Cover Image

Understanding Multimodal LLMs: the Mechanistic Interpretability of Llava in Visual Question Answering

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Yu, Zeping, Ananiadou, Sophia
Format:	Preprint
Published:	2024
Subjects:	Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Understanding and Mitigating Gender Bias in LLMs via Interpretable Neuron Editing
by: Yu, Zeping, et al.
Published: (2025)

Locate-then-Merge: Neuron-Level Parameter Fusion for Mitigating Catastrophic Forgetting in Multimodal LLMs
by: Yu, Zeping, et al.
Published: (2025)

Interpreting Arithmetic Mechanism in Large Language Models through Comparative Neuron Analysis
by: Yu, Zeping, et al.
Published: (2024)

Back Attention: Understanding and Enhancing Multi-Hop Reasoning in Large Language Models
by: Yu, Zeping, et al.
Published: (2025)

How do Large Language Models Learn In-Context? Query and Key Matrices of In-Context Heads are Two Towers for Metric Learning
by: Yu, Zeping, et al.
Published: (2024)

Neuron-Level Knowledge Attribution in Large Language Models
by: Yu, Zeping, et al.
Published: (2023)

Emotion Detection for Misinformation: A Review
by: Liu, Zhiwei, et al.
Published: (2023)

Break the Checkbox: Challenging Closed-Style Evaluations of Cultural Alignment in LLMs
by: Kabir, Mohsinul, et al.
Published: (2025)

MMAFFBen: A Multilingual and Multimodal Affective Analysis Benchmark for Evaluating LLMs and VLMs
by: Liu, Zhiwei, et al.
Published: (2025)

Towards Perceiving Small Visual Details in Zero-shot Visual Question Answering with Multimodal LLMs
by: Zhang, Jiarui, et al.
Published: (2023)

Efficient Multimodal Planning Agent for Visual Question-Answering
by: Chen, Zhuo, et al.
Published: (2026)

On Mechanistic Circuits for Extractive Question-Answering
by: Basu, Samyadeep, et al.
Published: (2025)

Intrinsic Subgraph Generation for Interpretable Graph based Visual Question Answering
by: Tilli, Pascal, et al.
Published: (2024)

Discrete Subgraph Sampling for Interpretable Graph based Visual Question Answering
by: Tilli, Pascal, et al.
Published: (2024)

Multimodal Reranking for Knowledge-Intensive Visual Question Answering
by: Wen, Haoyang, et al.
Published: (2024)

Multimodal Commonsense Knowledge Distillation for Visual Question Answering
by: Yang, Shuo, et al.
Published: (2024)

ProMQA: Question Answering Dataset for Multimodal Procedural Activity Understanding
by: Hasegawa, Kimihiro, et al.
Published: (2024)

Augmenting Multimodal LLMs with Self-Reflective Tokens for Knowledge-based Visual Question Answering
by: Cocchi, Federico, et al.
Published: (2024)

Do LLMs Understand Romanian Driving Laws? A Study on Multimodal and Fine-Tuned Question Answering
by: Barbu, Eduard, et al.
Published: (2025)

Multimodal Integration of Human-Like Attention in Visual Question Answering
by: Sood, Ekta, et al.
Published: (2021)

Coal Mining Question Answering with LLMs
by: Rivera, Antonio Carlos, et al.
Published: (2024)

MAGIC-VQA: Multimodal And Grounded Inference with Commonsense Knowledge for Visual Question Answering
by: Yang, Shuo, et al.
Published: (2025)

I've got the "Answer"! Interpretation of LLMs Hidden States in Question Answering
by: Goloviznina, Valeriya, et al.
Published: (2024)

Towards Interpretable Mental Health Analysis with Large Language Models
by: Yang, Kailai, et al.
Published: (2023)

Factual consistency evaluation of summarization in the Era of large language models
by: Luo, Zheheng, et al.
Published: (2024)

The Lay Person's Guide to Biomedicine: Orchestrating Large Language Models
by: Luo, Zheheng, et al.
Published: (2024)

Disentangled VAD Representations via a Variational Framework for Political Stance Detection
by: Xu, Beiyu, et al.
Published: (2025)

Design as Desired: Utilizing Visual Question Answering for Multimodal Pre-training
by: Su, Tongkun, et al.
Published: (2024)

EmoLLMs: A Series of Emotional Large Language Models and Annotation Tools for Comprehensive Affective Analysis
by: Liu, Zhiwei, et al.
Published: (2024)

Dynamic Clue Bottlenecks: Towards Interpretable-by-Design Visual Question Answering
by: Fu, Xingyu, et al.
Published: (2023)

Selectively Answering Visual Questions
by: Eisenschlos, Julian Martin, et al.
Published: (2024)

Identifying and Answering Questions with False Assumptions: An Interpretable Approach
by: Wang, Zijie, et al.
Published: (2025)

Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models
by: Zhang, Hengyuan, et al.
Published: (2026)

MentaLLaMA: Interpretable Mental Health Analysis on Social Media with Large Language Models
by: Yang, Kailai, et al.
Published: (2023)

Implicit Graph, Explicit Retrieval: Towards Efficient and Interpretable Long-horizon Memory for Large Language Models
by: Zhang, Xin, et al.
Published: (2026)

Natural Language Understanding and Inference with MLLM in Visual Question Answering: A Survey
by: Kuang, Jiayi, et al.
Published: (2024)

How Good LLMs Are at Answering Bangla Medical Visual Questions? Dataset and Benchmarking
by: Ahmed, Rafid, et al.
Published: (2026)

Interpretable LLM-based Table Question Answering
by: Nguyen, Giang, et al.
Published: (2024)

On the Calibration of Multilingual Question Answering LLMs
by: Yang, Yahan, et al.
Published: (2023)

EVJVQA Challenge: Multilingual Visual Question Answering
by: Nguyen, Ngan Luu-Thuy, et al.
Published: (2023)