2 citations · 3 across the 30 of their papers we have counts for
17 papers · 1 filter
Gaussian Material Fields for Volumetric Multi-Energy CT Decomposition
Jian Lin, Jiancheng Fang, Hongming Shan +3
Volumetric material decomposition in multi-energy computed tomography requires a representation that organizes multiple three-dimensional material fields in a common spatial domain…
Hallucination Across the Reasoning Lifecycle: Interface Visibility, Causal Evidence, and Release Control in Large Reasoning Models
Zhe Yu, Mohan Li, Lei Yu +6
Reasoning errors can propagate into later decisions and memory. This survey synthesizes 312 papers and first-party reports on text-based reasoning hallucinations around three quest…
Readable Before Actionable: Causal Tracing of Indirect Prompt Injection
Zhe Yu, Wenpeng Xing, Xingxing Yang +1
Indirect prompt injection causes LLM agents to follow commands embedded in external data. A probe may distinguish instructions from data without identifying a state edit that chang…
TTS-Guard: Black-Box Ownership Verification of Text-to-Speech Models via Adaptive Adversarial Speaker-Pair Fingerprints
Xubin Yue, Zhenhua Xu, Zhebo Wang +5
The rapid maturation of zero-shot Text-to-Speech (TTS) models has turned high-quality voice cloning into a widely available capability, raising acute concerns over unauthorised rep…
FIDES: Faithful Inference via Deep Evidence Signals for Retrieval-Memory Conflict in RAG
Zhe Yu, Wenpeng Xing, Tiancheng Zhao +3
When retrieved evidence contradicts parametric memory, language models frequently ignore context and default to memorized priors -- a failure that undermines the core purpose of re…
TriLens: Per-Layer Logit-Lens Entropy for White-Box Hallucination Detection
Bohan Yang, Yijun Gong, Zhi Zhang +3
When a language model hallucinates, the final answer is wrong, but the mistake is not necessarily invisible inside the model. Different internal pathways may remain uncertain, disa…
Detecting Is Not Resolving: The Monitoring Control Gap in Retrieval Augmented LLMs
Zhe Yu, Wenpeng Xing, Chen Ye +4
Retrieval-augmented LLMs are deployed for tasks where evidence quality determines action safety, yet evaluation protocols assume that single-turn robustness predicts robustness whe…
Composition Collapse: Stable Factual Knowledge Does Not Imply Compositional Reasoning
Zhe Yu, Wenpeng Xing, Yunzhao Wei +4
Post-training is routinely evaluated through aggregate benchmark scores that treat multi-hop reasoning as a single capability -- as if a model that answers more questions correctly…
The Attribution Blind Spot: Detecting When Language Models Rely on Memory Rather Than Retrieved Context
Zhe Yu, Wenpeng Xing, Yunzhao Wei +4
Retrieval-augmented generation promises to ground language model outputs in external evidence, yet the field has no reliable way to verify whether retrieved context actually govern…
Cordon-MAS: Defending RAG against Knowledge Poisoning via Information-Flow Control
Zhe Yu, Wenpeng Xing, Gaolei Li +4
Retrieval-augmented generation (RAG) increasingly underpins high-stakes applications, yet remains vulnerable to Confundo-style poisoning where adversarially optimized documents man…
Silencing the Guardrails: Inference-Time Jailbreaking via Dynamic Contextual Representation Ablation
Wenpeng Xing, Moran Fang, Guangtai Wang +2
While Large Language Models (LLMs) have achieved remarkable performance, they remain vulnerable to jailbreak attacks that circumvent safety constraints. Existing strategies, rangin…
MO-RiskVAE: A Multi-Omics Variational Autoencoder for Survival Risk Modeling in Multiple MyelomaMO-RiskVAE
Zixuan Chen, Heng Zhang, YuPeng Qin +5
Multimodal variational autoencoders (VAEs) have emerged as a powerful framework for survival risk modeling in multiple myeloma by integrating heterogeneous omics and clinical data.…
LatentAudit: Real-Time White-Box Faithfulness Monitoring for Retrieval-Augmented Generation with Verifiable Deployment
Zhe Yu, Wenpeng Xing, Meng Han
Retrieval-augmented generation (RAG) mitigates hallucination but does not eliminate it: a deployed system must still decide, at inference time, whether its answer is actually suppo…
From Retinal Evidence to Safe Decisions: RETINA-SAFE and ECRT for Hallucination Risk Triage in Medical LLMs
Zhe Yu, Wenpeng Xing, Meng Han
Hallucinations in medical large language models (LLMs) remain a safety-critical issue, particularly when available evidence is insufficient or conflicting. We study this problem in…
KinGuard: Hierarchical Kinship-Aware Fingerprinting to Defend Against Large Language Model Stealing
Zhenhua Xu, Xiaoning Tian, Wenjun Zeng +5
Protecting the intellectual property of large language models requires robust ownership verification. Conventional backdoor fingerprinting, however, is flawed by a stealth-robustne…
ICPO: Illocution-Calibrated Policy Optimization for Multi-Turn Conversation
Zhebo Wang, Xiaohu Mu, Zijie Zhou +4
Large Language Models (LLMs) in multi-turn conversations often suffer from a ``lost-in-conversation'' phenomenon, where they struggle to recover from early incorrect assumptions, p…
ForgetMark: Stealthy Fingerprint Embedding via Targeted Unlearning in Language Models
Zhenhua Xu, Haobo Zhang, Zhebo Wang +4
Existing invasive (backdoor) fingerprints suffer from high-perplexity triggers that are easily filtered, fixed response patterns exposed by heuristic detectors, and spurious activa…