Imagen de Portada

Same Answer, Different Representations: Hidden instability in VLMs

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Wani, Farooq Ahmad, Suglia, Alessandro, Saxena, Rohit, Gema, Aryo Pradipta, Kwan, Wai-Chung, Barez, Fazl, Bucarelli, Maria Sofia, Silvestri, Fabrizio, Minervini, Pasquale
Formato:	Preprint
Publicado:	2026
Materias:	Artificial Intelligence Computer Vision and Pattern Recognition
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Lost in Time: Clock and Calendar Understanding Challenges in Multimodal LLMs
por: Saxena, Rohit, et al.
Publicado: (2025)

SCOPE: Self-Play via Co-Evolving Policies for Open-Ended Tasks
por: Kwan, Wai-Chung, et al.
Publicado: (2026)

Learning with Noisy Labels through Learnable Weighting and Centroid Similarity
por: Wani, Farooq Ahmad, et al.
Publicado: (2023)

VLM-RobustBench: A Comprehensive Benchmark for Robustness of Vision-Language Models
por: Saxena, Rohit, et al.
Publicado: (2026)

PISA: Prioritized Invariant Subgraph Aggregation
por: Ghasemi, Ali, et al.
Publicado: (2025)

Subtract the Corruption: Training-Data-Free Corrective Machine Unlearning using Task Arithmetic
por: Mozafari, Mostafa, et al.
Publicado: (2025)

Do Composed Image Retrieval Benchmarks Require Multimodal Composition?
por: Attimonelli, Matteo, et al.
Publicado: (2026)

Edinburgh Clinical NLP at SemEval-2024 Task 2: Fine-tune your model unless you have access to GPT-4
por: Gema, Aryo Pradipta, et al.
Publicado: (2024)

Parameter-Efficient Fine-Tuning of LLaMA for the Clinical Domain
por: Gema, Aryo Pradipta, et al.
Publicado: (2023)

Energy Guided smoothness to improve Robustness in Graph Classification
por: Wani, Farooq Ahmad, et al.
Publicado: (2024)

Same Question, Different Words: A Latent Adversarial Framework for Prompt Robustness
por: Fu, Tingchen, et al.
Publicado: (2025)

Edinburgh Clinical NLP at MEDIQA-CORR 2024: Guiding Large Language Models with Hints
por: Gema, Aryo Pradipta, et al.
Publicado: (2024)

Query Circuits: Explaining How Language Models Answer User Prompts
por: Wu, Tung-Yu, et al.
Publicado: (2025)

Self-Training Large Language Models for Tool-Use Without Demonstrations
por: Luo, Ne, et al.
Publicado: (2025)

GRADA: Graph-based Reranking against Adversarial Documents Attack
por: Zheng, Jingjie, et al.
Publicado: (2025)

Noiser: Bounded Input Perturbations for Attributing Large Language Models
por: Madani, Mohammad Reza Ghasemi, et al.
Publicado: (2025)

Analyzing LLM Instruction Optimization for Tabular Fact Verification
por: Du, Xiaotang, et al.
Publicado: (2026)

PiCSAR: Probabilistic Confidence Selection And Ranking for Reasoning Chains
por: Leang, Joshua Ong Jun, et al.
Publicado: (2025)

PosterSum: A Multimodal Benchmark for Scientific Poster Summarization
por: Saxena, Rohit, et al.
Publicado: (2025)

The Hallucinations Leaderboard -- An Open Effort to Measure Hallucinations in Large Language Models
por: Hong, Giwon, et al.
Publicado: (2024)

DeCoRe: Decoding by Contrasting Retrieval Heads to Mitigate Hallucinations
por: Gema, Aryo Pradipta, et al.
Publicado: (2024)

An Analysis of Decoding Methods for LLM-based Agents for Faithful Multi-Hop Question Answering
por: Murphy, Alexander, et al.
Publicado: (2025)

Towards Understanding Subliminal Learning: When and How Hidden Biases Transfer
por: Schrodi, Simon, et al.
Publicado: (2025)

SafetyNet: Detecting Harmful Outputs in LLMs by Modeling and Monitoring Deceptive Behaviors
por: Chaudhary, Maheep, et al.
Publicado: (2025)

Understanding Addition in Transformers
por: Quirke, Philip, et al.
Publicado: (2023)

Analysing the Residual Stream of Language Models Under Knowledge Conflicts
por: Zhao, Yu, et al.
Publicado: (2024)

Steering Knowledge Selection Behaviours in LLMs via SAE-Based Representation Engineering
por: Zhao, Yu, et al.
Publicado: (2024)

Trust Me, I'm Wrong: LLMs Hallucinate with Certainty Despite Knowing the Answer
por: Simhi, Adi, et al.
Publicado: (2025)

$\nabla τ$: Gradient-based and Task-Agnostic machine Unlearning
por: Trippa, Daniel, et al.
Publicado: (2024)

Select, Label, Evaluate: Active Testing in NLP
por: Purificato, Antonio, et al.
Publicado: (2026)

Link Prediction with Physics-Inspired Graph Neural Networks
por: Di Francesco, Andrea Giuseppe, et al.
Publicado: (2024)

CoMAT: Chain of Mathematically Annotated Thought Improves Mathematical Reasoning
por: Leang, Joshua Ong Jun, et al.
Publicado: (2024)

Scalpel vs. Hammer: GRPO Amplifies Existing Capabilities, SFT Replaces Them
por: Rajani, Neel, et al.
Publicado: (2025)

Exploring Early Symptom Experiences and Self- Management Coping Strategies of Kidney Transplant Patients
por: Wani, Fazl Ur Rahman
Publicado: (2026)

Rethinking AI Cultural Alignment
por: Bravansky, Michal, et al.
Publicado: (2025)

Towards Interpretable Sequence Continuation: Analyzing Shared Circuits in Large Language Models
por: Lan, Michael, et al.
Publicado: (2023)

Understanding Addition and Subtraction in Transformers
por: Quirke, Philip, et al.
Publicado: (2024)

Enhancing Long Document Long Form Summarisation with Self-Planning
por: Du, Xiaotang, et al.
Publicado: (2025)

Recursive Think-Answer Process for LLMs and VLMs
por: Lee, Byung-Kwan, et al.
Publicado: (2026)

A topological description of loss surfaces based on Betti Numbers
por: Bucarelli, Maria Sofia, et al.
Publicado: (2024)