Copertina

Investigating Concept Alignment Using Implausible Category Members

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Rane, Sunayana, Lake, Brenden M., Griffiths, Thomas L.
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Concept Alignment
di: Rane, Sunayana, et al.
Pubblicazione: (2024)

The Reasonable Person Standard for AI
di: Rane, Sunayana
Pubblicazione: (2024)

CoLLEGe: Concept Embedding Generation for Large Language Models
di: Teehan, Ryan, et al.
Pubblicazione: (2024)

Whither symbols in the era of advanced neural networks?
di: Griffiths, Thomas L., et al.
Pubblicazione: (2025)

Are they human? Detecting large language models by probing human memory constraints
di: Schug, Simon, et al.
Pubblicazione: (2026)

Overcoming classic challenges for artificial neural networks by providing incentives and practice
di: Irie, Kazuki, et al.
Pubblicazione: (2024)

SAGE-Eval: Evaluating LLMs for Systematic Generalizations of Safety Facts
di: Yueh-Han, Chen, et al.
Pubblicazione: (2025)

Comparing Abstraction in Humans and Large Language Models Using Multimodal Serial Reproduction
di: Kumar, Sreejan, et al.
Pubblicazione: (2024)

An explainable transformer circuit for compositional generalization
di: Tang, Cheng, et al.
Pubblicazione: (2025)

Compositional learning of functions in humans and machines
di: Zhou, Yanli, et al.
Pubblicazione: (2024)

Goals as Reward-Producing Programs
di: Davidson, Guy, et al.
Pubblicazione: (2024)

H-ARC: A Robust Estimate of Human Performance on the Abstraction and Reasoning Corpus Benchmark
di: LeGris, Solim, et al.
Pubblicazione: (2024)

Do Large Language Models Reason Causally Like Us? Even Better?
di: Dettki, Hanna M., et al.
Pubblicazione: (2025)

Rapid Word Learning Through Meta In-Context Learning
di: Wang, Wentao, et al.
Pubblicazione: (2025)

Distilling Symbolic Priors for Concept Learning into Neural Networks
di: Marinescu, Ioana, et al.
Pubblicazione: (2024)

HEIE: MLLM-Based Hierarchical Explainable AIGC Image Implausibility Evaluator
di: Yang, Fan, et al.
Pubblicazione: (2024)

BRITE: A Benchmark for Reliable and Interpretable T2V Evaluation on Implausible Scenarios
di: Tilak, Advait, et al.
Pubblicazione: (2026)

TRAVL: A Recipe for Making Video-Language Models Better Judges of Physics Implausibility
di: Motamed, Saman, et al.
Pubblicazione: (2025)

Fluent but Foreign: Even Regional LLMs Lack Cultural Alignment
di: Agarwal, Dhruv, et al.
Pubblicazione: (2025)

Beyond the Doors of Perception: Vision Transformers Represent Relations Between Objects
di: Lepori, Michael A., et al.
Pubblicazione: (2024)

Understanding the Limits of Vision Language Models Through the Lens of the Binding Problem
di: Campbell, Declan, et al.
Pubblicazione: (2024)

Cat-DPO: Category-Adaptive Safety Alignment
di: Yang, Tiankai, et al.
Pubblicazione: (2026)

Convolutional Neural Networks Can (Meta-)Learn the Same-Different Relation
di: Gupta, Max, et al.
Pubblicazione: (2025)

Probing the Probes: Methods and Metrics for Concept Alignment
di: Lysnæs-Larsen, Jacob, et al.
Pubblicazione: (2025)

Toward Efficient Exploration by Large Language Model Agents
di: Arumugam, Dilip, et al.
Pubblicazione: (2025)

Optimizing Path Planning using Deep Reinforcement Learning for UGVs in Precision Agriculture
di: Patade, Laukik, et al.
Pubblicazione: (2026)

Conformal Prediction as Bayesian Quadrature
di: Snell, Jake C., et al.
Pubblicazione: (2025)

Incoherent Probability Judgments in Large Language Models
di: Zhu, Jian-Qiao, et al.
Pubblicazione: (2024)

Learning Like Humans: Analogical Concept Learning for Generalized Category Discovery
di: Han, Jizhou, et al.
Pubblicazione: (2026)

A Rational Analysis of the Effects of Sycophantic AI
di: Batista, Rafael M., et al.
Pubblicazione: (2026)

GOAL: Geometrically Optimal Alignment for Continual Generalized Category Discovery
di: Han, Jizhou, et al.
Pubblicazione: (2026)

Deep Neural Networks Can Learn Generalizable Same-Different Visual Relations
di: Tartaglini, Alexa R., et al.
Pubblicazione: (2023)

Reasoning Shapes Alignment: Investigating Cultural Alignment in Large Reasoning Models with Cultural Norms
di: Wang, Yuhang, et al.
Pubblicazione: (2025)

Learning Human-like Representations to Enable Learning Human Values
di: Wynn, Andrea, et al.
Pubblicazione: (2023)

Prototype-Grounded Concept Models for Verifiable Concept Alignment
di: Colamonaco, Stefano, et al.
Pubblicazione: (2026)

Using Reinforcement Learning to Train Large Language Models to Explain Human Decisions
di: Zhu, Jian-Qiao, et al.
Pubblicazione: (2025)

Deciphering the Factors Influencing the Efficacy of Chain-of-Thought: Probability, Memorization, and Noisy Reasoning
di: Prabhakar, Akshara, et al.
Pubblicazione: (2024)

Process Matters more than Output for Distinguishing Humans from Machines
di: Rmus, Milena, et al.
Pubblicazione: (2026)

Recovering Event Probabilities from Large Language Model Embeddings via Axiomatic Constraints
di: Zhu, Jian-Qiao, 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)