, whereas all spin-photocurrent responses are forbidden in MnS2. Our findings therefore establish inversion symmetry breaking induced by compensated magnetic order as a route to generating and controlling nonlinear photocurrents.

cond-mat.mtrl-sci↗

When Confidence Rises Too Early: Detecting Shortcut Reasoning via Premature Answer Commitment

The reasoning trajectory of a Large Language Model (LLM) is often treated as a verbalized description of its internal reasoning. However, such trajectories can be unfaithful: a model may rely on shortcuts to reach an answer and then post-rationalize the decision with a seemingly coherent chain of thought. Detecting this shortcut reasoning is challenging because existing monitors and verifiers mainly inspect textual traces or final outcomes, rather than how the model's belief in its answer develops during generation. We introduce ConfLens, a framework that tracks the evolution of confidence in the final answer throughout reasoning. Across three shortcut reasoning settings, we observe a common pattern of premature confidence, where shortcut samples become highly confident in the final answer at early reasoning stages. Existing confidence estimation methods, however, show limited generalizability, reliability, or efficiency for detecting this behavior. We therefore propose the Distributional Answer Commitment Score (DACS), a distributional confidence estimator that measures the entropy of the model's probability distribution over answer commitment at each reasoning step. DACS captures how concentrated the model's answer belief is without requiring ground-truth answers or task-specific verifiers. We further convert ConfLens detection results into interpretable signals for reward models to reduce their preference for shortcut reasoning. Experiments on mathematical and code reasoning tasks show that ConfLens with DACS improves shortcut reasoning detection by over 4.3% F1 compared with strong baselines and reduces the mismatch between faithfulness and correctness in reward model preferences.

cs.CL↗

Enhanced ShockBurst for Ultra Low-Power On-Demand Sensing

On-demand sensing requires battery-powered Internet-of-Things (IoT) and implantable medical devices to remain in deep sleep and activate wireless communication only when data transmission is required. In such systems, battery lifetime depends strongly on radio active time. This work investigates how communication architecture and physical layer (PHY) configuration influence radio active time by comparing connection-oriented Bluetooth Low Energy (BLE) with connectionless Enhanced ShockBurst (ESB) on identical BLE-compatible hardware. Under identical 2 Mbps PHY configurations, ESB reduces wake-up latency and energy consumption to approximately one-twentieth of BLE by eliminating connection establishment and maintenance overhead. Increasing the ESB PHY rate from 2 to 4 Mbps further shortens packet airtime by approximately 52% and reduces transmission energy by approximately 43%. Finally, a first-in, first-out (FIFO)-triggered implantable loop recorder prototype demonstrates that jointly optimizing communication architecture, PHY configuration, and buffered transmission enables sleep-wake operation and reduces total system power consumption by approximately 60% compared with conventional BLE operation. These results identify minimizing radio active time as a key design principle for ultra-low-power on-demand sensing and provide practical guidance for battery-powered sensing systems.

eess.SY↗

Equivalent Modeling of Load-Side Systems With Distributed Renewable Generation Considering Fault Responses and Nodal Voltage Coherence

Operating conditions and fault severity change both the initial states and control modes of active distribution networks. Direct capacity aggregation can therefore lose the power responses required for transmission-system dynamic analysis. This paper develops a procedure for generating low-order physical electromagnetic transient equivalents from a small set of representative operating conditions. Device power, ride-through states, load mechanical states, and local sequence voltages are combined with electrical distance to form response families. Response reconstruction and terminal simulation errors determine the retained architecture, after which bounded sensitivity calculations determine effective dynamic coefficients. The architecture and coefficients are then fixed. For a new operating condition, capacity and power balances, voltage-dependent load relations, and an initialization correction generate the model parameters from static inputs and power-flow results. A representative severe fault establishes a template for each fault type, which is reused across fault depths. Aggregation and switching-time bounds explain the roles of voltage coherence and state separation. Comparisons with direct aggregation show improved terminal responses across operating conditions and several fault types, with the largest gains under severe unbalanced faults. The method provides a reusable physical equivalent for operating-condition studies and fault-depth screening.

eess.SY↗

Orbital-resolved superexchange and topological magnon bands in MXene Fe$_2$C

Magnetic MXenes are promising candidates for future spintronics due to their intriguing properties. Nevertheless, the topological properties of magnon bands and superexchange mechanism remain relatively underexplored. In this work, we have calculated the spin wave dispersions for MXene Fe$_2$C using the linear spin wave method, with the exchange coupling parameters obtained from first-principles calculations. Owing to the staggered stacking of two Fe sub-lattices, the interlayer exchange coupling lifts the degeneracy of the ferromagnetic magnon modes. A Dirac point is identified in the magnon bands at the $K$ point. The topological properties of magnon bands, including Berry curvature, valley Chern number and edge states, are further computed by means of a two-band model. We also derive an effective Hamiltonian to explain the magnonic topology, which is protected by the $C_{3v}$ rotational symmetry. To understand the microscopic origin of the exchange couplings that govern the magnon bands, we then construct a refined model integrating perturbation theory and the tight-binding approach. The ferromagnetic superexchange coupling is mediated by the virtual hopping between the d orbitals of two distinct Fe sites via a pair of orthogonal p orbitals at the bridging C site. In detail, the intralayer exchange coupling is governed by the in-plane $p_x$ and $p_y$ orbitals, while the out-of-plane $p_z$ orbital is responsible for the interlayer exchange coupling. Our results establish a direct link between the orbital-resolved anisotropic superexchange and topological properties of the magnon bands in magnetic MXene Fe$_2$C, providing theoretical guidance for future spintronics applications.

cond-mat.mtrl-sci↗

ABSOL: Aggregated Bayesian Subsampling Orchestrated with LLMs

Large language models are increasingly used as natural-language interfaces to structured data, yet they remain unreliable when answers require consistent evidence conditioning, dependency-aware reasoning, and uncertainty estimation. Bayesian networks provide an explicit probabilistic reasoning layer, but learning useful structures from data remains costly and fragile at scale. We introduce ABSOL, a hybrid LLM-guided Bayesian network structure-learning framework that uses LLMs as bounded semantic guides. Across five discrete BN benchmarks spanning 27 to 1041 nodes, ABSOL is the only evaluated method to produce a viable graph on every benchmark, and achieves the highest Edge F_1 on every benchmark larger than 27 nodes with GPT-5.4. The four LLM augmentations, which contribute complementary semantic evidence to the statistical backbone, improve Edge F_1 over the non-LLM aggregation backbone by +0.23 on average. Complementary post-hoc refinement experiments suggest that these gains depend in part on limiting the LLM's authority over the final structure. Together, these results show that language-derived semantic knowledge can substantially improve scalable probabilistic structure learning when used as bounded guidance within a statistically grounded reasoning pipeline. The code for ABSOL is available at github.com/megagonlabs/absol-bn.

cs.CL↗

Reevaluating Bluetooth Low Energy for Ingestible Electronics

Bluetooth Low Energy (BLE) is widely used in wearable devices but has rarely been considered for ingestible electronics because of severe tissue attenuation at 2.4 GHz. In this work, we systematically reevaluate BLE for ingestible applications by benchmarking it against representative Sub-GHz schemes in terms of tissue attenuation, power consumption, throughput, reliability, bidirectional communication, latency, and system integration. Water-phantom and in vivo measurements confirm stronger attenuation at 2.4 GHz, by approximately 40 dB; however, front-end-module (FEM)-assisted BLE compensates for this loss while maintaining practical received signal levels and energy efficiency. For ingestible sensing applications requiring below 100 kbps, BLE with a 20 dBm transmission power achieves lower power consumption than the evaluated Sub-GHz alternatives. BLE also provides protocol-level reliability through retransmission and in-order packet delivery, whereas Sub-GHz links can suffer packet loss under high attenuation. In addition, BLE supports bidirectional communication with limited throughput degradation, while the evaluated Sub-GHz implementation shows a substantial reduction. End-to-end measurements further demonstrate lower BLE latency because of its native compatibility with modern computing infrastructure. Finally, BLE offers advantages in antenna form factor, ecosystem support, and system integration. These results demonstrate that properly configured BLE is a practical communication solution for next-generation ingestible electronics.

eess.SY↗

What Eviction Destroys: A Restore-Counterfactual Audit of Forgetting in Agent Memory

Agent memory systems must discard stored information when their history exceeds a fixed token budget. Existing budget-accuracy frontiers quantify the resulting loss in accuracy, but do not distinguish irreversible losses caused by eviction from recoverable retrieval failures. We introduce the restore counterfactual, a per-question paired intervention that reinstates the question's gold evidence in the read-time context and reruns the same reader. Combining the change in correctness with whether the evidence was retained after eviction classifies each oracle-answerable error as recoverable, irreversible, or residual; in the residual case, the answer remains incorrect after restoration. We evaluate FIFO, random, redundancy-aware, and LLM-importance eviction on LongMemEval-S at three budgets and under two retrieval regimes, using GPT-4o-mini as the primary reader and judge and GPT-5.4-mini as a robustness reader. Under top-k retrieval at an 80k-token budget, the irreversible share among errors corrected by restoration is 0.67-0.73 for FIFO, random, and redundancy-aware eviction, compared with 0.60 for LLM-importance. At 8k tokens, it reaches 1.00 for all four policies. Recoverable errors occur under top-k retrieval at 80k tokens but are absent under forced-gold injection by construction, so budget-accuracy results are not directly comparable unless the retrieval regime is reported. An exploratory matched-accuracy analysis detects no difference in irreversible rate among accuracy-matched policy pairs at a resolution of 1.2-6 percentage points. The same analysis detects the deliberately destructive control. To our knowledge, this is the first per-item, per-question restore-counterfactual audit of eviction for external agent-memory stores on a standard conversational benchmark.

cs.CL↗

BudgetSchemaBench: A Budget-Swept Diagnostic for Schema Context in Text-to-SQL

Data agents over structured sources must fit database schema into the model's context window. Large catalogs can span many databases and thousands of columns, so cost constraints may require choosing between table coverage and serialization detail well before the context window is full. We introduce BudgetSchemaBench, an execution-grounded diagnostic for this setting. Its construction derives relevance labels mechanically from gold SQL, without human- or LLM-authored ground truth. Using a pooled 80-database catalog, we sweep four schema-context budgets and compare three representations while keeping each retriever's table ranking fixed. A source-namespace check rejects queries that obtain the correct result from the wrong database. The evaluation covers three conditions: end-to-end retrieval; frozen-gold, in which the required tables are guaranteed; and a probe that removes those tables. For the primary solver with raw serialization, raising the budget from 2.5% to 50% of the catalog improves execution accuracy on 1,279 held-out questions by 18 percentage points under lexical retrieval but only 3 under dense retrieval; the dense retriever already finds most required tables at the smallest budget. When the required tables are removed, 94.6% of correct predictions name one of them exactly, consistent with reconstruction of absent schema from parametric knowledge. For the two main solvers in the frozen-gold condition, the three representations differ by at most 2 percentage points, and the widest paired 95% confidence interval bounds the difference within +/-4 points. We observe the same qualitative patterns with one reasoning model from a different family. When retrieval is coverage-limited, execution accuracy is more sensitive to the schema budget than to the tested serializations. The diagnostic and the code used to construct and evaluate it are publicly available.

cs.CL↗

Who Maintains Agent Skills? A Longitudinal Study of Human-Governed, AI-Assisted Skill Maintenance

Lifelong LLM agents increasingly rely on external skill artifacts as one element for preserving and reusing capabilities over time. These skills (usually portable Markdown files such as SKILL.md) describe when and how to apply a capability and must be corrected, expanded, and consolidated as tools and usage patterns shift over deployment. Recent work seeks to automate skill curation, but it largely evaluates against automated baselines and treats human maintenance as an unmeasured bottleneck. We study that missing process directly. We mine the full commit histories of five public AI-skill repositories, a purposive sample of AI-tooling organizations, covering 873 commits, 143 skill files, and 254 substantive post-creation edits from October 2025 to June 2026. We code each edit with pre-registered governance, operation, and trigger-evidence codebooks. Three findings emerge. First, every substantive edit is authored or merged through a named human account, while 62% carry an AI co-author trailer, with large repository-level variation. Second, these edits are genuine curation: an audited sample shows that most change skill content, and the coded operations are dominated by additions and corrections. Third, a pre-registered rule-likeness axis fails its reliability gate; reliably coding rule-likeness from commit artifacts remains an open measurement problem. We release the corpus, codebooks, mining scripts, and a replay protocol for automated skill curators. For self-evolving agents, public skill maintenance currently looks less like an autonomous pipeline than a human-governed, AI-assisted loop that future curators must measure against and operate within.

cs.CL↗

A Study on THz Plasmonics in a CMOS Continuum Transistor Array

This work addresses the limitations of CMOS at terahertz (THz) frequencies, where charge transit time and parasitic capacitances restrict the maximum operating frequency, fmax. As transistor dimensions shrink, reduced current handling capabilities further challenge CMOS, necessitating novel circuit design approaches for the THz domain. By leveraging the plasma characteristics of electron channels in CMOS transistors, this study explores a potential solution for THz signal amplification. Key mechanisms in plasma wave amplification within a continuum transistor array (CTA) formed by 28 nm fully depleted silicon-on-insulator (FD-SOI) CMOS transistors are investigated. A hydrodynamic transport model combined with Pierce's theory is presented to describe plasma wave propagation along the CTA. Simulations of gated amplifiers demonstrate the potential for THz signal amplification in advanced fabrication nodes. Finally, a proof-of-concept plasma wave amplifier operating at 700 GHz has been designed and fabricated, exhibiting amplification along the plasma wave propagation path.

eess.SY↗