Cover Image

TriLens: Per-Layer Logit-Lens Entropy for White-Box Hallucination Detection

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Yang, Bohan, Gong, Yijun, Zhang, Zhi, Zhang, Ge, Xing, Wenpeng, Han, Meng
Format:	Preprint
Published:	2026
Subjects:	Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

LatentAudit: Real-Time White-Box Faithfulness Monitoring for Retrieval-Augmented Generation with Verifiable Deployment
by: Yu, Zhe, et al.
Published: (2026)

FaithLens: Detecting and Explaining Faithfulness Hallucination
by: Si, Shuzheng, et al.
Published: (2025)

From Retinal Evidence to Safe Decisions: RETINA-SAFE and ECRT for Hallucination Risk Triage in Medical LLMs
by: Yu, Zhe, et al.
Published: (2026)

Spectral Logit Sculpting: Adaptive Low-Rank Logit Transformation for Controlled Text Generation
by: Li, Jin, et al.
Published: (2025)

HalluLens: LLM Hallucination Benchmark
by: Bang, Yejin, et al.
Published: (2025)

Heterogeneous Graph Structure Learning through the Lens of Data-generating Processes
by: Jiang, Keyue, et al.
Published: (2025)

Towards Understanding Extrapolation: a Causal Lens
by: Kong, Lingjing, et al.
Published: (2025)

SePer: Measure Retrieval Utility Through The Lens Of Semantic Perplexity Reduction
by: Dai, Lu, et al.
Published: (2025)

ViT-Lens: Towards Omni-modal Representations
by: Lei, Weixian, et al.
Published: (2023)

Revisiting Transformers through the Lens of Low Entropy and Dynamic Sparsity
by: Ren, Ruifeng, et al.
Published: (2025)

Counterfactual Probing for Hallucination Detection and Mitigation in Large Language Models
by: Feng, Yijun
Published: (2025)

Entropy-Lens: Uncovering Decision Strategies in LLMs
by: Ali, Riccardo, et al.
Published: (2025)

HGMF: A Hierarchical Gaussian Mixture Framework for Scalable Tool Invocation within the Model Context Protocol
by: Xing, Wenpeng, et al.
Published: (2025)

Learned Hallucination Detection in Black-Box LLMs using Token-level Entropy Production Rate
by: Moslonka, Charles, et al.
Published: (2025)

Lookback Lens: Detecting and Mitigating Contextual Hallucinations in Large Language Models Using Only Attention Maps
by: Chuang, Yung-Sung, et al.
Published: (2024)

The Attribution Blind Spot: Detecting When Language Models Rely on Memory Rather Than Retrieved Context
by: Yu, Zhe, et al.
Published: (2026)

TimeLens: Rethinking Video Temporal Grounding with Multimodal LLMs
by: Zhang, Jun, et al.
Published: (2025)

Is Chain-of-Thought Reasoning of LLMs a Mirage? A Data Distribution Lens
by: Zhao, Chengshuai, et al.
Published: (2025)

Rectifying LLM Thought from Lens of Optimization
by: Liu, Junnan, et al.
Published: (2025)

CloudLens: Modeling and Detecting Cloud Security Vulnerabilities
by: Kazdagli, Mikhail, et al.
Published: (2024)

MEraser: An Effective Fingerprint Erasure Approach for Large Language Models
by: Zhang, Jingxuan, et al.
Published: (2025)

ProjLens: Unveiling the Role of Projectors in Multimodal Model Safety
by: Wang, Kun, et al.
Published: (2026)

Rethinking the Text-Vision Reasoning Imbalance in MLLMs through the Lens of Training Recipes
by: Yao, Guanyu, et al.
Published: (2025)

LogicLens: Visual-Logical Co-Reasoning for Text-Centric Forgery Analysis
by: Zeng, Fanwei, et al.
Published: (2025)

Silencing the Guardrails: Inference-Time Jailbreaking via Dynamic Contextual Representation Ablation
by: Xing, Wenpeng, et al.
Published: (2026)

Towards Robust and Secure Embodied AI: A Survey on Vulnerabilities and Attacks
by: Xing, Wenpeng, et al.
Published: (2025)

Evaluating LLMs' Assessment of Mixed-Context Hallucination Through the Lens of Summarization
by: Qi, Siya, et al.
Published: (2025)

Concise Reasoning in the Lens of Lagrangian Optimization
by: Gao, Chengqian, et al.
Published: (2025)

StructLens: A Structural Lens for Language Models via Maximum Spanning Trees
by: Sakajo, Haruki, et al.
Published: (2026)

A Causal Lens for Learning Long-term Fair Policies
by: Lear, Jacob, et al.
Published: (2025)

The Statistical Validation of Innovation Lens
by: Radaelli, Giacomo, et al.
Published: (2025)

PLPHP: Per-Layer Per-Head Vision Token Pruning for Efficient Large Vision-Language Models
by: Meng, Yu, et al.
Published: (2025)

Grounding from an AI and Cognitive Science Lens
by: Bajaj, Goonmeet, et al.
Published: (2024)

Turning Black Box into White Box: Dataset Distillation Leaks
by: Chen, Huajie, et al.
Published: (2026)

Hallucination Detection with the Internal Layers of LLMs
by: Preiß, Martin
Published: (2025)

CCHall: A Novel Benchmark for Joint Cross-Lingual and Cross-Modal Hallucinations Detection in Large Language Models
by: Zhang, Yongheng, et al.
Published: (2025)

NeuRel-Attack: Neuron Relearning for Safety Disalignment in Large Language Models
by: Zhou, Yi, et al.
Published: (2025)

ARO: A New Lens On Matrix Optimization For Large Models
by: Gong, Wenbo, et al.
Published: (2026)

ConceptLens: from Pixels to Understanding
by: Dalal, Abhilekha, et al.
Published: (2024)

Semantic Entropy Probes: Robust and Cheap Hallucination Detection in LLMs
by: Kossen, Jannik, et al.
Published: (2024)