Copertina

Measuring How LLMs Internalize Human Psychological Concepts: A preliminary analysis

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Hamada, Hiro Taiyo, Fujisawa, Ippei, Kawakita, Genji, Yamada, Yuki
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Machine Learning Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Psychological Concept Neurons: Can Neural Control Bias Probing and Shift Generation in LLMs?
di: Harada, Yuto, et al.
Pubblicazione: (2026)

How Well Do LLMs Predict Human Behavior? A Measure of their Pretrained Knowledge
di: Gao, Wayne, et al.
Pubblicazione: (2026)

Scalable Valuation of Human Feedback through Provably Robust Model Alignment
di: Fujisawa, Masahiro, et al.
Pubblicazione: (2025)

Signs Beat Floats: Low-Rank Double-Binary Adaptation for On-Device Fine-Tuning
di: Fujisawa, Yoshihiko, et al.
Pubblicazione: (2026)

Exploring the Frontiers of LLMs in Psychological Applications: A Comprehensive Review
di: Ke, Luoma, et al.
Pubblicazione: (2024)

ProcBench: Benchmark for Multi-Step Reasoning and Following Procedure
di: Fujisawa, Ippei, et al.
Pubblicazione: (2024)

On LLMs' Internal Representation of Code Correctness
di: Ribeiro, Francisco, et al.
Pubblicazione: (2025)

Artificial Neural Nets and the Representation of Human Concepts
di: Freiesleben, Timo
Pubblicazione: (2023)

Adaptive Scoring and Thresholding with Human Feedback for Robust Out-of-Distribution Detection
di: Yamada, Daisuke, et al.
Pubblicazione: (2025)

How Likely Do LLMs with CoT Mimic Human Reasoning?
di: Bao, Guangsheng, et al.
Pubblicazione: (2024)

Explainable Human Activity Recognition: A Unified Review of Concepts and Mechanisms
di: Kundu, Mainak, et al.
Pubblicazione: (2026)

Measuring Leakage in Concept-Based Methods: An Information Theoretic Approach
di: Makonnen, Mikael, et al.
Pubblicazione: (2025)

More Than Bits: Multi-Envelope Double Binary Factorization for Extreme Quantization
di: Ichikawa, Yuma, et al.
Pubblicazione: (2025)

Reinforcement Learning Fine-Tuning Enhances Activation Intensity and Diversity in the Internal Circuitry of LLMs
di: Zhang, Honglin, et al.
Pubblicazione: (2025)

MindCraft: How Concept Trees Take Shape In Deep Models
di: Tian, Bowei, et al.
Pubblicazione: (2025)

Enhancing Output Diversity Improves Conjugate Gradient-based Adversarial Attacks
di: Yamamura, Keiichiro, et al.
Pubblicazione: (2024)

Norm Anchors Make Model Edits Last
di: Liu, Mingda, et al.
Pubblicazione: (2026)

How Good Are LLMs at Processing Tool Outputs?
di: Kate, Kiran, et al.
Pubblicazione: (2025)

Connecting Concept Convexity and Human-Machine Alignment in Deep Neural Networks
di: Dorszewski, Teresa, et al.
Pubblicazione: (2024)

An Analysis of Concept Bottleneck Models: Measuring, Understanding, and Mitigating the Impact of Noisy Annotations
di: Park, Seonghwan, et al.
Pubblicazione: (2025)

Beyond Single Concept Vector: Modeling Concept Subspace in LLMs with Gaussian Distribution
di: Zhao, Haiyan, et al.
Pubblicazione: (2024)

Learning Displacement-Robust Representations for Landslide Early Warning under Rainfall Forecast Uncertainty
di: Ozeki, Ren, et al.
Pubblicazione: (2026)

SelfReflect: Can LLMs Communicate Their Internal Answer Distribution?
di: Kirchhof, Michael, et al.
Pubblicazione: (2025)

NEAT: Concept driven Neuron Attribution in LLMs
di: Kavuri, Vivek Hruday, et al.
Pubblicazione: (2025)

Coordinate Matrix Machine: A Human-level Concept Learning to Classify Very Similar Documents
di: Sadri, Amin, et al.
Pubblicazione: (2025)

How to Measure the Intelligence of Large Language Models?
di: Körber, Nils, et al.
Pubblicazione: (2024)

From Attribution Maps to Human-Understandable Explanations through Concept Relevance Propagation
di: Achtibat, Reduan, et al.
Pubblicazione: (2022)

Graph Neural Networks for Gut Microbiome Metaomic data: A preliminary work
di: Irwin, Christopher, et al.
Pubblicazione: (2024)

Zero-Shot LLMs in Human-in-the-Loop RL: Replacing Human Feedback for Reward Shaping
di: Nazir, Mohammad Saif, et al.
Pubblicazione: (2025)

Exploring Concept Depth: How Large Language Models Acquire Knowledge and Concept at Different Layers?
di: Jin, Mingyu, et al.
Pubblicazione: (2024)

Erased but Not Forgotten: How Backdoors Compromise Concept Erasure
di: Braun, Tobias, et al.
Pubblicazione: (2025)

How Random is Random? Evaluating the Randomness and Humaness of LLMs' Coin Flips
di: Van Koevering, Katherine, et al.
Pubblicazione: (2024)

On the Internal Representations of Graph Metanetworks
di: Yeom, Taesun, et al.
Pubblicazione: (2025)

A Shared Valence Axis Across Modern LLMs and Human EEG: The Saturation Regularity
di: Radwan, Yousef A., et al.
Pubblicazione: (2026)

Subgoal-based Reward Shaping to Improve Efficiency in Reinforcement Learning
di: Okudo, Takato, et al.
Pubblicazione: (2021)

Evaluation of LLMs-based Hidden States as Author Representations for Psychological Human-Centered NLP Tasks
di: Soni, Nikita, et al.
Pubblicazione: (2025)

Reinforcement-learning robotic sailboats: simulator and preliminary results
di: Vasconcellos, Eduardo Charles, et al.
Pubblicazione: (2024)

Addressing Concept Mislabeling in Concept Bottleneck Models Through Preference Optimization
di: Penaloza, Emiliano, et al.
Pubblicazione: (2025)

ConceptTracer: Interactive Analysis of Concept Saliency and Selectivity in Neural Representations
di: Knauer, Ricardo, et al.
Pubblicazione: (2026)

How Susceptible are LLMs to Influence in Prompts?
di: Anagnostidis, Sotiris, et al.
Pubblicazione: (2024)