Copertina

TruthPrInt: Mitigating Large Vision-Language Models Object Hallucination Via Latent Truthful-Guided Pre-Intervention

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Duan, Jinhao, Kong, Fei, Cheng, Hao, Diffenderfer, James, Kailkhura, Bhavya, Sun, Lichao, Zhu, Xiaofeng, Shi, Xiaoshuang, Xu, Kaidi
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Computer Vision and Pattern Recognition Artificial Intelligence Computation and Language
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

UProp: Investigating the Uncertainty Propagation of LLMs in Multi-Step Agentic Decision-Making
di: Duan, Jinhao, et al.
Pubblicazione: (2025)

GTBench: Uncovering the Strategic Reasoning Limitations of LLMs via Game-Theoretic Evaluations
di: Duan, Jinhao, et al.
Pubblicazione: (2024)

LRR-Bench: Left, Right or Rotate? Vision-Language models Still Struggle With Spatial Understanding Tasks
di: Kong, Fei, et al.
Pubblicazione: (2025)

ACT-Diffusion: Efficient Adversarial Consistency Training for One-step Diffusion Models
di: Kong, Fei, et al.
Pubblicazione: (2023)

Adversarial Robustness Limits via Scaling-Law and Human-Alignment Studies
di: Bartoldson, Brian R., et al.
Pubblicazione: (2024)

LLM Unlearning Reveals a Stronger-Than-Expected Coreset Effect in Current Benchmarks
di: Pal, Soumyadeep, et al.
Pubblicazione: (2025)

Shifting Attention to Relevance: Towards the Predictive Uncertainty Quantification of Free-Form Large Language Models
di: Duan, Jinhao, et al.
Pubblicazione: (2023)

Double Visual Defense: Adversarial Pre-training and Instruction Tuning for Improving Vision-Language Model Robustness
di: Wang, Zeyu, et al.
Pubblicazione: (2025)

COIN: Uncertainty-Guarding Selective Question Answering for Foundation Models with Provable Risk Guarantees
di: Wang, Zhiyuan, et al.
Pubblicazione: (2025)

Train for Truth, Keep the Skills: Binary Retrieval-Augmented Reward Mitigates Hallucinations
di: Chen, Tong, et al.
Pubblicazione: (2025)

TruthX: Alleviating Hallucinations by Editing Large Language Models in Truthful Space
di: Zhang, Shaolei, et al.
Pubblicazione: (2024)

Decoding Compressed Trust: Scrutinizing the Trustworthiness of Efficient LLMs Under Compression
di: Hong, Junyuan, et al.
Pubblicazione: (2024)

Truth-Aware Context Selection: Mitigating Hallucinations of Large Language Models Being Misled by Untruthful Contexts
di: Yu, Tian, et al.
Pubblicazione: (2024)

Seeing It or Not? Interpretable Vision-aware Latent Steering to Mitigate Object Hallucinations
di: Chen, Boxu, et al.
Pubblicazione: (2025)

Two Pathways to Truthfulness: On the Intrinsic Encoding of LLM Hallucinations
di: Luo, Wen, et al.
Pubblicazione: (2026)

The Truth, the Whole Truth, and Nothing but the Truth: Automatic Visualization Evaluation from Reconstruction Quality
di: Bujack, Roxana, et al.
Pubblicazione: (2026)

ICT: Image-Object Cross-Level Trusted Intervention for Mitigating Object Hallucination in Large Vision-Language Models
di: Chen, Junzhe, et al.
Pubblicazione: (2024)

SOUL: Unlocking the Power of Second-Order Optimization for LLM Unlearning
di: Jia, Jinghan, et al.
Pubblicazione: (2024)

Truth Knows No Language: Evaluating Truthfulness Beyond English
di: Figueras, Blanca Calvo, et al.
Pubblicazione: (2025)

Truth Forest: Toward Multi-Scale Truthfulness in Large Language Models through Intervention without Tuning
di: Chen, Zhongzhi, et al.
Pubblicazione: (2023)

End-to-End Mesh Optimization of a Hybrid Deep Learning Black-Box PDE Solver
di: Ma, Shaocong, et al.
Pubblicazione: (2024)

Object Hallucination-Free Reinforcement Unlearning for Vision-Language Models
di: Jia, Kaidi, et al.
Pubblicazione: (2026)

Graphing the Truth: Structured Visualizations for Automated Hallucination Detection in LLMs
di: Agrawal, Tanmay
Pubblicazione: (2025)

Truthful Text Sanitization Guided by Inference Attacks
di: Pilán, Ildikó, et al.
Pubblicazione: (2024)

Calibration without Ground Truth
di: Kong, Yuqing, et al.
Pubblicazione: (2026)

The Hard Positive Truth about Vision-Language Compositionality
di: Kamath, Amita, et al.
Pubblicazione: (2024)

CLAIM: Mitigating Multilingual Object Hallucination in Large Vision-Language Models with Cross-Lingual Attention Intervention
di: Ye, Zekai, et al.
Pubblicazione: (2025)

Enhanced Language Model Truthfulness with Learnable Intervention and Uncertainty Expression
di: Bayat, Farima Fatahi, et al.
Pubblicazione: (2024)

IUQ: Interrogative Uncertainty Quantification for Long-Form Large Language Model Generation
di: Fan, Haozhi, et al.
Pubblicazione: (2026)

See Fair, Speak Truth: Equitable Attention Improves Grounding and Reduces Hallucination in Vision-Language Alignment
di: Azeez, Mohammad Anas, et al.
Pubblicazione: (2026)

ConU: Conformal Uncertainty in Large Language Models with Correctness Coverage Guarantees
di: Wang, Zhiyuan, et al.
Pubblicazione: (2024)

Truth Neurons
di: Li, Haohang, et al.
Pubblicazione: (2025)

Energy-Guided Decoding for Object Hallucination Mitigation
di: Liu, Xixi, et al.
Pubblicazione: (2025)

CAI: Caption-Sensitive Attention Intervention for Mitigating Object Hallucination in Large Vision-Language Models
di: Li, Qiming, et al.
Pubblicazione: (2025)

The Facade of Truth: Uncovering and Mitigating LLM Susceptibility to Deceptive Evidence
di: Wan, Herun, et al.
Pubblicazione: (2026)

Pathological Truth Bias in Vision-Language Models
di: Thube, Yash
Pubblicazione: (2025)

TruthStance: An Annotated Dataset of Conversations on Truth Social
di: Ameen, Fathima, et al.
Pubblicazione: (2026)

Mitigating Object Hallucinations via Sentence-Level Early Intervention
di: Peng, Shangpin, et al.
Pubblicazione: (2025)

The Architecture of Truth
di: Kent, Robert E.
Pubblicazione: (2024)

Truth Factors
di: Kent, Robert E.
Pubblicazione: (2024)