Cover Image

Saying the Unsaid: Revealing the Hidden Language of Multimodal Systems Through Telephone Games

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zhao, Juntu, Zhang, Jialing, Li, Chongxuan, Wang, Dequan
Format:	Preprint
Published:	2025
Subjects:	Computation and Language Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Lost in Translation: Latent Concept Misalignment in Text-to-Image Diffusion Models
by: Zhao, Juntu, et al.
Published: (2024)

MAC: A Live Benchmark for Multimodal Large Language Models in Scientific Understanding
by: Jiang, Mohan, et al.
Published: (2025)

Chip-Tuning: Classify Before Language Models Say
by: Zhu, Fangwei, et al.
Published: (2024)

Reasoning and the Trusting Behavior of DeepSeek and GPT: An Experiment Revealing Hidden Fault Lines in Large Language Models
by: Li, Rubing, et al.
Published: (2025)

ReFusion: A Diffusion Large Language Model with Parallel Autoregressive Decoding
by: Li, Jia-Nan, et al.
Published: (2025)

MLLM-Microscope: Unlocking Hidden Structure Within Multimodal Large Language Models
by: Mussabayev, Ravil, et al.
Published: (2026)

DatasetResearch: Benchmarking Agent Systems for Demand-Driven Dataset Discovery
by: Li, Keyu, et al.
Published: (2025)

When Language Overrules: Revealing Text Dominance in Multimodal Large Language Models
by: Wu, Huyu, et al.
Published: (2025)

LLM as a Broken Telephone: Iterative Generation Distorts Information
by: Mohamed, Amr, et al.
Published: (2025)

Who is in the Spotlight: The Hidden Bias Undermining Multimodal Retrieval-Augmented Generation
by: Yao, Jiayu, et al.
Published: (2025)

RepreGuard: Detecting LLM-Generated Text by Revealing Hidden Representation Patterns
by: Chen, Xin, et al.
Published: (2025)

Jailbreaking Multimodal Large Language Models via Shuffle Inconsistency
by: Zhao, Shiji, et al.
Published: (2025)

UltraLLaDA: Scaling the Context Length to 128K for Diffusion Large Language Models
by: He, Guangxin, et al.
Published: (2025)

Honest AI: Fine-Tuning "Small" Language Models to Say "I Don't Know", and Reducing Hallucination in RAG
by: Chen, Xinxi, et al.
Published: (2024)

Revealing the Barriers of Language Agents in Planning
by: Xie, Jian, et al.
Published: (2024)

The Art of Saying No: Contextual Noncompliance in Language Models
by: Brahman, Faeze, et al.
Published: (2024)

GameTraversalBenchmark: Evaluating Planning Abilities Of Large Language Models Through Traversing 2D Game Maps
by: Nasir, Muhammad Umair, et al.
Published: (2024)

Variational Reasoning for Language Models
by: Zhou, Xiangxin, et al.
Published: (2025)

Induced Numerical Instability: Hidden Costs in Multimodal Large Language Models
by: Wong, Wai Tuck, et al.
Published: (2026)

SMS Spam Detection and Classification to Combat Abuse in Telephone Networks Using Natural Language Processing
by: Oyeyemi, Dare Azeez, et al.
Published: (2024)

Mitigating Hidden Confounding by Progressive Confounder Imputation via Large Language Models
by: Yang, Hao, et al.
Published: (2025)

The Model Says Walk: How Surface Heuristics Override Implicit Constraints in LLM Reasoning
by: Li, Yubo, et al.
Published: (2026)

Component-Level Lesioning of Language Models Reveals Clinically Aligned Aphasia Phenotypes
by: Wang, Yifan, et al.
Published: (2026)

"Hunt Takes Hare": Theming Games Through Game-Word Vector Translation
by: Younès, Rabii, et al.
Published: (2024)

See or Say Graphs: Agent-Driven Scalable Graph Structure Understanding with Vision-Language Models
by: Han, Shuo, et al.
Published: (2025)

Say It Differently: Linguistic Styles as Jailbreak Vectors
by: Panda, Srikant, et al.
Published: (2025)

Explanation Bias is a Product: Revealing the Hidden Lexical and Position Preferences in Post-Hoc Feature Attribution
by: Kamp, Jonathan, et al.
Published: (2025)

The Hidden Structure -- Improving Legal Document Understanding Through Explicit Text Formatting
by: Braun, Christian, et al.
Published: (2025)

Using Game Play to Investigate Multimodal and Conversational Grounding in Large Multimodal Models
by: Hakimov, Sherzod, et al.
Published: (2024)

Saying More Than They Know: A Framework for Quantifying Epistemic-Rhetorical Miscalibration in Large Language Models
by: Bakhshi, Asim D.
Published: (2026)

The Image Reconstruction Game: Drawing Common Ground Through Iterative Multimodal Dialogue
by: Hakimov, Sherzod, et al.
Published: (2026)

AI Telephone Surveying: Automating Quantitative Data Collection with an AI Interviewer
by: Leybzon, Danny D., et al.
Published: (2025)

Say Anything but This: When Tokenizer Betrays Reasoning in LLMs
by: Ayoobi, Navid, et al.
Published: (2026)

Finding and Reactivating Post-Trained LLMs' Hidden Safety Mechanisms
by: Li, Mingjie, et al.
Published: (2026)

From Leaky Thoughts to Private Reasoning: Controlling What LRMs Say to Themselves
by: Puerto, Haritz, et al.
Published: (2026)

Counterfactual Evaluation Reveals Hidden Capability Profiles in Clinical LLMs and Agents
by: Turk, Matt
Published: (2026)

Multimodal Reasoning with Multimodal Knowledge Graph
by: Lee, Junlin, et al.
Published: (2024)

Playing Language Game with LLMs Leads to Jailbreaking
by: Peng, Yu, et al.
Published: (2024)

Circumventing Safety Alignment in Large Language Models Through Embedding Space Toxicity Attenuation
by: Zhang, Zhibo, et al.
Published: (2025)

Revealing the Intrinsic Ethical Vulnerability of Aligned Large Language Models
by: Lian, Jiawei, et al.
Published: (2025)