arXiv subjects

Qiyuan Li

Publications and source records attributed to Qiyuan Li.

6 recordsLinked to original sources

arXiv2026

StateSwap: Probing Support-Elimination Hidden States in Multiple-Choice Questions

Large language models often answer the same multiple-choice question inconsistently when it is posed under support-oriented and elimination-oriented framings. We investigate whether these discrepancies arise from different internal representations induced by the two framings. We introduce a dual-framing protocol with minimally varied prompts that use either support- or elimination-oriented framing while keeping the evaluation target fixed. To probe the internal computation, we append an untrained special token, [STATE], and treat its residual-stream activation as an intervention interface. Across both models, the two framings induce separable [STATE] activations concentrated in intermediate layers. Swapping these activations between paired prompts systematically changes predictions and improves cross-framing agreement, providing intervention-based evidence that the activations are behaviorally relevant. Beyond instance-level substitution, mean-difference steering directions derived from the dual-framing contrast exhibit more bounded layer-wise responses than matched contrastive activation addition directions under the evaluated protocol.

cs.CL↗

arXiv2026

GraphRareBench: An Auditable Graph-Evidence Benchmark for Phenotype-Driven Rare-Disease Diagnosis

Phenotype-driven diagnostic benchmarks usually report the rank of the reference disease, but they rarely reveal which plausible alternatives are ranked above it or what evidence a tool-using model examines before making its decision. We introduce GraphRareBench, a provenance-preserving benchmark containing 2,365 ontology-derived cases and 18,093 target-confounder pairs. Each case includes a coarsened HPO query, a fixed candidate pool, graph-defined hard confounders, and source-linked evidence records. On the 237-case gene-component-disjoint test split, supervised rankers using a shared 21-feature interface achieved MRRs ranging from 0.640 to 0.740 and case-averaged target-over-confounder accuracies ranging from 0.898 to 0.916. Agents instantiated with Agents-A1 and DeepSeek-V4-Flash achieved MRRs of 0.746 and 0.718, respectively. Their paired MRR difference was not statistically significant, whereas their target-evidence coverage differed by 0.561. Together with the observation that 22.1% to 43.7% of selected Hit@10 successes still ranked at least one graph-defined hard confounder above the target, these results indicate that full-pool retrieval, hard-confounder discrimination, and observable evidence access capture complementary aspects of model behavior. GraphRareBench therefore provides a foundation for more transparent and evidence-aware evaluation of phenotype-driven diagnostic systems. Code and data are available at https://github.com/GUI0609/GraphRareBench.

q-bio.QM↗

arXiv2025

Beyond Demographics: Enhancing Cultural Value Survey Simulation with Multi-Stage Personality-Driven Cognitive Reasoning

Introducing MARK, the Multi-stAge Reasoning frameworK for cultural value survey response simulation, designed to enhance the accuracy, steerability, and interpretability of large language models in this task. The system is inspired by the type dynamics theory in the MBTI psychological framework for personality research. It effectively predicts and utilizes human demographic information for simulation: life-situational stress analysis, group-level personality prediction, and self-weighted cognitive imitation. Experiments on the World Values Survey show that MARK outperforms existing baselines by 10% accuracy and reduces the divergence between model predictions and human preferences. This highlights the potential of our framework to improve zero-shot personalization and help social scientists interpret model predictions.

cs.CL↗

arXiv2025

Reviewing Clinical Knowledge in Medical Large Language Models: Training and Beyond

The large-scale development of large language models (LLMs) in medical contexts, such as diagnostic assistance and treatment recommendations, necessitates that these models possess accurate medical knowledge and deliver traceable decision-making processes. Clinical knowledge, encompassing the insights gained from research on the causes, prognosis, diagnosis, and treatment of diseases, has been extensively examined within real-world medical practices. Recently, there has been a notable increase in research efforts aimed at integrating this type of knowledge into LLMs, encompassing not only traditional text and multimodal data integration but also technologies such as knowledge graphs (KGs) and retrieval-augmented generation (RAG). In this paper, we review the various initiatives to embed clinical knowledge into training-based, KG-supported, and RAG-assisted LLMs. We begin by gathering reliable knowledge sources from the medical domain, including databases and datasets. Next, we evaluate implementations for integrating clinical knowledge through specialized datasets and collaborations with external knowledge sources such as KGs and relevant documentation. Furthermore, we discuss the applications of the developed medical LLMs in the industrial sector to assess the disparity between models developed in academic settings and those in industry. We conclude the survey by presenting evaluation systems applicable to relevant tasks and identifying potential challenges facing this field. In this review, we do not aim for completeness, since any ostensibly complete review would soon be outdated. Our goal is to illustrate diversity by selecting representative and accessible items from current research and industry practices, reflecting real-world situations rather than claiming completeness. Thus, we emphasize showcasing diverse approaches.

cs.AI↗

arXiv2024

An interpretable imbalanced semi-supervised deep learning framework for improving differential diagnosis of skin diseases

Dermatological diseases are among the most common disorders worldwide. This paper presents the first study of the interpretability and imbalanced semi-supervised learning of the multiclass intelligent skin diagnosis framework (ISDL) using 58,457 skin images with 10,857 unlabeled samples. Pseudo-labelled samples from minority classes have a higher probability at each iteration of class-rebalancing self-training, thereby promoting the utilization of unlabeled samples to solve the class imbalance problem. Our ISDL achieved a promising performance with an accuracy of 0.979, sensitivity of 0.975, specificity of 0.973, macro-F1 score of 0.974 and area under the receiver operating characteristic curve (AUC) of 0.999 for multi-label skin disease classification. The Shapley Additive explanation (SHAP) method is combined with our ISDL to explain how the deep learning model makes predictions. This finding is consistent with the clinical diagnosis. We also proposed a sampling distribution optimisation strategy to select pseudo-labelled samples in a more effective manner using ISDLplus. Furthermore, it has the potential to relieve the pressure placed on professional doctors, as well as help with practical issues associated with a shortage of such doctors in rural areas.

cs.CV↗

arXiv2022

Permutation-based tests for discontinuities in event studies

We propose using a permutation test to detect discontinuities in an underlying economic model at a known cutoff point. Relative to the existing literature, we show that this test is well suited for event studies based on time-series data. The test statistic measures the distance between the empirical distribution functions of observed data in two local subsamples on the two sides of the cutoff. Critical values are computed via a standard permutation algorithm. Under a high-level condition that the observed data can be coupled by a collection of conditionally independent variables, we establish the asymptotic validity of the permutation test, allowing the sizes of the local subsamples to be either be fixed or grow to infinity. In the latter case, we also establish that the permutation test is consistent. We demonstrate that our high-level condition can be verified in a broad range of problems in the infill asymptotic time-series setting, which justifies using the permutation test to detect jumps in economic variables such as volatility, trading activity, and liquidity. These potential applications are illustrated in an empirical case study for selected FOMC announcements during the ongoing COVID-19 pandemic.

econ.EM↗