9 papers · 1 filter
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…
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…