arXiv subjects

Tianhang Zhang

Publications and source records attributed to Tianhang Zhang.

18 recordsLinked to original sources

arXiv2026

Development of a High-Performance Permanent Magnet System for Ion Trapping Experiments

This work presents the design and fabrication of a compact permanent magnet based on an optimized stacked structure of fifteen NdFeB rings. The tunable NS-SN-NS configuration generates a central magnetic field of 0.8T with a reconstructed uniformity of 99.988% within a 1mm radius spherical volume. The remaining field inhomogeneity is dominated by radial dipole components. Requiring neither cryogenics nor external power, this design provides a high-performance and cost-effective alternative to superconducting magnets for applications in ion-trap development and Fourier-transform ion cyclotron resonance mass spectrometry.

physics.atom-ph↗

arXiv2026

Development of a compact cryogenic Penning trap with permanent magnets: An intermediate step toward the Shanghai Penning Trap

Penning traps, renowned for their unparalleled precision in determining fundamental properties such as mass and magnetic moments, are cornerstone instruments in modern physics. Their applications span from nuclear structure studies to stringent tests of quantum electrodynamics and CPT invariance. Although Penning traps have been demonstrated for fundamental studies, often employing superconducting magnets, their high cost and operational complexity remain challenges. In this work, we report the development of a compact cryogenic Penning trap that utilizes a permanent magnet to provide a confining magnetic field, offering a more economical and flexible alternative. We have successfully demonstrated all core functionalities of this system, including ion generation, transport, confinement, manipulation, and signal detection. This compact trap not only serves as a vital technical testbed for the development of the Shanghai Penning Trap, but also establishes a cryogenic Penning-trap experiment platform for ion trapping and cooling applications as well as envisaged spectroscopic studies applications.

physics.atom-ph↗

arXiv2025

Using large language models to produce literature reviews: Usages and systematic biases of microphysics parametrizations in 2699 publications

Large language models afford opportunities for using computers for intensive tasks, realizing research opportunities that have not been considered before. One such opportunity could be a systematic interrogation of the scientific literature. Here, we show how a large language model can be used to construct a literature review of 2699 publications associated with microphysics parametrizations in the Weather and Research Forecasting (WRF) model, with the goal of learning how they were used and their systematic biases, when simulating precipitation. The database was constructed of publications identified from Web of Science and Scopus searches. The large language model GPT-4 Turbo was used to extract information about model configurations and performance from the text of 2699 publications. Our results reveal the landscape of how nine of the most popular microphysics parameterizations have been used around the world: Lin, Ferrier, WRF Single-Moment, Goddard Cumulus Ensemble, Morrison, Thompson, and WRF Double-Moment. More studies used one-moment parameterizations before 2020 and two-moment parameterizations after 2020. Seven out of nine parameterizations tended to overestimate precipitation. However, systematic biases of parameterizations differed in various regions. Except simulations using the Lin, Ferrier, and Goddard parameterizations that tended to underestimate precipitation over almost all locations, the remaining six parameterizations tended to overestimate, particularly over China, southeast Asia, western United States, and central Africa. This method could be used by other researchers to help understand how the increasingly massive body of scientific literature can be harnessed through the power of artificial intelligence to solve their research problems.

cs.AI↗

arXiv2024

RepEval: Effective Text Evaluation with LLM Representation

The era of Large Language Models (LLMs) raises new demands for automatic evaluation metrics, which should be adaptable to various application scenarios while maintaining low cost and effectiveness. Traditional metrics for automatic text evaluation are often tailored to specific scenarios, while LLM-based evaluation metrics are costly, requiring fine-tuning or rely heavily on the generation capabilities of LLMs. Besides, previous LLM-based metrics ignore the fact that, within the space of LLM representations, there exist direction vectors that indicate the estimation of text quality. To this end, we introduce RepEval, a metric that leverages the projection of LLM representations for evaluation. Through simple prompt modifications, RepEval can easily transition to various tasks, requiring only minimal sample pairs for direction vector construction. Results on fourteen datasets across two evaluation tasks demonstrate the high effectiveness of our method, which exhibits a higher correlation with human judgments than previous methods, even in complex evaluation scenarios involving pair-wise selection under nuanced aspects. Our work underscores the richness of information regarding text quality embedded within LLM representations, offering insights for the development of new metrics.

cs.CL↗

arXiv2024

SH2: Self-Highlighted Hesitation Helps You Decode More Truthfully

Large language models (LLMs) demonstrate great performance in text generation. However, LLMs are still suffering from hallucinations. In this work, we propose an inference-time method, Self-Highlighted Hesitation (SH2), to help LLMs decode more truthfully. SH2 is based on a simple fact rooted in information theory that for an LLM, the tokens predicted with lower probabilities are prone to be more informative than others. Our analysis shows that the tokens assigned with lower probabilities by an LLM are more likely to be closely related to factual information, such as nouns, proper nouns, and adjectives. Therefore, we propose to ''highlight'' the factual information by selecting the tokens with the lowest probabilities and concatenating them to the original context, thus forcing the model to repeatedly read and hesitate on these tokens before generation. During decoding, we also adopt contrastive decoding to emphasize the difference in the output probabilities brought by the hesitation. Experimental results demonstrate that our SH2, requiring no additional data or models, can effectively help LLMs elicit factual knowledge and distinguish hallucinated contexts. Significant and consistent improvements are achieved by SH2 for LLaMA-7b, LLaMA2-7b and Mistral-7b on multiple hallucination tasks.

cs.CL↗

arXiv2024

ECon: On the Detection and Resolution of Evidence Conflicts

The rise of large language models (LLMs) has significantly influenced the quality of information in decision-making systems, leading to the prevalence of AI-generated content and challenges in detecting misinformation and managing conflicting information, or "inter-evidence conflicts." This study introduces a method for generating diverse, validated evidence conflicts to simulate real-world misinformation scenarios. We evaluate conflict detection methods, including Natural Language Inference (NLI) models, factual consistency (FC) models, and LLMs, on these conflicts (RQ1) and analyze LLMs' conflict resolution behaviors (RQ2). Our key findings include: (1) NLI and LLM models exhibit high precision in detecting answer conflicts, though weaker models suffer from low recall; (2) FC models struggle with lexically similar answer conflicts, while NLI and LLM models handle these better; and (3) stronger models like GPT-4 show robust performance, especially with nuanced conflicts. For conflict resolution, LLMs often favor one piece of conflicting evidence without justification and rely on internal knowledge if they have prior beliefs.

cs.CL↗

arXiv2024

RAGChecker: A Fine-grained Framework for Diagnosing Retrieval-Augmented Generation

Despite Retrieval-Augmented Generation (RAG) showing promising capability in leveraging external knowledge, a comprehensive evaluation of RAG systems is still challenging due to the modular nature of RAG, evaluation of long-form responses and reliability of measurements. In this paper, we propose a fine-grained evaluation framework, RAGChecker, that incorporates a suite of diagnostic metrics for both the retrieval and generation modules. Meta evaluation verifies that RAGChecker has significantly better correlations with human judgments than other evaluation metrics. Using RAGChecker, we evaluate 8 RAG systems and conduct an in-depth analysis of their performance, revealing insightful patterns and trade-offs in the design choices of RAG architectures. The metrics of RAGChecker can guide researchers and practitioners in developing more effective RAG systems. This work has been open sourced at https://github.com/amazon-science/RAGChecker.

cs.CL↗

arXiv2024

Attention Fusion Reverse Distillation for Multi-Lighting Image Anomaly Detection

This study targets Multi-Lighting Image Anomaly Detection (MLIAD), where multiple lighting conditions are utilized to enhance imaging quality and anomaly detection performance. While numerous image anomaly detection methods have been proposed, they lack the capacity to handle multiple inputs for a single sample, like multi-lighting images in MLIAD. Hence, this study proposes Attention Fusion Reverse Distillation (AFRD) to handle multiple inputs in MLIAD. For this purpose, AFRD utilizes a pre-trained teacher network to extract features from multiple inputs. Then these features are aggregated into fused features through an attention module. Subsequently, a corresponding student net-work is utilized to regress the attention fused features. The regression errors are denoted as anomaly scores during inference. Experiments on Eyecandies demonstrates that AFRD achieves superior MLIAD performance than other MLIAD alternatives, also highlighting the benefit of using multiple lighting conditions for anomaly detection.

cs.CV↗

arXiv2024

RefChecker: Reference-based Fine-grained Hallucination Checker and Benchmark for Large Language Models

Large Language Models (LLMs) have shown impressive capabilities but also a concerning tendency to hallucinate. This paper presents RefChecker, a framework that introduces claim-triplets to represent claims in LLM responses, aiming to detect fine-grained hallucinations. In RefChecker, an extractor generates claim-triplets from a response, which are then evaluated by a checker against a reference. We delineate three task settings: Zero, Noisy and Accurate Context, to reflect various real-world use cases. We curated a benchmark spanning various NLP tasks and annotated 11k claim-triplets from 2.1k responses by seven LLMs. RefChecker supports both proprietary and open-source models as the extractor and checker. Experiments demonstrate that claim-triplets enable superior hallucination detection, compared to other granularities such as response, sentence and sub-sentence level claims. RefChecker outperforms prior methods by 6.8 to 26.1 points on our benchmark and the checking results of RefChecker are strongly aligned with human judgments. This work is open sourced at https://github.com/amazon-science/RefChecker

cs.CL↗

arXiv2024

GeoGalactica: A Scientific Large Language Model in Geoscience

Large language models (LLMs) have achieved huge success for their general knowledge and ability to solve a wide spectrum of tasks in natural language processing (NLP). Due to their impressive abilities, LLMs have shed light on potential inter-discipline applications to foster scientific discoveries of a specific domain by using artificial intelligence (AI for science, AI4S). In the meantime, utilizing NLP techniques in geoscience research and practice is wide and convoluted, contributing from knowledge extraction and document classification to question answering and knowledge discovery. In this work, we take the initial step to leverage LLM for science, through a rather straightforward approach. We try to specialize an LLM into geoscience, by further pre-training the model with a vast amount of texts in geoscience, as well as supervised fine-tuning (SFT) the resulting model with our custom collected instruction tuning dataset. These efforts result in a model GeoGalactica consisting of 30 billion parameters. To our best knowledge, it is the largest language model for the geoscience domain. More specifically, GeoGalactica is from further pre-training of Galactica. We train GeoGalactica over a geoscience-related text corpus containing 65 billion tokens, preserving as the largest geoscience-specific text corpus. Then we fine-tune the model with 1 million pairs of instruction-tuning data consisting of questions that demand professional geoscience knowledge to answer. In this technical report, we will illustrate in detail all aspects of GeoGalactica, including data collection, data cleaning, base model selection, pre-training, SFT, and evaluation. We open-source our data curation tools and the checkpoints of GeoGalactica during the first 3/4 of pre-training.

cs.CL↗

arXiv2023

Survey on Factuality in Large Language Models: Knowledge, Retrieval and Domain-Specificity

This survey addresses the crucial issue of factuality in Large Language Models (LLMs). As LLMs find applications across diverse domains, the reliability and accuracy of their outputs become vital. We define the Factuality Issue as the probability of LLMs to produce content inconsistent with established facts. We first delve into the implications of these inaccuracies, highlighting the potential consequences and challenges posed by factual errors in LLM outputs. Subsequently, we analyze the mechanisms through which LLMs store and process facts, seeking the primary causes of factual errors. Our discussion then transitions to methodologies for evaluating LLM factuality, emphasizing key metrics, benchmarks, and studies. We further explore strategies for enhancing LLM factuality, including approaches tailored for specific domains. We focus two primary LLM configurations standalone LLMs and Retrieval-Augmented LLMs that utilizes external data, we detail their unique challenges and potential enhancements. Our survey offers a structured guide for researchers aiming to fortify the factual reliability of LLMs.

cs.CL↗

arXiv2023

Enhancing Uncertainty-Based Hallucination Detection with Stronger Focus

Large Language Models (LLMs) have gained significant popularity for their impressive performance across diverse fields. However, LLMs are prone to hallucinate untruthful or nonsensical outputs that fail to meet user expectations in many real-world applications. Existing works for detecting hallucinations in LLMs either rely on external knowledge for reference retrieval or require sampling multiple responses from the LLM for consistency verification, making these methods costly and inefficient. In this paper, we propose a novel reference-free, uncertainty-based method for detecting hallucinations in LLMs. Our approach imitates human focus in factuality checking from three aspects: 1) focus on the most informative and important keywords in the given text; 2) focus on the unreliable tokens in historical context which may lead to a cascade of hallucinations; and 3) focus on the token properties such as token type and token frequency. Experimental results on relevant datasets demonstrate the effectiveness of our proposed method, which achieves state-of-the-art performance across all the evaluation metrics and eliminates the need for additional information.

cs.CL↗

arXiv2023

K2: A Foundation Language Model for Geoscience Knowledge Understanding and Utilization

Large language models (LLMs) have achieved great success in general domains of natural language processing. In this paper, we bring LLMs to the realm of geoscience with the objective of advancing research and applications in this field. To this end, we present the first-ever LLM in geoscience, K2, alongside a suite of resources developed to further promote LLM research within geoscience. For instance, we have curated the first geoscience instruction tuning dataset, GeoSignal, which aims to align LLM responses to geoscience-related user queries. Additionally, we have established the first geoscience benchmark, GeoBench, to evaluate LLMs in the context of geoscience. In this work, we experiment with a complete recipe to adapt a pre-trained general-domain LLM to the geoscience domain. Specifically, we further train the LLaMA-7B model on 5.5B tokens of geoscience text corpus, including over 1 million pieces of geoscience literature, and utilize GeoSignal's supervised data to fine-tune the model. Moreover, we share a protocol that can efficiently gather domain-specific data and construct domain-supervised data, even in situations where manpower is scarce. Meanwhile, we equip K2 with the abilities of using tools to be a naive geoscience aide. Experiments conducted on the GeoBench demonstrate the effectiveness of our approach and datasets on geoscience knowledge understanding and utilization.We open-source all the training data and K2 model checkpoints at https://github.com/davendw49/k2.

cs.CL↗

arXiv2020

On the Modified Einstein-Laub and Modified Chu Optical Force Formulations

In several experiments involving material background, it has been observed that the Chu, Einstein-Laub and Ampere formulations of optical force lead to either different optical forces or wrong total optical force. In order to identify the exact reason behind such significant disagreements, we investigate the optical force in a number of tractor beam and lateral force experiments. We demonstrate that the modified Einstein-Laub or modified Chu formulations, obtained from two mathematical consistency conditions of force calculation, give the time-averaged force that agrees with the experiments. We consider both the chiral and achiral objects embedded in complex material backgrounds. Though the distinct formulations of optical force have been made mathematically equivalent in this work; the aspect of physical consistency of these distinct optical force formulations have also been investigated. It is known that the theory of Minkowski suggests zero bulk force inside a lossless object for which we still do not have any experimental verification. In contrast, both modified Einstein-Laub and modified Chu force formulations suggest non-zero bulk force inside a lossless object. Hence, for a future resolution of this discrepancy, we also suggest a possible experiment to investigate the bulk force and to check the validity of these distinct formulations.

physics.optics↗

arXiv2018

Chiral standing waves and its trapping force on chiral particles

Up to now, in the literature of optical manipulation, optical force due to chirality usually coexists with the non-chiral force and the chiral force usually takes a very small portion of the total force. In this work, we investigate a case where the optical force exerted on an object is purely due to the chirality while there is zero force on non-chiral object. We find that a trapping force arises on chiral particles when it is placed in a field consisted of two orthogonally polarized counter-propagating plane waves. We have revealed the underlying physics of this force by modeling the particle as a chiral diploe and analytically study the optical force. We find besides chirality; the trapping force is also closely related to the dual electric-magnetic symmetry of field and dual asymmetry of material. We also demonstrate that the proposed idea is not restricted to dipolar chiral objects only. Chiral Mie objects can also be trapped based on the technique proposed in this article. Notably, such chiral trapping forces have been found robust by varying several parameters throughout the investigation. This trapping force may find applications in identifying object's chirality and the selective trapping of chiral objects.

physics.optics↗

arXiv2017

Spherical Plasmonic Heterodimers: Reversal of Optical Binding Force as the Effect of Symmetry Breaking

The stimulating connection between the reversal of near field plasmonic binding force and the role of symmetry breaking has not been investigated in detail in literature. As both bonding and anti-bonding modes are present in the visible spectra of well-known spherical plasmonic heterodimer sets, binding force reversal is commonly believed to occur for all such heterodimers. But our work suggests a very different proposal. We demonstrate that for the symmetry broken heterodimer configurations: reversal of lateral (for on-axis heterodimers) and longitudinal (for off-axis heterodimers: end-fire and nearly end-fire configurations) near field binding force follow fully distinct mechanisms; i.e. later one on relative orientation and constructive dipole-quadrupole resonance but the former one on light polarization and the induced electric resonance. Interestingly, the reversal of longitudinal near field binding force can be easily controlled just by changing the direction of light propagation or just their relative orientation. Though it is commonly believed that plasmonic forces mostly arise from the surface force and Fano resonance can be a promising way to achieve binding force reversal; our study based on Lorentz force dynamics suggests notably opposite proposals (for both instances) for the case of plasmonic spherical heterodimers. Observations of this article can be very useful for improved sensors, particle clustering and aggregation.

physics.optics↗

arXiv2017

Consistency of time averaged optical force laws for embedded chiral and achiral objects

Although it is commonly believed that all the volumetric optical force laws should lead to the same total optical force for chiral and achiral objects, this idea has been invalidated in some recent works by investigating several previous experiments involving material background. To identify the exact reason of such significant disagreement, we inspect two tractor beam and one lateral force experiments on using distinct stress tensors (STs). To solve the problems of total force, we propose two consistency conditions of time averaged forces. We demonstrate that exactly at the boundary of an object, the difference of the consistent external Minkowski ST and internal ST of Chu (and Einstein-Laub) is found in agreement with the surface force yielded by Chu (and Einstein-Laub) force only when the background is air rather than a material. We identify this as one of the main reasons (among few other identified reasons) of the disagreements observed for real experiments. Finally, based on the proposed consistency conditions, we demonstrate that: by modifying the Einstein-Laub or Chu formulation, time-averaged STs and volume forces are obtainable those can overcome the aforementioned inconsistencies of real experiments for both chiral and achiral Mie objects embedded in even complex material backgrounds.

physics.optics↗

arXiv2017

Substrate Effect on Plasmonic Cube Dimers: Reversal of Optical Binding Force Induced by Strong Fano Resonance

The behavior of Fano resonance and the reversal of near field optical binding force of dimers over different substrates have not been studied so far. In this work, we observe that if the closely located plasmonic cube homodimers over glass or high permittivity dielectric substrate are illuminated with plane wave polarized parallel to dimer axis, no reversal of optical binding force occurs. But if we apply the same set-up over a plasmonic substrate, stable Fano resonance occurs along with the reversal of near field binding force. It is observed that during such Fano resonance stronger coupling occurs between the dimers and plasmonic substrate along with the strong enhancement of the substrate current. Such near field binding force reversals of plasmonic cube dimers have been explained based on the observed unusual behavior of optical Lorentz force during the induced stronger Fano resonance and the dipole-dipole resonance. Although previously reported reversals of near field optical binding forces were highly sensitive to particle size/shape (i.e. for heterodimers) and inter-particle distance, our configuration provides much relaxation of those parameters and hence should be verified experimentally with simpler experimental set-ups.

physics.optics↗