arXiv subjects

Runze Xia

Publications and source records attributed to Runze Xia.

5 recordsLinked to original sources

arXiv2026

DUD: Decoupled Update Dynamics for Reliable Uncertainty Quantification in Large Language Models

Accurate Uncertainty Quantification (UQ) is critical for reliable deployment of Large Language Models (LLMs), yet traditional probability-based metrics often fail to capture the model's true epistemic state. While recent mechanistic approaches leverage hidden state dynamics, they typically aggregate residual stream updates, conflating the distinct roles of parametric memory (Feed-Forward Networks) and contextual processing (Attention). We argue that this aggregation obscures fine-grained mechanistic conflicts, such as memory-context misalignment, that are fundamental indicators of uncertainty. To address this, we introduce \textbf{D}ecoupled \textbf{U}pdate \textbf{D}ynamics \textbf{(DUD)}, a framework that explicitly decouples FFN and Attention contributions via noise-induced causal interventions. By quantifying the independent restoration capabilities of each module, we construct a dual-stream dynamic profile that captures the model's internal fragility. Extensive experiments demonstrate that DUD significantly outperforms state-of-the-art baselines in both uncertainty estimation and calibration, while exhibiting superior cross-dataset generalization, validating decoupled dynamics as a robust proxy for model faithfulness.

cs.CL↗

arXiv2026

Hallucination Mitigating for Medical Report Generation

In the realm of medical report generation (MRG), the integration of natural language processing has emerged as a vital tool to alleviate the workload of radiologists. Despite the impressive capabilities demonstrated by large vision language models (LVLMs) in understanding natural language, their susceptibility to generating plausible yet inaccurate claims, known as ``hallucinations'', raises concerns-especially in the nuanced and critical field of medical. In this work, we introduce a framework, \textbf{K}nowledge-\textbf{E}nhanced with Fine-Grained \textbf{R}einforced Rewards \textbf{M}edical Report Generation (KERM), to tackle the issue. Our approach refines the input to the LVLM by first utilizing MedCLIP for knowledge retrieval, incorporating relevant lesion fact sentences from a curated knowledge corpus. We then introduce a novel purification module to ensure the retrieved knowledge is contextually relevant to the patient's clinical context. Subsequently, we employ fine-grained rewards to guide these models in generating highly supportive and clinically relevant descriptions, ensuring the alignment of model's outputs with desired behaviors. Experimental results on IU-Xray and MIMIC-CXR datasets validate the effectiveness of our approach in mitigating hallucinations and enhancing report quality.

cs.CL↗

arXiv2025

From Reasoning LLMs to BERT: A Two-Stage Distillation Framework for Search Relevance

Query-service relevance prediction in e-commerce search systems faces strict latency requirements that prevent the direct application of Large Language Models (LLMs). To bridge this gap, we propose a two-stage reasoning distillation framework to transfer reasoning capabilities from a powerful teacher LLM to a lightweight, deployment-friendly student model. In the first stage, we address the limitations of general-purpose LLMs by constructing a domain-adapted teacher model. This is achieved through a three-step process: domain-adaptive pre-training to inject platform knowledge, supervised fine-tuning to elicit reasoning skills, and preference optimization with a multi-dimensional reward model to ensure the generation of reliable and preference-aligned reasoning paths. This teacher can then automatically annotate massive query-service pairs from search logs with both relevance labels and reasoning chains. In the second stage, to address the challenges of architectural heterogeneity in standard distillation, we introduce Contrastive Reasoning Self-Distillation (CRSD). By modeling the behavior of the same student model under ``standard'' and ``reasoning-augmented'' inputs as a teacher-student relationship, CRSD enables the lightweight model to internalize the teacher's complex decision-making mechanisms without needing the explicit reasoning path at inference. Offline evaluations and online A/B testing in the Meituan search advertising system demonstrate that our framework achieves significant improvements across multiple metrics, validating its effectiveness and practical value.

cs.IR↗

arXiv2025

Improving Brain-to-Image Reconstruction via Fine-Grained Text Bridging

Brain-to-Image reconstruction aims to recover visual stimuli perceived by humans from brain activity. However, the reconstructed visual stimuli often missing details and semantic inconsistencies, which may be attributed to insufficient semantic information. To address this issue, we propose an approach named Fine-grained Brain-to-Image reconstruction (FgB2I), which employs fine-grained text as bridge to improve image reconstruction. FgB2I comprises three key stages: detail enhancement, decoding fine-grained text descriptions, and text-bridged brain-to-image reconstruction. In the detail-enhancement stage, we leverage large vision-language models to generate fine-grained captions for visual stimuli and experimentally validate its importance. We propose three reward metrics (object accuracy, text-image semantic similarity, and image-image semantic similarity) to guide the language model in decoding fine-grained text descriptions from fMRI signals. The fine-grained text descriptions can be integrated into existing reconstruction methods to achieve fine-grained Brain-to-Image reconstruction.

cs.CV↗

arXiv2024

Decoding the Echoes of Vision from fMRI: Memory Disentangling for Past Semantic Information

The human visual system is capable of processing continuous streams of visual information, but how the brain encodes and retrieves recent visual memories during continuous visual processing remains unexplored. This study investigates the capacity of working memory to retain past information under continuous visual stimuli. And then we propose a new task Memory Disentangling, which aims to extract and decode past information from fMRI signals. To address the issue of interference from past memory information, we design a disentangled contrastive learning method inspired by the phenomenon of proactive interference. This method separates the information between adjacent fMRI signals into current and past components and decodes them into image descriptions. Experimental results demonstrate that this method effectively disentangles the information within fMRI signals. This research could advance brain-computer interfaces and mitigate the problem of low temporal resolution in fMRI.

cs.CL↗