Cover Image

Difficult Task Yes but Simple Task No: Unveiling the Laziness in Multimodal LLMs

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zhao, Sihang, Yuan, Youliang, Tang, Xiaoying, He, Pinjia
Format:	Preprint
Published:	2024
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

SHAPE: Unifying Safety, Helpfulness and Pedagogy for Educational LLMs
by: Zhao, Sihang, et al.
Published: (2026)

Can't See the Forest for the Trees: Benchmarking Multimodal Safety Awareness for Multimodal LLMs
by: Wang, Wenxuan, et al.
Published: (2025)

Towards Evaluating Proactive Risk Awareness of Multimodal Language Models
by: Yuan, Youliang, et al.
Published: (2025)

Refuse Whenever You Feel Unsafe: Improving Safety in LLMs via Decoupled Refusal Training
by: Yuan, Youliang, et al.
Published: (2024)

PaSBench-Video: A Streaming Video Benchmark for Proactive Safety Warning
by: Zhao, Yusong, et al.
Published: (2026)

Frontier LLMs Still Struggle with Simple Reasoning Tasks
by: Malek, Alan, et al.
Published: (2025)

Yes-MT's Submission to the Low-Resource Indic Language Translation Shared Task in WMT 2024
by: Bhaskar, Yash, et al.
Published: (2025)

Shorten After You're Right: Lazy Length Penalties for Reasoning RL
by: Yuan, Danlong, et al.
Published: (2025)

Can They Dixit? Yes they Can! Dixit as a Playground for Multimodal Language Model Capabilities
by: Balepur, Nishant, et al.
Published: (2025)

Unlocking the Power of Multi-Agent LLM for Reasoning: From Lazy Agents to Deliberation
by: Zhang, Zhiwei, et al.
Published: (2025)

SATA: A Paradigm for LLM Jailbreak via Simple Assistive Task Linkage
by: Dong, Xiaoning, et al.
Published: (2024)

How Multimodal LLMs Solve Image Tasks: A Lens on Visual Grounding, Task Reasoning, and Answer Decoding
by: Yu, Zhuoran, et al.
Published: (2025)

LogicAsker: Evaluating and Improving the Logical Reasoning Ability of Large Language Models
by: Wan, Yuxuan, et al.
Published: (2024)

Is the Pope Catholic? Yes, the Pope is Catholic. Generative Evaluation of Non-Literal Intent Resolution in LLMs
by: Yerukola, Akhila, et al.
Published: (2024)

Finding the Translation Switch: Discovering and Exploiting the Task-Initiation Features in LLMs
by: Wu, Xinwei, et al.
Published: (2026)

Autonomous Evaluation of LLMs for Truth Maintenance and Reasoning Tasks
by: Karia, Rushang, et al.
Published: (2024)

Are Long-LLMs A Necessity For Long-Context Tasks?
by: Qian, Hongjin, et al.
Published: (2024)

Position: Avoid Overstretching LLMs for every Enterprise Task
by: Singh, Kuldeep, et al.
Published: (2026)

ArgBench: Benchmarking LLMs on Computational Argumentation Tasks
by: Ajjour, Yamen, et al.
Published: (2026)

TSEmbed: Unlocking Task Scaling in Universal Multimodal Embeddings
by: Wu, Yebo, et al.
Published: (2026)

Unveiling Divergent Inductive Biases of LLMs on Temporal Data
by: Kishore, Sindhu, et al.
Published: (2024)

Active Task Disambiguation with LLMs
by: Kobalczyk, Katarzyna, et al.
Published: (2025)

Multi-Task Learning with LLMs for Implicit Sentiment Analysis: Data-level and Task-level Automatic Weight Learning
by: Lai, Wenna, et al.
Published: (2024)

TaskBench: Benchmarking Large Language Models for Task Automation
by: Shen, Yongliang, et al.
Published: (2023)

CulturALL: Benchmarking Multilingual and Multicultural Competence of LLMs on Grounded Tasks
by: Lin, Peiqin, et al.
Published: (2026)

Hidden in the Haystack: Smaller Needles are More Difficult for LLMs to Find
by: Bianchi, Owen, et al.
Published: (2025)

Evaluating the Evaluator: Measuring LLMs' Adherence to Task Evaluation Instructions
by: Murugadoss, Bhuvanashree, et al.
Published: (2024)

Identifying Good and Bad Neurons for Task-Level Controllable LLMs
by: Li, Wenjie, et al.
Published: (2026)

Improving Task Diversity in Label Efficient Supervised Finetuning of LLMs
by: Arabelly, Abhinav, et al.
Published: (2025)

Can LLMs Generate High-Quality Task-Specific Conversations?
by: Li, Shengqi, et al.
Published: (2025)

Magis-Bench: Evaluating LLMs on Magistrate-Level Legal Tasks
by: Pires, Ramon, et al.
Published: (2026)

Incomplete Tasks Induce Shutdown Resistance in Some Frontier LLMs
by: Schlatter, Jeremy, et al.
Published: (2025)

PsychiatryBench: A Multi-Task Benchmark for LLMs in Psychiatry
by: Fouda, Aya E., et al.
Published: (2025)

SELT: Self-Evaluation Tree Search for LLMs with Task Decomposition
by: Wu, Mengsong, et al.
Published: (2025)

OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments
by: Xie, Tianbao, et al.
Published: (2024)

NYT-Connections: A Deceptively Simple Text Classification Task that Stumps System-1 Thinkers
by: Lopez, Angel Yahir Loredo, et al.
Published: (2024)

Whitening Not Recommended for Classification Tasks in LLMs
by: Forooghi, Ali, et al.
Published: (2024)

AnyTaskTune: Advanced Domain-Specific Solutions through Task-Fine-Tuning
by: Cui, Jiaxi, et al.
Published: (2024)

UoR-NCL at SemEval-2025 Task 1: Using Generative LLMs and CLIP Models for Multilingual Multimodal Idiomaticity Representation
by: Markchom, Thanet, et al.
Published: (2025)

Structured Thinking Matters: Improving LLMs Generalization in Causal Inference Tasks
by: Sun, Wentao, et al.
Published: (2025)