Copertina

Harnessing Reasoning Trajectories for Hallucination Detection via Answer-agreement Representation Shaping

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Zhang, Jianxiong, Guo, Bing, Jiang, Yuming, Wang, Haobo, An, Bo, Du, Sean
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

FLaG: Fine-Grained Latent Grouping for Hallucination Detection
di: Ye, Wentao, et al.
Pubblicazione: (2026)

Steer LLM Latents for Hallucination Detection
di: Park, Seongheon, et al.
Pubblicazione: (2025)

HaloScope: Harnessing Unlabeled LLM Generations for Hallucination Detection
di: Du, Xuefeng, et al.
Pubblicazione: (2024)

Answer First, Reason Later: Aligning Search Relevance via Mode-Balanced Reinforcement Learning
di: Zhang, Shijie, et al.
Pubblicazione: (2026)

When Answers Stray from Questions: Hallucination Detection via Question-Answer Orthogonal Decomposition
di: Yao, Siyang, et al.
Pubblicazione: (2026)

Harnessing Feature Resonance under Arbitrary Target Alignment for Out-of-Distribution Node Detection
di: Yang, Shenzhi, et al.
Pubblicazione: (2025)

InterrogateLLM: Zero-Resource Hallucination Detection in LLM-Generated Answers
di: Yehuda, Yakir, et al.
Pubblicazione: (2024)

Online Influence Maximization: Concept and Algorithm
di: Guo, Jianxiong
Pubblicazione: (2023)

Reasoned Safety Alignment: Ensuring Jailbreak Defense via Answer-Then-Check
di: Cao, Chentao, et al.
Pubblicazione: (2025)

Measuring and Reducing LLM Hallucination without Gold-Standard Answers
di: Wei, Jiaheng, et al.
Pubblicazione: (2024)

LLM Reasoning as Trajectories: Step-Specific Representation Geometry and Correctness Signals
di: Sun, Lihao, et al.
Pubblicazione: (2026)

MolTailor: Tailoring Chemical Molecular Representation to Specific Tasks via Text Prompts
di: Guo, Haoqiang, et al.
Pubblicazione: (2024)

Graph Edge Representation via Tensor Product Graph Convolutional Representation
di: Jiang, Bo, et al.
Pubblicazione: (2024)

xTED: Cross-Domain Adaptation via Diffusion-Based Trajectory Editing
di: Niu, Haoyi, et al.
Pubblicazione: (2024)

Learning to Reason for Hallucination Span Detection
di: Su, Hsuan, et al.
Pubblicazione: (2025)

Bolster Hallucination Detection via Prompt-Guided Data Augmentation
di: Li, Wenyun, et al.
Pubblicazione: (2025)

Embedding Trajectory for Out-of-Distribution Detection in Mathematical Reasoning
di: Wang, Yiming, et al.
Pubblicazione: (2024)

Representation Consistency for Accurate and Coherent LLM Answer Aggregation
di: Jiang, Junqi, et al.
Pubblicazione: (2025)

OASIS: Harnessing Diffusion Adversarial Network for Ocean Salinity Imputation using Sparse Drifter Trajectories
di: Li, Bo, et al.
Pubblicazione: (2025)

Harnesses for Inference-Time Alignment over Execution Trajectories
di: Wang, Boyuan, et al.
Pubblicazione: (2026)

Self-supervised Trajectory Representation Learning with Temporal Regularities and Travel Semantics
di: Jiang, Jiawei, et al.
Pubblicazione: (2022)

Hidden Representation Clustering with Multi-Task Representation Learning towards Robust Online Budget Allocation
di: Wang, Xiaohan, et al.
Pubblicazione: (2025)

CRAFT: Calibrated Reasoning with Answer-Faithful Traces via Reinforcement Learning for Multi-Hop Question Answering
di: Liu, Yu, et al.
Pubblicazione: (2026)

Understanding and Mitigating the Bias in Sample Selection for Learning with Noisy Labels
di: Wei, Qi, et al.
Pubblicazione: (2024)

RAVR: Reference-Answer-guided Variational Reasoning for Large Language Models
di: Lin, Tianqianjin, et al.
Pubblicazione: (2025)

Incentivizing LLMs to Self-Verify Their Answers
di: Zhang, Fuxiang, et al.
Pubblicazione: (2025)

Scalable Trajectory-User Linking with Dual-Stream Representation Networks
di: Zhang, Hao, et al.
Pubblicazione: (2025)

Right Question is Already Half the Answer: Fully Unsupervised LLM Reasoning Incentivization
di: Zhang, Qingyang, et al.
Pubblicazione: (2025)

Plantain: Plan-Answer Interleaved Reasoning
di: Liang, Anthony, et al.
Pubblicazione: (2025)

Reasoning Model Unlearning: Forgetting Traces, Not Just Answers, While Preserving Reasoning Skills
di: Wang, Changsheng, et al.
Pubblicazione: (2025)

Boosting LLM Reasoning via Human-Inspired Reward Shaping
di: Lin, Wenze, et al.
Pubblicazione: (2026)

KnowHalu: Hallucination Detection via Multi-Form Knowledge Based Factual Checking
di: Zhang, Jiawei, et al.
Pubblicazione: (2024)

Robust Hallucination Detection in LLMs via Adaptive Token Selection
di: Niu, Mengjia, et al.
Pubblicazione: (2025)

Semantic Energy: Detecting LLM Hallucination Beyond Entropy
di: Ma, Huan, et al.
Pubblicazione: (2025)

Mitigating Hallucinations in Large Language Models via Causal Reasoning
di: Li, Yuangang, et al.
Pubblicazione: (2025)

Understanding Multimodal Hallucination with Parameter-Free Representation Alignment
di: Wang, Yueqian, et al.
Pubblicazione: (2024)

On the Robustness of Answer Formats in Medical Reasoning Models
di: Taveekitworachai, Pittawat, et al.
Pubblicazione: (2025)

Interpreting and Editing Vision-Language Representations to Mitigate Hallucinations
di: Jiang, Nick, et al.
Pubblicazione: (2024)

Generalization or Hallucination? Understanding Out-of-Context Reasoning in Transformers
di: Huang, Yixiao, et al.
Pubblicazione: (2025)

DefAn: Definitive Answer Dataset for LLMs Hallucination Evaluation
di: Rahman, A B M Ashikur, et al.
Pubblicazione: (2024)