Cover Image

Beyond Next Token Probabilities: Learnable, Fast Detection of Hallucinations and Data Contamination on LLM Output Distributions

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Bar-Shalom, Guy, Frasca, Fabrizio, Lim, Derek, Gelberg, Yoav, Ziser, Yftah, El-Yaniv, Ran, Chechik, Gal, Maron, Haggai
Format:	Preprint
Published:	2025
Subjects:	Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Beyond Token Probes: Hallucination Detection via Activation Tensors with ACT-ViT
by: Bar-Shalom, Guy, et al.
Published: (2025)

Neural Message-Passing on Attention Graphs for Hallucination Detection
by: Frasca, Fabrizio, et al.
Published: (2025)

On The Expressive Power of GNN Derivatives
by: Eitan, Yam, et al.
Published: (2025)

Topological Blindspots: Understanding and Extending Topological Deep Learning Through the Lens of Expressivity
by: Eitan, Yam, et al.
Published: (2024)

A Flexible, Equivariant Framework for Subgraph GNNs via Graph Products and Graph Coarsening
by: Bar-Shalom, Guy, et al.
Published: (2024)

FS-KAN: Permutation Equivariant Kolmogorov-Arnold Networks via Function Sharing
by: Elbaz, Ran, et al.
Published: (2025)

Learning on LoRAs: GL-Equivariant Processing of Low-Rank Weight Spaces for Large Finetuned Models
by: Putterman, Theo, et al.
Published: (2024)

More Test-Time Compute Can Hurt: Overestimation Bias in LLM Beam Search
by: Dalal, Gal, et al.
Published: (2026)

Subgraphormer: Unifying Subgraph GNNs and Graph Transformers via Graph Products
by: Bar-Shalom, Guy, et al.
Published: (2024)

Balancing Efficiency and Expressiveness: Subgraph GNNs with Walk-Based Centrality
by: Southern, Joshua, et al.
Published: (2025)

Training Transformers for KV Cache Compressibility
by: Gelberg, Yoav, et al.
Published: (2026)

Knowing Before Saying: LLM Representations Encode Information About Chain-of-Thought Success Before Completion
by: Afzal, Anum, et al.
Published: (2025)

Policy Optimized Text-to-Image Pipeline Design
by: Gadot, Uri, et al.
Published: (2025)

Understanding and Improving Laplacian Positional Encodings For Temporal GNNs
by: Galron, Yaniv, et al.
Published: (2025)

Efficient GNN Training Through Structure-Aware Randomized Mini-Batching
by: Balaji, Vignesh, et al.
Published: (2025)

Spanning the Visual Analogy Space with a Weight Basis of LoRAs
by: Manor, Hila, et al.
Published: (2026)

A Graph Meta-Network for Learning on Kolmogorov-Arnold Networks
by: Bar-Shalom, Guy, et al.
Published: (2026)

GradMetaNet: An Equivariant Architecture for Learning on Gradients
by: Gelberg, Yoav, et al.
Published: (2025)

Equivariant Deep Weight Space Alignment
by: Navon, Aviv, et al.
Published: (2023)

Lightning-Fast Image Inversion and Editing for Text-to-Image Diffusion Models
by: Samuel, Dvir, et al.
Published: (2023)

Learning from Historical Activations in Graph Neural Networks
by: Galron, Yaniv, et al.
Published: (2026)

From Competition to Collaboration: Designing Sustainable Mechanisms Between LLMs and Online Forums
by: Fono, Niv, et al.
Published: (2026)

Layer by Layer: Uncovering Where Multi-Task Learning Happens in Instruction-Tuned Large Language Models
by: Zhao, Zheng, et al.
Published: (2024)

Improved Generalization of Weight Space Networks via Augmentations
by: Shamsian, Aviv, et al.
Published: (2024)

Fast Encoder-Based 3D from Casual Videos via Point Track Processing
by: Kasten, Yoni, et al.
Published: (2024)

Graph Metanetworks for Processing Diverse Neural Architectures
by: Lim, Derek, et al.
Published: (2023)

Aligning What LLMs Do and Say: Towards Self-Consistent Explanations
by: Admoni, Sahar, et al.
Published: (2025)

SafeSteer: Interpretable Safety Steering with Refusal-Evasion in LLMs
by: Ghosh, Shaona, et al.
Published: (2025)

Future Directions in the Theory of Graph Machine Learning
by: Morris, Christopher, et al.
Published: (2024)

The Empirical Impact of Neural Parameter Symmetries, or Lack Thereof
by: Lim, Derek, et al.
Published: (2024)

Towards Foundation Models on Graphs: An Analysis on Cross-Dataset Transfer of Pretrained GNNs
by: Frasca, Fabrizio, et al.
Published: (2024)

TPA: Next Token Probability Attribution for Detecting Hallucinations in RAG
by: Lu, Pengqian, et al.
Published: (2025)

When Knowledge Is Not Free: Cost-Aware Evidence Selection in Retrieval-Augmented Generation
by: Wu, Mingyan, et al.
Published: (2026)

On the Reconstruction of Training Data from Group Invariant Networks
by: Elbaz, Ran, et al.
Published: (2024)

SHINE: A Scalable In-Context Hypernetwork for Mapping Context to LoRA in a Single Pass
by: Liu, Yewei, et al.
Published: (2026)

It Takes a Graph to Know a Graph: Rewiring for Homophily with a Reference Graph
by: Mendelman, Harel, et al.
Published: (2025)

On the Expressive Power of Permutation-Equivariant Weight-Space Networks
by: Dayan, Adir, et al.
Published: (2026)

On the Expressive Power of Spectral Invariant Graph Neural Networks
by: Zhang, Bohang, et al.
Published: (2024)

TriTex: Learning Texture from a Single Mesh via Triplane Semantic Features
by: Cohen-Bar, Dana, et al.
Published: (2025)

From Actions to Words: Towards Abstractive-Textual Policy Summarization in RL
by: Admoni, Sahar, et al.
Published: (2025)