Copertina

Vision-Language Models Align with Human Neural Representations in Concept Processing

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Bavaresco, Anna, Kloots, Marianne de Heer, Pezzelle, Sandro, Fernández, Raquel
Natura:	Preprint
Pubblicazione:	2024
Soggetti:	Computation and Language
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Human-like Linguistic Biases in Neural Speech Models: Phonetic Categorization and Phonotactic Constraints in Wav2Vec2.0
di: Kloots, Marianne de Heer, et al.
Pubblicazione: (2024)

Perception of Phonological Assimilation by Neural Speech Recognition Models
di: Pouw, Charlotte, et al.
Pubblicazione: (2024)

The Curious Case of Visual Grounding: Different Effects for Speech- and Text-based Language Encoders
di: Sauter, Adrian, et al.
Pubblicazione: (2025)

Describing Images $\textit{Fast and Slow}$: Quantifying and Predicting the Variation in Human Signals during Visuo-Linguistic Processes
di: Takmaz, Ece, et al.
Pubblicazione: (2024)

Experiential Semantic Information and Brain Alignment: Are Multimodal Models Better than Language Models?
di: Bavaresco, Anna, et al.
Pubblicazione: (2025)

The BLA Benchmark: Investigating Basic Language Abilities of Pre-Trained Multimodal Models
di: Chen, Xinyi, et al.
Pubblicazione: (2023)

Linguists should learn to love speech-based deep learning models
di: Kloots, Marianne de Heer, et al.
Pubblicazione: (2025)

How Language Models Conflate Logical Validity with Plausibility: A Representational Analysis of Content Effects
di: Bertolazzi, Leonardo, et al.
Pubblicazione: (2025)

Beyond Divergent Creativity: A Human-Based Evaluation of Creativity in Large Language Models
di: Nakajima, Kumiko, et al.
Pubblicazione: (2026)

Natural Language Generation from Visual Events: State-of-the-Art and Key Open Questions
di: Surikuchi, Aditya K, et al.
Pubblicazione: (2025)

Where is the multimodal goal post? On the Ability of Foundation Models to Recognize Contextually Important Moments
di: Surikuchi, Aditya K, et al.
Pubblicazione: (2026)

Do Pre-Trained Language Models Detect and Understand Semantic Underspecification? Ask the DUST!
di: Wildenburg, Frank, et al.
Pubblicazione: (2024)

Naming, Describing, and Quantifying Visual Objects in Humans and LLMs
di: Testoni, Alberto, et al.
Pubblicazione: (2024)

Not (yet) the whole story: Evaluating Visual Storytelling Requires More than Measuring Coherence, Grounding, and Repetition
di: Surikuchi, Aditya K, et al.
Pubblicazione: (2024)

Tracking the emergence of linguistic structure in self-supervised models learning from speech
di: Kloots, Marianne de Heer, et al.
Pubblicazione: (2026)

What do self-supervised speech models know about Dutch? Analyzing advantages of language-specific pre-training
di: Kloots, Marianne de Heer, et al.
Pubblicazione: (2025)

Who is the richest club in the championship? Detecting and Rewriting Underspecified Questions Improve QA Performance
di: Huang, Yunchong, et al.
Pubblicazione: (2026)

They want to pretend not to understand: The Limits of Current LLMs in Interpreting Implicit Content of Political Discourse
di: Paci, Walter, et al.
Pubblicazione: (2025)

Exploring bat song syllable representations in self-supervised audio encoders
di: Kloots, Marianne de Heer, et al.
Pubblicazione: (2024)

Have Faith in Faithfulness: Going Beyond Circuit Overlap When Finding Model Mechanisms
di: Hanna, Michael, et al.
Pubblicazione: (2024)

Are formal and functional linguistic mechanisms dissociated in language models?
di: Hanna, Michael, et al.
Pubblicazione: (2025)

Aligning Large Language Models with Human Preferences through Representation Engineering
di: Liu, Wenhao, et al.
Pubblicazione: (2023)

LLMs instead of Human Judges? A Large Scale Empirical Study across 20 NLP Evaluation Tasks
di: Bavaresco, Anna, et al.
Pubblicazione: (2024)

Don't Buy it! Reassessing the Ad Understanding Abilities of Contrastive Multimodal Models
di: Bavaresco, A., et al.
Pubblicazione: (2024)

Is my model perplexed for the right reason? Contrasting LLMs' Benchmark Behavior with Token-Level Perplexity
di: Prins, Zoë, et al.
Pubblicazione: (2026)

Vision-Language Models Struggle to Align Entities across Modalities
di: Alonso, Iñigo, et al.
Pubblicazione: (2025)

Steering Risk Preferences in Large Language Models by Aligning Behavioral and Neural Representations
di: Zhu, Jian-Qiao, et al.
Pubblicazione: (2025)

Linear Representations of Hierarchical Concepts in Language Models
di: Sakata, Masaki, et al.
Pubblicazione: (2026)

Investigating Human-Aligned Large Language Model Uncertainty
di: Moore, Kyle, et al.
Pubblicazione: (2025)

Improving Multilingual Language Models by Aligning Representations through Steering
di: Mahmoud, Omar, et al.
Pubblicazione: (2025)

Aligning Neural Machine Translation Models: Human Feedback in Training and Inference
di: Ramos, Miguel Moura, et al.
Pubblicazione: (2023)

Large Concept Models: Language Modeling in a Sentence Representation Space
di: LCM team, et al.
Pubblicazione: (2024)

DRESS: Instructing Large Vision-Language Models to Align and Interact with Humans via Natural Language Feedback
di: Chen, Yangyi, et al.
Pubblicazione: (2023)

Concept-based Analysis of Neural Networks via Vision-Language Models
di: Mangal, Ravi, et al.
Pubblicazione: (2024)

If CLIP Could Talk: Understanding Vision-Language Model Representations Through Their Preferred Concept Descriptions
di: Esfandiarpoor, Reza, et al.
Pubblicazione: (2024)

Fairer Preferences Elicit Improved Human-Aligned Large Language Model Judgments
di: Zhou, Han, et al.
Pubblicazione: (2024)

AlignX: Advancing Multilingual Large Language Models with Multilingual Representation Alignment
di: Bu, Mengyu, et al.
Pubblicazione: (2025)

Aligning Language Models with Human Preferences via a Bayesian Approach
di: Wang, Jiashuo, et al.
Pubblicazione: (2023)

Semantic Representation Attack against Aligned Large Language Models
di: Lian, Jiawei, et al.
Pubblicazione: (2025)

AlignSAE: Concept-Aligned Sparse Autoencoders
di: Yang, Minglai, et al.
Pubblicazione: (2025)