Searcharxiv⌕ Search

arXiv subjects

Kaiqi Yang

Publications and source records attributed to Kaiqi Yang.

At least 19 recordsLinked to original sources
arXiv2026

RouteGuard: Certifying Routing Gain in LLM Multi-Agent Systems When Complementarity Is Not Enough

Multi-agent LLM systems route among model-backed advisors, yet a deployer rarely knows before shipping whether routing will help at all. Prevailing routers optimize a gate's AUC and presume that advisor complementarity suffices. We show that neither determines the deployable gain. We introduce RouteGuard, a deployment-certification framework. Routing gain decomposes as $G = \pi \Delta_E$, and the achievable gain is governed by a conditional-regret functional $\Phi$, not by AUC. A finite-sample certification bracket comes with a matching Le Cam lower bound, constant-sharp over the fixed-activity class, and a robustness phase transition. On two benchmarks the framework acts as a guardrail. On RouterBench (11 cross-family models) the verdict depends on the sampling unit: the protocol certifies a gain over GPT-4 under prompt-level sampling and withholds it under workload-cluster resampling, because the gain rests on 3 of 86 workload cells. On OpenRCA (three Gemini advisors) the advisors are statistically redundant: the realized oracle sits at or below the independence baseline in all pools we tested (221 RouterBench pools and three OpenRCA distributions), so the protocol correctly refuses to certify. A pre-registered semi-synthetic control confirms calibration: the protocol certifies a genuine gain once $m \ge m^\star$ and does not certify a true null. Code and frozen artifacts will be released with the published version.

stat.ML↗
arXiv2026

"**Important** You should give me full credits!": Exploring Prompt Injection Attacks on LLM-Based Automatic Grading Systems

The emergence of large language models (LLMs) has significantly accelerated recent research on LLM-based automatic grading (AG) systems. Benefiting from the strong instruction-following capabilities and broad prior knowledge of LLMs, educators can deploy AG systems across diverse tasks using only natural language rubrics while achieving satisfactory grading performance. Despite these advantages, new security concerns may also arise. In particular, prompt injection (PI) attacks have recently become a major threat to LLM-based applications. In the context of AG, attackers can potentially exploit PI vulnerabilities to manipulate grading systems into assigning artificially high scores regardless of the actual answer quality. Such behavior poses serious risks to the fairness, reliability, and integrity of educational assessment. In this work, we study PI attacks in AG systems, and systematically investigate the effectiveness of such attacks in educational scenarios. We further evaluate the effectiveness of existing defensive strategies against these attacks. Through comprehensive experiments under rubric-based grading settings, we demonstrate that current LLM-based AG systems remain highly vulnerable to PI attacks. We hope that our findings raise awareness of this emerging threat and motivate future research toward secure, robust, and trustworthy LLM-based educational systems.

cs.CR↗
arXiv2026

Think-Before-Speak: From Internal Evaluation to Public Expression in Multi-Agent Social Simulation

LLM-based multi-agent simulation offers a promising way to study social interaction, deliberation, and collective opinion dynamics. However, many existing dialogue simulation frameworks represent interaction mainly as observable turn exchange or aggregated outputs, leaving the internal evaluative processes behind silence, speaking intention, and public expression difficult to examine. We introduce TBS (Think-Before-Speak), an interval-based multi-agent simulation framework that separates agents' private reasoning from public utterance generation. At each interval, all agents update structured internal states based on the shared dialogue history and their own memory. These states include dissonance-related appraisal, perceived opinion climate, perceived isolation risk, response strategy, and willingness to speak. The orchestrator then resolves competing speaking intentions and commits one utterance to the public dialogue, allowing internal evaluation and public interaction to co-evolve over time. We evaluate TBS in simulated town hall discussions on a climate-related policy issue. Results show that TBS produces coherent internal-state traces and that these traces vary systematically across turn-allocation, silence, and memory conditions. Dissonance-related appraisal increases agents' willingness to speak, whereas silence-pressure appraisal decreases it. Once speaking intention is formed, public expression is shaped mainly by turn-allocation rules. These findings suggest that TBS supports mechanism-sensitive social simulation by making the pathway from internal evaluation to public expression observable and analyzable.

cs.AI↗
arXiv2026

Confusion-Aware Rubric Optimization for LLM-based Automated Grading

Accurate and unambiguous guidelines are critical for large language model (LLM) based graders, yet manually crafting these prompts is often sub-optimal as LLMs can misinterpret expert guidelines or lack necessary domain specificity. Consequently, the field has moved toward automated prompt optimization to refine grading guidelines without the burden of manual trial and error. However, existing frameworks typically aggregate independent and unstructured error samples into a single update step, resulting in "rule dilution" where conflicting constraints weaken the model's grading logic. To address these limitations, we introduce Confusion-Aware Rubric Optimization (CARO), a novel framework that enhances accuracy and computational efficiency by structurally separating error signals. CARO leverages the confusion matrix to decompose monolithic error signals into distinct modes, allowing for the diagnosis and repair of specific misclassification patterns individually. By synthesizing targeted "fixing patches" for dominant error modes and employing a diversity-aware selection mechanism, the framework prevents guidance conflict and eliminates the need for resource-heavy nested refinement loops. Empirical evaluations on teacher education and STEM datasets demonstrate that CARO significantly outperforms existing SOTA methods. These results suggest that replacing mixed-error aggregation with surgical, mode-specific repair yields robust improvements in automated assessment scalability and precision.

cs.AI↗
arXiv2026

Optimizing In-Context Demonstrations for LLM-based Automated Grading

Automated assessment of open-ended student responses is a critical capability for scaling personalized feedback in education. While large language models (LLMs) have shown promise in grading tasks via in-context learning (ICL), their reliability is heavily dependent on the selection of few-shot exemplars and the construction of high-quality rationales. Standard retrieval methods typically select examples based on semantic similarity, which often fails to capture subtle decision boundaries required for rubric adherence. Furthermore, manually crafting the expert rationales needed to guide these models can be a significant bottleneck. To address these limitations, we introduce GUIDE (Grading Using Iteratively Designed Exemplars), a framework that reframes exemplar selection and refinement in automated grading as a boundary-focused optimization problem. GUIDE operates on a continuous loop of selection and refinement, employing novel contrastive operators to identify "boundary pairs" that are semantically similar but possess different grades. We enhance exemplars by generating discriminative rationales that explicitly articulate why a response receives a specific score to the exclusion of adjacent grades. Extensive experiments across datasets in physics, chemistry, and pedagogical content knowledge demonstrate that GUIDE significantly outperforms standard retrieval baselines. By focusing the model's attention on the precise edges of rubric, our approach shows exceptionally robust gains on borderline cases and improved rubric adherence. GUIDE paves the way for trusted, scalable assessment systems that align closely with human pedagogical standards.

cs.AI↗
arXiv2026

From Flat to Structural: Enhancing Automated Short Answer Grading with GraphRAG

Automated short answer grading (ASAG) is critical for scaling educational assessment, yet large language models (LLMs) often struggle with hallucinations and strict rubric adherence due to their reliance on generalized pre-training. While Rretrieval-Augmented Generation (RAG) mitigates these issues, standard "flat" vector retrieval mechanisms treat knowledge as isolated fragments, failing to capture the structural relationships and multi-hop reasoning essential for complex educational content. To address this limitation, we introduce a Graph Retrieval-Augmented Generation (GraphRAG) framework that organizes reference materials into a structured knowledge graph to explicitly model dependencies between concepts. Our methodology employs a dual-phase pipeline: utilizing Microsoft GraphRAG for high-fidelity graph construction and the HippoRAG neurosymbolic algorithm to execute associative graph traversals, thereby retrieving comprehensive, connected subgraphs of evidence. Experimental evaluations on a Next Generation Science Standards (NGSS) dataset demonstrate that this structural approach significantly outperforms standard RAG baselines across all metrics. Notably, the HippoRAG implementation achieved substantial improvements in evaluating Science and Engineering Practices (SEP), confirming the superiority of structural retrieval in verifying the logical reasoning chains required for higher-order academic assessment.

cs.CL↗
arXiv2026

How Uncertain Is the Grade? A Benchmark of Uncertainty Metrics for LLM-Based Automatic Assessment

The rapid rise of large language models (LLMs) is reshaping the landscape of automatic assessment in education. While these systems demonstrate substantial advantages in adaptability to diverse question types and flexibility in output formats, they also introduce new challenges related to output uncertainty, stemming from the inherently probabilistic nature of LLMs. Output uncertainty is an inescapable challenge in automatic assessment, as assessment results often play a critical role in informing subsequent pedagogical actions, such as providing feedback to students or guiding instructional decisions. Unreliable or poorly calibrated uncertainty estimates can lead to unstable downstream interventions, potentially disrupting students' learning processes and resulting in unintended negative consequences. To systematically understand this challenge and inform future research, we benchmark a broad range of uncertainty quantification methods in the context of LLM-based automatic assessment. Although the effectiveness of these methods has been demonstrated in many tasks across other domains, their applicability and reliability in educational settings, particularly for automatic grading, remain underexplored. Through comprehensive analyses of uncertainty behaviors across multiple assessment datasets, LLM families, and generation control settings, we characterize the uncertainty patterns exhibited by LLMs in grading scenarios. Based on these findings, we evaluate the strengths and limitations of different uncertainty metrics and analyze the influence of key factors, including model families, assessment tasks, and decoding strategies, on uncertainty estimates. Our study provides actionable insights into the characteristics of uncertainty in LLM-based automatic assessment and lays the groundwork for developing more reliable and effective uncertainty-aware grading systems in the future.

cs.AI↗
arXiv2025

Iterative LLM-Based Generation and Refinement of Distracting Conditions in Math Word Problems

Mathematical reasoning serves as a crucial testbed for the intelligence of large language models (LLMs), and math word problems (MWPs) are a popular type of math problems. Most MWP datasets consist of problems containing only the necessary information, while problems with distracting and excessive conditions are often overlooked. Prior works have tested popular LLMs and found a dramatic performance drop in the presence of distracting conditions. However, datasets of MWPs with distracting conditions are limited, and most suffer from lower levels of difficulty and out-of-context expressions. This makes distracting conditions easy to identify and exclude, thus reducing the credibility of benchmarking on them. Moreover, when adding distracting conditions, the reasoning and answers may also change, requiring intensive labor to check and write the solutions. To address these issues, we design an iterative framework to generate distracting conditions using LLMs. We develop a set of prompts to revise MWPs from different perspectives and cognitive levels, encouraging the generation of distracting conditions as well as suggestions for further revision. Another advantage is the shared solutions between original and revised problems: we explicitly guide the LLMs to generate distracting conditions that do not alter the original solutions, thus avoiding the need to generate new solutions. This framework is efficient and easy to deploy, reducing the overhead of generating MWPs with distracting conditions while maintaining data quality.

cs.CL↗
arXiv2025

Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving

Large language models (LLMs) have been widely used for problem-solving tasks. Most recent work improves their performance through supervised fine-tuning (SFT) with labeled data or reinforcement learning (RL) from task feedback. In this paper, we study a new perspective: the divergence in solutions generated by LLMs for a single problem. We show that higher solution divergence is positively related to better problem-solving abilities across various models. Based on this finding, we propose solution divergence as a novel metric that can support both SFT and RL strategies. We test this idea on three representative problem domains and find that using solution divergence consistently improves success rates. These results suggest that solution divergence is a simple but effective tool for advancing LLM training and evaluation.

cs.CL↗
arXiv2025

A LLM-Driven Multi-Agent Systems for Professional Development of Mathematics Teachers

Professional development (PD) serves as the cornerstone for teacher tutors to grasp content knowledge. However, providing equitable and timely PD opportunities for teachers poses significant challenges. To address this issue, we introduce I-VIP (Intelligent Virtual Interactive Program), an intelligent tutoring platform for teacher professional development, driven by large language models (LLMs) and supported by multi-agent frameworks. This platform offers a user-friendly conversational interface and allows users to employ a variety of interactive tools to facilitate question answering, knowledge comprehension, and reflective summarization while engaging in dialogue. To underpin the functionality of this platform, including knowledge expectation analysis, response scoring and classification, and feedback generation, the multi-agent frameworks are leveraged to enhance the accuracy of judgments and mitigate the issue of missing key points.

cs.CY↗
arXiv2025

DiffLiB: High-fidelity differentiable modeling of lithium-ion batteries and efficient gradient-based parameter identification

The physics-based Doyle-Fuller-Newman (DFN) model, widely adopted for its precise electrochemical modeling, stands out among various simulation models of lithium-ion batteries (LIBs). Although the DFN model is powerful in forward predictive analysis, the inverse identification of its model parameters has remained a long-standing challenge. The numerous unknown parameters associated with the nonlinear, time-dependent, and multi-scale DFN model are extremely difficult to be determined accurately and efficiently, hindering the practical use of such battery simulation models in industrial applications. To tackle this challenge, we introduce DiffLiB, a high-fidelity finite-element-based LIB simulation framework, equipped with advanced differentiable programming techniques so that efficient gradient-based inverse parameter identification is enabled. Customized automatic differentiation rules are defined by identifying the VJP (vector-Jacobian product) structure in the chain rule and implemented using adjoint-based implicit differentiation methods. Four numerical examples, including both 2D and 3D forward predictions and inverse parameter identification, are presented to validate the accuracy and computational efficiency of DiffLiB. Benchmarking against COMSOL demonstrates excellent agreement in forward predictions, with terminal voltage discrepancies maintaining a root-mean-square error (RMSE) below 2 mV across all test conditions. In parameter identification tasks using experimentally measured voltage data, the proposed gradient-based optimization scheme achieves superior computational performance, with 96% fewer forward predictions and 72% less computational time compared with gradient-free approaches. These results demonstrate that DiffLiB is a versatile and powerful computational framework for the development of advanced LIBs.

cs.CE↗
arXiv2025

LLM-based Automated Grading with Human-in-the-Loop

The rise of artificial intelligence (AI) technologies, particularly large language models (LLMs), has brought significant advancements to the field of education. Among various applications, automatic short answer grading (ASAG), which focuses on evaluating open-ended textual responses, has seen remarkable progress with the introduction of LLMs. These models not only enhance grading performance compared to traditional ASAG approaches but also move beyond simple comparisons with predefined "golden" answers, enabling more sophisticated grading scenarios, such as rubric-based evaluation. However, existing LLM-powered methods still face challenges in achieving human-level grading performance in rubric-based assessments due to their reliance on fully automated approaches. In this work, we explore the potential of LLMs in ASAG tasks by leveraging their interactive capabilities through a human-in-the-loop (HITL) approach. Our proposed framework, GradeHITL, utilizes the generative properties of LLMs to pose questions to human experts, incorporating their insights to refine grading rubrics dynamically. This adaptive process significantly improves grading accuracy, outperforming existing methods and bringing ASAG closer to human-level evaluation.

cs.CL↗
arXiv2025

Enhancing LLM-Based Short Answer Grading with Retrieval-Augmented Generation

Short answer assessment is a vital component of science education, allowing evaluation of students' complex three-dimensional understanding. Large language models (LLMs) that possess human-like ability in linguistic tasks are increasingly popular in assisting human graders to reduce their workload. However, LLMs' limitations in domain knowledge restrict their understanding in task-specific requirements and hinder their ability to achieve satisfactory performance. Retrieval-augmented generation (RAG) emerges as a promising solution by enabling LLMs to access relevant domain-specific knowledge during assessment. In this work, we propose an adaptive RAG framework for automated grading that dynamically retrieves and incorporates domain-specific knowledge based on the question and student answer context. Our approach combines semantic search and curated educational sources to retrieve valuable reference materials. Experimental results in a science education dataset demonstrate that our system achieves an improvement in grading accuracy compared to baseline LLM approaches. The findings suggest that RAG-enhanced grading systems can serve as reliable support with efficient performance gains.

cs.CL↗
arXiv2024

Ask-Before-Detection: Identifying and Mitigating Conformity Bias in LLM-Powered Error Detector for Math Word Problem Solutions

The rise of large language models (LLMs) offers new opportunities for automatic error detection in education, particularly for math word problems (MWPs). While prior studies demonstrate the promise of LLMs as error detectors, they overlook the presence of multiple valid solutions for a single MWP. Our preliminary analysis reveals a significant performance gap between conventional and alternative solutions in MWPs, a phenomenon we term conformity bias in this work. To mitigate this bias, we introduce the Ask-Before-Detect (AskBD) framework, which generates adaptive reference solutions using LLMs to enhance error detection. Experiments on 200 examples of GSM8K show that AskBD effectively mitigates bias and improves performance, especially when combined with reasoning-enhancing techniques like chain-of-thought prompting.

cs.CL↗
arXiv2024

Beyond Partisan Leaning: A Comparative Analysis of Political Bias in Large Language Models

As large language models (LLMs) become increasingly embedded in civic, educational, and political information environments, concerns about their potential political bias have grown. Prior research often evaluates such bias through simulated personas or predefined ideological typologies, which may introduce artificial framing effects or overlook how models behave in general use scenarios. This study adopts a persona-free, topic-specific approach to evaluate political behavior in LLMs, reflecting how users typically interact with these systems-without ideological role-play or conditioning. We introduce a two-dimensional framework: one axis captures partisan orientation on highly polarized topics (e.g., abortion, immigration), and the other assesses sociopolitical engagement on less polarized issues (e.g., climate change, foreign policy). Using survey-style prompts drawn from the ANES and Pew Research Center, we analyze responses from 43 LLMs developed in the U.S., Europe, China, and the Middle East. We propose an entropy-weighted bias score to quantify both the direction and consistency of partisan alignment, and identify four behavioral clusters through engagement profiles. Findings show most models lean center-left or left ideologically and vary in their nonpartisan engagement patterns. Model scale and openness are not strong predictors of behavior, suggesting that alignment strategy and institutional context play a more decisive role in shaping political expression.

cs.CY↗
arXiv2024

A LLM-Powered Automatic Grading Framework with Human-Level Guidelines Optimization

Open-ended short-answer questions (SAGs) have been widely recognized as a powerful tool for providing deeper insights into learners' responses in the context of learning analytics (LA). However, SAGs often present challenges in practice due to the high grading workload and concerns about inconsistent assessments. With recent advancements in natural language processing (NLP), automatic short-answer grading (ASAG) offers a promising solution to these challenges. Despite this, current ASAG algorithms are often limited in generalizability and tend to be tailored to specific questions. In this paper, we propose a unified multi-agent ASAG framework, GradeOpt, which leverages large language models (LLMs) as graders for SAGs. More importantly, GradeOpt incorporates two additional LLM-based agents - the reflector and the refiner - into the multi-agent system. This enables GradeOpt to automatically optimize the original grading guidelines by performing self-reflection on its errors. Through experiments on a challenging ASAG task, namely the grading of pedagogical content knowledge (PCK) and content knowledge (CK) questions, GradeOpt demonstrates superior performance in grading accuracy and behavior alignment with human graders compared to representative baselines. Finally, comprehensive ablation studies confirm the effectiveness of the individual components designed in GradeOpt.

cs.AI↗
arXiv2024

Spectral-Aware Augmentation for Enhanced Graph Representation Learning

Graph Contrastive Learning (GCL) has demonstrated remarkable effectiveness in learning representations on graphs in recent years. To generate ideal augmentation views, the augmentation generation methods should preserve essential information while discarding less relevant details for downstream tasks. However, current augmentation methods usually involve random topology corruption in the spatial domain, which fails to adequately address information spread across different frequencies in the spectral domain. Our preliminary study highlights this issue, demonstrating that spatial random perturbations impact all frequency bands almost uniformly. Given that task-relevant information typically resides in specific spectral regions that vary across graphs, this one-size-fits-all approach can pose challenges. We argue that indiscriminate spatial random perturbation might unintentionally weaken task-relevant information, reducing its effectiveness. To tackle this challenge, we propose applying perturbations selectively, focusing on information specific to different frequencies across diverse graphs. In this paper, we present GASSER, a model that applies tailored perturbations to specific frequencies of graph structures in the spectral domain, guided by spectral hints. Through extensive experimentation and theoretical analysis, we demonstrate that the augmentation views generated by GASSER are adaptive, controllable, and intuitively aligned with the homophily ratios and spectrum of graph structures.

cs.LG↗