arXiv subjects

Zheng Yuan

Publications and source records attributed to Zheng Yuan.

At least 55 records · Page 3Linked to original sources

arXiv2025

GenQuest: An LLM-based Text Adventure Game for Language Learners

GenQuest is a generative text adventure game that leverages Large Language Models (LLMs) to facilitate second language learning through immersive, interactive storytelling. The system engages English as a Foreign Language (EFL) learners in a collaborative "choose-your-own-adventure" style narrative, dynamically generated in response to learner choices. Game mechanics such as branching decision points and story milestones are incorporated to maintain narrative coherence while allowing learner-driven plot development. Key pedagogical features include content generation tailored to each learner's proficiency level, and a vocabulary assistant that provides in-context explanations of learner-queried text strings, ranging from words and phrases to sentences. Findings from a pilot study with university EFL students in China indicate promising vocabulary gains and positive user perceptions. Also discussed are suggestions from participants regarding the narrative length and quality, and the request for multi-modal content such as illustrations.

cs.CL↗

arXiv2025

Neuro-Symbolic Entity Alignment via Variational Inference

Entity alignment (EA) aims to merge two knowledge graphs (KGs) by identifying equivalent entity pairs. Existing methods can be categorized into symbolic and neural models. Symbolic models, while precise, struggle with substructure heterogeneity and sparsity, whereas neural models, although effective, generally lack interpretability and cannot handle uncertainty. We propose NeuSymEA, a unified neuro-symbolic reasoning framework that combines the strengths of both methods to fully exploit the cross-KG structural pattern for robust entity alignment. NeuSymEA models the joint probability of all possible pairs' truth scores in a Markov random field, regulated by a set of rules, and optimizes it with the variational EM algorithm. In the E-step, a neural model parameterizes the truth score distributions and infers missing alignments. In the M-step, the rule weights are updated based on the observed and inferred alignments, handling uncertainty. We introduce an efficient symbolic inference engine driven by logic deduction, enabling reasoning with extended rule lengths. NeuSymEA achieves a significant 7.6\% hit@1 improvement on $\text{DBP15K}_{\text{ZH-EN}}$ compared with strong baselines and demonstrates robustness in low-resource settings, achieving 73.7\% hit@1 accuracy on $\text{DBP15K}_{\text{FR-EN}}$ with only 1\% pairs as seed alignments. Codes are released at https://github.com/chensyCN/NeuSymEA-NeurIPS25.

cs.AI↗

arXiv2025

A Survey of Graph Retrieval-Augmented Generation for Customized Large Language Models

Large language models (LLMs) have demonstrated remarkable capabilities in a wide range of tasks, yet their application to specialized domains remains challenging due to the need for deep expertise. Retrieval-Augmented generation (RAG) has emerged as a promising solution to customize LLMs for professional fields by seamlessly integrating external knowledge bases, enabling real-time access to domain-specific expertise during inference. Despite its potential, traditional RAG systems, based on flat text retrieval, face three critical challenges: (i) complex query understanding in professional contexts, (ii) difficulties in knowledge integration across distributed sources, and (iii) system efficiency bottlenecks at scale. This survey presents a systematic analysis of Graph-based Retrieval-Augmented Generation (GraphRAG), a new paradigm that revolutionizes domain-specific LLM applications. GraphRAG addresses traditional RAG limitations through three key innovations: (i) graph-structured knowledge representation that explicitly captures entity relationships and domain hierarchies, (ii) efficient graph-based retrieval techniques that enable context-preserving knowledge retrieval with multihop reasoning ability, and (iii) structure-aware knowledge integration algorithms that leverage retrieved knowledge for accurate and logical coherent generation of LLMs. In this survey, we systematically analyze the technical foundations of GraphRAG and examine current implementations across various professional domains, identifying key technical challenges and promising research directions. All the related resources of GraphRAG, including research papers, open-source data, and projects, are collected for the community in https://github.com/DEEP-PolyU/Awesome-GraphRAG.

cs.CL↗

arXiv2025

Beyond the Score: Uncertainty-Calibrated LLMs for Automated Essay Assessment

Automated Essay Scoring (AES) systems now reach near human agreement on some public benchmarks, yet real-world adoption, especially in high-stakes examinations, remains limited. A principal obstacle is that most models output a single score without any accompanying measure of confidence or explanation. We address this gap with conformal prediction, a distribution-free wrapper that equips any classifier with set-valued outputs and formal coverage guarantees. Two open-source large language models (Llama-3 8B and Qwen-2.5 3B) are fine-tuned on three diverse corpora (ASAP, TOEFL11, Cambridge-FCE) and calibrated at a 90 percent risk level. Reliability is assessed with UAcc, an uncertainty-aware accuracy that rewards models for being both correct and concise. To our knowledge, this is the first work to combine conformal prediction and UAcc for essay scoring. The calibrated models consistently meet the coverage target while keeping prediction sets compact, indicating that open-source, mid-sized LLMs can already support teacher-in-the-loop AES; we discuss scaling and broader user studies as future work.

cs.CL↗

arXiv2025

Seed-Prover: Deep and Broad Reasoning for Automated Theorem Proving

LLMs have demonstrated strong mathematical reasoning abilities by leveraging reinforcement learning with long chain-of-thought, yet they continue to struggle with theorem proving due to the lack of clear supervision signals when solely using natural language. Dedicated domain-specific languages like Lean provide clear supervision via formal verification of proofs, enabling effective training through reinforcement learning. In this work, we propose \textbf{Seed-Prover}, a lemma-style whole-proof reasoning model. Seed-Prover can iteratively refine its proof based on Lean feedback, proved lemmas, and self-summarization. To solve IMO-level contest problems, we design three test-time inference strategies that enable both deep and broad reasoning. Seed-Prover proves $78.1\%$ of formalized past IMO problems, saturates MiniF2F, and achieves over 50\% on PutnamBench, outperforming the previous state-of-the-art by a large margin. To address the lack of geometry support in Lean, we introduce a geometry reasoning engine \textbf{Seed-Geometry}, which outperforms previous formal geometry engines. We use these two systems to participate in IMO 2025 and fully prove 5 out of 6 problems. This work represents a significant advancement in automated mathematical reasoning, demonstrating the effectiveness of formal verification with long chain-of-thought reasoning.

cs.AI↗

arXiv2025

Hydrodynamic Insight Drives Multimodal Light_Field Dynamics via Streamline Engineering

Since the 1970s, analogies between laser dynamics and fluid systems have provided insight into phenomena such as chaos, multistability, and turbulence. Building on this perspective, we model the optical field as an energy fluid and interpret Poynting-vector trajectories as energy streamlines, yielding a unified, three_dimensional map of light's free-space dynamics. By sculpting these streamlines, we develop an approach to talior vortex-beam propagation dynamics that suppresses both diffraction- and OAM-induced broadening. Extending this method to general structured modes, we enable a single field to exhibit customizable multimodal dynamics that integrate features from primary structured light families: the diffraction-free, self-healing behavior of Bessel beams; the tunable self-similarity of Laguerre-Gaussian beams and adjustable self-acceleration of Airy beams. Additionally, it allows for adjustable propagating energy-density profiles to counteract losses. Optical-tweezer experiments,analogous to particle-tracking velocimetry in fluid dynamics, show that trapped microspheres closely follow the designed streamlines, validating the streamline geometries and indicating a potential route toward precision 3D optomechanical control. In a proof-of-principle free-space communication experiment, vortex beams with customized multimodal dynamics demonstrate several improvements, including more independent channels, reduced turbulence-induced mode scattering, and robust non-line-of-sight transmission. Together, the streamline-engineering approach offers a unified and adaptable strategy for tailoring light's propagation dynamics, with potential applications in precision optomechanics, optofluidics, and advanced optical networking.

physics.optics↗

arXiv2025

Vortex-Free Intrinsic Orbital Angular Momentum

Optical orbital angular momentum (OAM) has traditionally relied on vortex beams with helical phase fronts imparting quantized intrinsic OAM. Here, we introduce a fundamentally vortex_free framework where intrinsic OAM arises from the natural curvature of lights energy flow, specifically, the caustic geometry of self_accelerating beams whose curved trajectories act as orbital highways for photons. This OAM generation mechanism is independent of phase vortices but mirrors celestial orbital motion. Through numerical simulations, experimental characterization, and optomechanical measurements using optical tweezers, we demonstrate intrinsic vortex_free OAM rooted solely in beam intensity architecture. Generalizing beyond geometric caustics to arbitrary optical fields, we demonstrate OAM via curved Poynting_vector energy streamlines, unifying conventional vortex and novel vortex_free OAM under a single quantitative framework. Streamline engineering enables customizable rotational dynamics, including hybrid orbital_cyclonic motions reminiscent of tropical storms, with promising applications in precision optomechanics, optofluidics, and optical analogues of fluid dynamics. This energy-flow perspective offers a versatile platform for designing and quantifying OAM across structured light.

physics.optics↗

arXiv2025

Confidence Intervals for Evaluation of Data Mining

In data mining, when binary prediction rules are used to predict a binary outcome, many performance measures are used in a vast array of literature for the purposes of evaluation and comparison. Some examples include classification accuracy, precision, recall, F measures, and Jaccard index. Typically, these performance measures are only approximately estimated from a finite dataset, which may lead to findings that are not statistically significant. In order to properly quantify such statistical uncertainty, it is important to provide confidence intervals associated with these estimated performance measures. We consider statistical inference about general performance measures used in data mining, with both individual and joint confidence intervals. These confidence intervals are based on asymptotic normal approximations and can be computed fast, without needs to do bootstrap resampling. We study the finite sample coverage probabilities for these confidence intervals and also propose a `blurring correction' on the variance to improve the finite sample performance. This 'blurring correction' generalizes the plus-four method from binomial proportion to general performance measures used in data mining. Our framework allows multiple performance measures of multiple classification rules to be inferred simultaneously for comparisons.

stat.ML↗

arXiv2025

FullLoRA: Efficiently Boosting the Robustness of Pretrained Vision Transformers

In recent years, the Vision Transformer (ViT) model has gradually become mainstream in various computer vision tasks, and the robustness of the model has received increasing attention. However, existing large models tend to prioritize performance during training, potentially neglecting the robustness, which may lead to serious security concerns. In this paper, we establish a new challenge: exploring how to use a small number of additional parameters for adversarial finetuning to quickly and effectively enhance the adversarial robustness of a standardly trained model. To address this challenge, we develop novel LNLoRA module, incorporating a learnable layer normalization before the conventional LoRA module, which helps mitigate magnitude differences in parameters between the adversarial and standard training paradigms. Furthermore, we propose the FullLoRA framework by integrating the learnable LNLoRA modules into all key components of ViT-based models while keeping the pretrained model frozen, which can significantly improve the model robustness via adversarial finetuning in a parameter-efficient manner. Extensive experiments on several datasets demonstrate the superiority of our proposed FullLoRA framework. It achieves comparable robustness with full finetuning while only requiring about 5\% of the learnable parameters. This also effectively addresses concerns regarding extra model storage space and enormous training time caused by adversarial finetuning.

cs.CV↗

arXiv2025

Lean Workbook: A large-scale Lean problem set formalized from natural language math problems

Large language models have demonstrated impressive capabilities across various natural language processing tasks, especially in solving mathematical problems. However, large language models are not good at math theorem proving using formal languages like Lean. A significant challenge in this area is the scarcity of training data available in these formal languages. To address this issue, we propose a novel pipeline that iteratively generates and filters synthetic data to translate natural language mathematical problems into Lean 4 statements, and vice versa. Our results indicate that the synthetic data pipeline can provide useful training data and improve the performance of LLMs in translating and understanding complex mathematical problems and proofs. Our final dataset contains about 57K formal-informal question pairs along with searched proof from the math contest forum and 21 new IMO questions. We open-source our code at https://github.com/InternLM/InternLM-Math and our data at https://huggingface.co/datasets/InternLM/Lean-Workbook.

cs.CL↗

arXiv2025

Rubrik's Cube: Testing a New Rubric for Evaluating Explanations on the CUBE dataset

The performance and usability of Large-Language Models (LLMs) are driving their use in explanation generation tasks. However, despite their widespread adoption, LLM explanations have been found to be unreliable, making it difficult for users to distinguish good from bad explanations. To address this issue, we present Rubrik's CUBE, an education-inspired rubric and a dataset of 26k explanations, written and later quality-annotated using the rubric by both humans and six open- and closed-source LLMs. The CUBE dataset focuses on two reasoning and two language tasks, providing the necessary diversity for us to effectively test our proposed rubric. Using Rubrik, we find that explanations are influenced by both task and perceived difficulty. Low quality stems primarily from a lack of conciseness in LLM-generated explanations, rather than cohesion and word choice. The full dataset, rubric, and code are available at https://github.com/RubriksCube/rubriks_cube.

cs.CL↗

arXiv2025

A remark on a generalized Suita conjecture for finite points case

In this article, we use a class of harmonic functions (maybe multi-valued) to study the equality part in a weighted version of Suita conjecture for higher derivatives and finite points case, and we obtain some sufficient and necessary conditions for the equality part to hold when the harmonic part $u$ of the weight is trivial.

math.CV↗

arXiv2025

FormalMATH: Benchmarking Formal Mathematical Reasoning of Large Language Models

Formal mathematical reasoning remains a critical challenge for artificial intelligence, hindered by limitations of existing benchmarks in scope and scale. To address this, we present FormalMATH, a large-scale Lean4 benchmark comprising 5,560 formally verified problems spanning from high-school Olympiad challenges to undergraduate-level theorems across diverse domains (e.g., algebra, applied mathematics, calculus, number theory, and discrete mathematics). To mitigate the inefficiency of manual formalization, we introduce a novel human-in-the-loop autoformalization pipeline that integrates: (1) specialized large language models (LLMs) for statement autoformalization, (2) multi-LLM semantic verification, and (3) negation-based disproof filtering strategies using off-the-shelf LLM-based provers. This approach reduces expert annotation costs by retaining 72.09% of statements before manual verification while ensuring fidelity to the original natural-language problems. Our evaluation of state-of-the-art LLM-based theorem provers reveals significant limitations: even the strongest models achieve only 16.46% success rate under practical sampling budgets, exhibiting pronounced domain bias (e.g., excelling in algebra but failing in calculus) and over-reliance on simplified automation tactics. Notably, we identify a counterintuitive inverse relationship between natural-language solution guidance and proof success in chain-of-thought reasoning scenarios, suggesting that human-written informal reasoning introduces noise rather than clarity in the formal reasoning settings. We believe that FormalMATH provides a robust benchmark for benchmarking formal mathematical reasoning.

cs.AI↗

arXiv2025

Concavity property of minimal $L^2$ integrals with Lebesgue measurable gain III: open Riemann surfaces

In this article, we present a characterization of the concavity property of minimal $L^2$ integrals degenerating to linearity in the case of finite points on open Riemann surfaces. As an application, we give a characterization of the holding of equality in optimal jets $L^2$ extension problem from analytic subsets to open Riemann surfaces, which is a weighted jets version of Suita conjecture for analytic subsets.

math.CV↗

arXiv2025

Prompting open-source and commercial language models for grammatical error correction of English learner text

Thanks to recent advances in generative AI, we are able to prompt large language models (LLMs) to produce texts which are fluent and grammatical. In addition, it has been shown that we can elicit attempts at grammatical error correction (GEC) from LLMs when prompted with ungrammatical input sentences. We evaluate how well LLMs can perform at GEC by measuring their performance on established benchmark datasets. We go beyond previous studies, which only examined GPT* models on a selection of English GEC datasets, by evaluating seven open-source and three commercial LLMs on four established GEC benchmarks. We investigate model performance and report results against individual error types. Our results indicate that LLMs do not always outperform supervised English GEC models except in specific contexts -- namely commercial LLMs on benchmarks annotated with fluency corrections as opposed to minimal edits. We find that several open-source models outperform commercial ones on minimal edit benchmarks, and that in some settings zero-shot prompting is just as competitive as few-shot prompting.

cs.CL↗

arXiv2025

REVAL: A Comprehension Evaluation on Reliability and Values of Large Vision-Language Models

The rapid evolution of Large Vision-Language Models (LVLMs) has highlighted the necessity for comprehensive evaluation frameworks that assess these models across diverse dimensions. While existing benchmarks focus on specific aspects such as perceptual abilities, cognitive capabilities, and safety against adversarial attacks, they often lack the breadth and depth required to provide a holistic understanding of LVLMs' strengths and limitations. To address this gap, we introduce REVAL, a comprehensive benchmark designed to evaluate the \textbf{RE}liability and \textbf{VAL}ue of LVLMs. REVAL encompasses over 144K image-text Visual Question Answering (VQA) samples, structured into two primary sections: Reliability, which assesses truthfulness (\eg, perceptual accuracy and hallucination tendencies) and robustness (\eg, resilience to adversarial attacks, typographic attacks, and image corruption), and Values, which evaluates ethical concerns (\eg, bias and moral understanding), safety issues (\eg, toxicity and jailbreak vulnerabilities), and privacy problems (\eg, privacy awareness and privacy leakage). We evaluate 26 models, including mainstream open-source LVLMs and prominent closed-source models like GPT-4o and Gemini-1.5-Pro. Our findings reveal that while current LVLMs excel in perceptual tasks and toxicity avoidance, they exhibit significant vulnerabilities in adversarial scenarios, privacy preservation, and ethical reasoning. These insights underscore critical areas for future improvements, guiding the development of more secure, reliable, and ethically aligned LVLMs. REVAL provides a robust framework for researchers to systematically assess and compare LVLMs, fostering advancements in the field.

cs.CV↗

arXiv2025

Evaluating LLMs' Assessment of Mixed-Context Hallucination Through the Lens of Summarization

With the rapid development of large language models (LLMs), LLM-as-a-judge has emerged as a widely adopted approach for text quality evaluation, including hallucination evaluation. While previous studies have focused exclusively on single-context evaluation (e.g., discourse faithfulness or world factuality), real-world hallucinations typically involve mixed contexts, which remains inadequately evaluated. In this study, we use summarization as a representative task to comprehensively evaluate LLMs' capability in detecting mixed-context hallucinations, specifically distinguishing between factual and non-factual hallucinations. Through extensive experiments across direct generation and retrieval-based models of varying scales, our main observations are: (1) LLMs' intrinsic knowledge introduces inherent biases in hallucination evaluation; (2) These biases particularly impact the detection of factual hallucinations, yielding a significant performance bottleneck; (3) The fundamental challenge lies in effective knowledge utilization, balancing between LLMs' intrinsic knowledge and external context for accurate mixed-context hallucination evaluation.

cs.CL↗

arXiv2025

Dysca: A Dynamic and Scalable Benchmark for Evaluating Perception Ability of LVLMs

Currently many benchmarks have been proposed to evaluate the perception ability of the Large Vision-Language Models (LVLMs). However, most benchmarks conduct questions by selecting images from existing datasets, resulting in the potential data leakage. Besides, these benchmarks merely focus on evaluating LVLMs on the realistic style images and clean scenarios, leaving the multi-stylized images and noisy scenarios unexplored. In response to these challenges, we propose a dynamic and scalable benchmark named Dysca for evaluating LVLMs by leveraging synthesis images. Specifically, we leverage Stable Diffusion and design a rule-based method to dynamically generate novel images, questions and the corresponding answers. We consider 51 kinds of image styles and evaluate the perception capability in 20 subtasks. Moreover, we conduct evaluations under 4 scenarios (i.e., Clean, Corruption, Print Attacking and Adversarial Attacking) and 3 question types (i.e., Multi-choices, True-or-false and Free-form). Thanks to the generative paradigm, Dysca serves as a scalable benchmark for easily adding new subtasks and scenarios. A total of 24 advanced open-source LVLMs and 2 close-source LVLMs are evaluated on Dysca, revealing the drawbacks of current LVLMs. The benchmark is released at https://github.com/Robin-WZQ/Dysca.

cs.CV↗