Image de couverture de livre

Lookback Lens: Detecting and Mitigating Contextual Hallucinations in Large Language Models Using Only Attention Maps

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Chuang, Yung-Sung, Qiu, Linlu, Hsieh, Cheng-Yu, Krishna, Ranjay, Kim, Yoon, Glass, James
Format:	Preprint
Publié:	2024
Sujets:	Computation and Language Artificial Intelligence Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

DoLa: Decoding by Contrasting Layers Improves Factuality in Large Language Models
par: Chuang, Yung-Sung, et autres
Publié: (2023)

Found in the Middle: Calibrating Positional Attention Bias Improves Long Context Utilization
par: Hsieh, Cheng-Yu, et autres
Publié: (2024)

Don't "Overthink" Passage Reranking: Is Reasoning Truly Necessary?
par: Jedidi, Nour, et autres
Publié: (2025)

Zero-Shot Dense Retrieval with Embeddings from Relevance Feedback
par: Jedidi, Nour, et autres
Publié: (2024)

Gradient-guided Attention Map Editing: Towards Efficient Contextual Hallucination Mitigation
par: Wang, Yu, et autres
Publié: (2025)

Devils in Middle Layers of Large Vision-Language Models: Interpreting, Detecting and Mitigating Object Hallucinations via Attention Lens
par: Jiang, Zhangqi, et autres
Publié: (2024)

Natural Language Embedded Programs for Hybrid Language Symbolic Reasoning
par: Zhang, Tianhua, et autres
Publié: (2023)

Bayesian Teaching Enables Probabilistic Reasoning in Large Language Models
par: Qiu, Linlu, et autres
Publié: (2025)

MAP: Mitigating Hallucinations in Large Vision-Language Models with Map-Level Attention Processing
par: Li, Chenxi, et autres
Publié: (2025)

The Hard Positive Truth about Vision-Language Compositionality
par: Kamath, Amita, et autres
Publié: (2024)

Curiosity-driven Red-teaming for Large Language Models
par: Hong, Zhang-Wei, et autres
Publié: (2024)

Learning to Attribute with Attention
par: Cohen-Wang, Benjamin, et autres
Publié: (2025)

Visual Attention Drifts,but Anchors Hold:Mitigating Hallucination in Multimodal Large Language Models via Cross-Layer Visual Anchors
par: Yang, Chengxu, et autres
Publié: (2026)

Hallucination Detection and Mitigation in Large Language Models
par: Pesaranghader, Ahmad, et autres
Publié: (2026)

Modality Bias in LVLMs: Analyzing and Mitigating Object Hallucination via Attention Lens
par: Zheng, Haohan, et autres
Publié: (2025)

Implicit Representations of Grammaticality in Language Models
par: Wang, Yingshan Susan, et autres
Publié: (2026)

Detecting Contextual Hallucinations in LLMs with Frequency-Aware Attention
par: Qi, Siya, et autres
Publié: (2026)

Beyond Logit Lens: Contextual Embeddings for Robust Hallucination Detection & Grounding in VLMs
par: Phukan, Anirudh, et autres
Publié: (2024)

Hallucination Detection in LLMs Using Spectral Features of Attention Maps
par: Binkowski, Jakub, et autres
Publié: (2025)

Segmentation-Based Attention Entropy: Detecting and Mitigating Object Hallucinations in Large Vision-Language Models
par: Song, Jiale, et autres
Publié: (2026)

Ablate-to-Validate: Are Vision-Language Models Really Using Continuous Thought Tokens?
par: Zhang, Tianyi, et autres
Publié: (2026)

Mirage-in-the-Eyes: Hallucination Attack on Multi-modal Large Language Models with Only Attention Sink
par: Wang
Publié: (2025)

Mirage in the Eyes: Hallucination Attack on Multi-modal Large Language Models with Only Attention Sink
par: Wang, Yining, et autres
Publié: (2025)

Dynamic Attention-Guided Context Decoding for Mitigating Context Faithfulness Hallucinations in Large Language Models
par: Huang, Yanwen, et autres
Publié: (2025)

Language Models use Lookbacks to Track Beliefs
par: Prakash, Nikhil, et autres
Publié: (2025)

Analyzing and Mitigating Object Hallucination in Large Vision-Language Models
par: Zhou, Yiyang, et autres
Publié: (2023)

Lookback Prophet Inequalities
par: Benomar, Ziyad, et autres
Publié: (2024)

Language-Agnostic Suicidal Risk Detection Using Large Language Models
par: Kim, June-Woo, et autres
Publié: (2025)

Detecting Hallucinations in SpeechLLMs at Inference Time Using Attention Maps
par: Waldendorf, Jonas, et autres
Publié: (2026)

FocalLens: Instruction Tuning Enables Zero-Shot Conditional Image Representations
par: Hsieh, Cheng-Yu, et autres
Publié: (2025)

HICD: Hallucination-Inducing via Attention Dispersion for Contrastive Decoding to Mitigate Hallucinations in Large Language Models
par: Jiang, Xinyan, et autres
Publié: (2025)

On the Same Wavelength? Evaluating Pragmatic Reasoning in Language Models across Broad Concepts
par: Qiu, Linlu, et autres
Publié: (2025)

Mitigating Multilingual Hallucination in Large Vision-Language Models
par: Qu, Xiaoye, et autres
Publié: (2024)

Mitigating Object Hallucinations in Large Vision-Language Models via Attention Calibration
par: Zhu, Younan, et autres
Publié: (2025)

Mitigating Hallucination in Large Vision-Language Models via Adaptive Attention Calibration
par: Fazli, Mehrdad, et autres
Publié: (2025)

Instruction-Aligned Visual Attention for Mitigating Hallucinations in Large Vision-Language Models
par: Li, Bin, et autres
Publié: (2025)

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

Attention Hijackers: Detect and Disentangle Attention Hijacking in LVLMs for Hallucination Mitigation
par: Chen, Beitao, et autres
Publié: (2025)

EEND-SAA: Enrollment-Less Main Speaker Voice Activity Detection Using Self-Attention Attractors
par: Wu, Wen-Yung, et autres
Publié: (2025)

Iterated Learning Improves Compositionality in Large Vision-Language Models
par: Zheng, Chenhao, et autres
Publié: (2024)