Image de couverture de livre

Where Does Reasoning Break? Step-Level Hallucination Detection via Hidden-State Transport Geometry

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Alvarez, Tyler, Baheri, Ali
Format:	Preprint
Publié:	2026
Sujets:	Computation and Language Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Where Should Diffusion Enter a Language Model? Geometry-Guided Hidden-State Replacement
par: Kong, Injin, et autres
Publié: (2026)

ICR Probe: Tracking Hidden State Dynamics for Reliable Hallucination Detection in LLMs
par: Zhang, Zhenliang, et autres
Publié: (2025)

Step-by-Step Reasoning to Solve Grid Puzzles: Where do LLMs Falter?
par: Tyagi, Nemika, et autres
Publié: (2024)

HARP: Hallucination Detection via Reasoning Subspace Projection
par: Hu, Junjie, et autres
Publié: (2025)

Where Fake Citations Are Made: Tracing Field-Level Hallucination to Specific Neurons in LLMs
par: Chen, Yuefei, et autres
Publié: (2026)

Unsupervised Hallucination Detection by Inspecting Reasoning Processes
par: Srey, Ponhvoan, et autres
Publié: (2025)

ConfSpec: Efficient Step-Level Speculative Reasoning via Confidence-Gated Verification
par: Liu, Siran, et autres
Publié: (2026)

HALoGEN: Fantastic LLM Hallucinations and Where to Find Them
par: Ravichander, Abhilasha, et autres
Publié: (2025)

Does Less Hallucination Mean Less Creativity? An Empirical Investigation in LLMs
par: Banerjee, Mohor, et autres
Publié: (2025)

Learning to Reason for Hallucination Span Detection
par: Su, Hsuan, et autres
Publié: (2025)

Where Do Prompt Perturbations Break Generation? A Segment-Level View of Robustness in LoRA-Tuned Language Models
par: Li, Zhuoyun, et autres
Publié: (2026)

Hallucination Detection and Hallucination Mitigation: An Investigation
par: Luo, Junliang, et autres
Publié: (2024)

Small Updates, Big Doubts: Does Parameter-Efficient Fine-tuning Enhance Hallucination Detection ?
par: Hu, Xu, et autres
Publié: (2026)

Enhancing Hallucination Detection via Future Context
par: Lee, Joosung, et autres
Publié: (2025)

Geometry-Aware Backdoor Attacks: Leveraging Curvature in Hyperbolic Embeddings
par: Baheri, Ali
Publié: (2025)

SmartThinker: Learning to Compress and Preserve Reasoning by Step-Level Length Control
par: He, Xingyang, et autres
Publié: (2025)

Is LLMs Hallucination Usable? LLM-based Negative Reasoning for Fake News Detection
par: Zhang, Chaowei, et autres
Publié: (2025)

LLM Reasoning as Trajectories: Step-Specific Representation Geometry and Correctness Signals
par: Sun, Lihao, et autres
Publié: (2026)

Phase Transitions in Affective Meaning Divergence: The Hidden Drift Before the Break
par: Litchiowong, Napassorn
Publié: (2026)

Detection and Mitigation of Hallucination in Large Reasoning Models: A Mechanistic Perspective
par: Sun, Zhongxiang, et autres
Publié: (2025)

Spatiotemporal Hidden-State Dynamics as a Signature of Internal Reasoning in Large Language Models
par: Furuya, Kotaro, et autres
Publié: (2026)

R3-RAG: Learning Step-by-Step Reasoning and Retrieval for LLMs via Reinforcement Learning
par: Li, Yuan, et autres
Publié: (2025)

Scalable Token-Level Hallucination Detection in Large Language Models
par: Min, Rui, et autres
Publié: (2026)

Don't Let It Hallucinate: Premise Verification via Retrieval-Augmented Logical Reasoning
par: Qin, Yuehan, et autres
Publié: (2025)

The Energy of Falsehood: Detecting Hallucinations via Diffusion Model Likelihoods
par: Gautam, Arpit Singh, et autres
Publié: (2026)

Token-Guard: Towards Token-Level Hallucination Control via Self-Checking Decoding
par: Zhu, Yifan, et autres
Publié: (2026)

From Associations to Activations: Comparing Behavioral and Hidden-State Semantic Geometry in LLMs
par: Schiekiera, Louis, et autres
Publié: (2026)

MedReason: Eliciting Factual Medical Reasoning Steps in LLMs via Knowledge Graphs
par: Wu, Juncheng, et autres
Publié: (2025)

Reasoning Models Know When They're Right: Probing Hidden States for Self-Verification
par: Zhang, Anqi, et autres
Publié: (2025)

Unsupervised Real-Time Hallucination Detection based on the Internal States of Large Language Models
par: Su, Weihang, et autres
Publié: (2024)

Black-Box Hallucination Detection via Consistency Under the Uncertain Expression
par: Joo, Seongho, et autres
Publié: (2025)

HIDE and Seek: Detecting Hallucinations in Language Models via Decoupled Representations
par: Chatterjee, Anwoy, et autres
Publié: (2025)

LLM Reasoners: New Evaluation, Library, and Analysis of Step-by-Step Reasoning with Large Language Models
par: Hao, Shibo, et autres
Publié: (2024)

Reasoning Fails Where Step Flow Breaks
par: Xu, Xiaoyu, et autres
Publié: (2026)

Expediting and Elevating Large Language Model Reasoning via Hidden Chain-of-Thought Decoding
par: Liu, Tianqiao, et autres
Publié: (2024)

Step-by-Step Fact Verification System for Medical Claims with Explainable Reasoning
par: Vladika, Juraj, et autres
Publié: (2025)

Hallucination Detection with Small Language Models
par: Cheung, Ming
Publié: (2025)

Hallucination Detection with the Internal Layers of LLMs
par: Preiß, Martin
Publié: (2025)

Towards Long Context Hallucination Detection
par: Liu, Siyi, et autres
Publié: (2025)

FactSelfCheck: Fact-Level Black-Box Hallucination Detection for LLMs
par: Sawczyn, Albert, et autres
Publié: (2025)