Copertina

Understanding How Value Neurons Shape the Generation of Specified Values in LLMs

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Su, Yi, Zhang, Jiayi, Yang, Shu, Wang, Xinhai, Hu, Lijie, Wang, Di
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Computation and Language
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Understanding and Mitigating Cross-lingual Privacy Leakage via Language-specific and Universal Privacy Neurons
di: Dong, Wenshuo, et al.
Pubblicazione: (2025)

Word Recovery in Large Language Models Enables Character-Level Tokenization Robustness
di: Yang, Zhipeng, et al.
Pubblicazione: (2026)

Understanding and Mitigating Political Stance Cross-topic Generalization in Large Language Models
di: Zhang, Jiayi, et al.
Pubblicazione: (2025)

Understanding the Repeat Curse in Large Language Models from a Feature Perspective
di: Yao, Junchi, et al.
Pubblicazione: (2025)

MoRAL: MoE Augmented LoRA for LLMs' Lifelong Learning
di: Yang, Shu, et al.
Pubblicazione: (2024)

Human Values Matter: Investigating How Misalignment Shapes Collective Behaviors in LLM Agent Communities
di: Zhang, Xiangxu, et al.
Pubblicazione: (2026)

Exploring the Personality Traits of LLMs through Latent Features Steering
di: Yang, Shu, et al.
Pubblicazione: (2024)

Direct Value Optimization: Improving Chain-of-Thought Reasoning in LLMs with Refined Values
di: Zhang, Hongbo, et al.
Pubblicazione: (2025)

Dialectical Alignment: Resolving the Tension of 3H and Security Threats of LLMs
di: Yang, Shu, et al.
Pubblicazione: (2024)

NeuronMLP: Efficient LLM Inference via Singular Value Decomposition Compression and Tiling on AWS Trainium
di: Song, Dinghong, et al.
Pubblicazione: (2025)

Flattery in Motion: Benchmarking and Analyzing Sycophancy in Video-LLMs
di: Zhou, Wenrui, et al.
Pubblicazione: (2025)

MONAL: Model Autophagy Analysis for Modeling Human-AI Interactions
di: Yang, Shu, et al.
Pubblicazione: (2024)

Following the Whispers of Values: Unraveling Neural Mechanisms Behind Value-Oriented Behaviors in LLMs
di: Hu, Ling, et al.
Pubblicazione: (2025)

Understanding the Physics of Key-Value Cache Compression for LLMs through Attention Dynamics
di: Ananthanarayanan, Samhruth, et al.
Pubblicazione: (2026)

ValueBench: Towards Comprehensively Evaluating Value Orientations and Understanding of Large Language Models
di: Ren, Yuanyi, et al.
Pubblicazione: (2024)

Raising the Bar: Investigating the Values of Large Language Models via Generative Evolving Testing
di: Jiang, Han, et al.
Pubblicazione: (2024)

AI and My Values: User Perceptions of LLMs' Ability to Extract, Embody, and Explain Human Values from Casual Conversations
di: Yun, Bhada, et al.
Pubblicazione: (2026)

CuMA: Aligning LLMs with Sparse Cultural Values via Demographic-Aware Mixture of Adapters
di: Sun, Ao, et al.
Pubblicazione: (2026)

Flames: Benchmarking Value Alignment of LLMs in Chinese
di: Huang, Kexin, et al.
Pubblicazione: (2023)

Cash or Comfort? How LLMs Value Your Inconvenience
di: Cedro, Mateusz, et al.
Pubblicazione: (2025)

Lost in Literalism: How Supervised Training Shapes Translationese in LLMs
di: Li, Yafu, et al.
Pubblicazione: (2025)

Understanding Reasoning in Chain-of-Thought from the Hopfieldian View
di: Hu, Lijie, et al.
Pubblicazione: (2024)

Mitigating Behavioral Hallucination in Multimodal Large Language Models for Sequential Images
di: You, Liangliang, et al.
Pubblicazione: (2025)

Enhancing Agentic RL with Progressive Reward Shaping and Value-based Sampling Policy Optimization
di: Su, Jianghao, et al.
Pubblicazione: (2025)

Beyond Benchmark: LLMs Evaluation with an Anthropomorphic and Value-oriented Roadmap
di: Wang, Jun, et al.
Pubblicazione: (2025)

SpeCache: Speculative Key-Value Caching for Efficient Generation of LLMs
di: Jie, Shibo, et al.
Pubblicazione: (2025)

ValueDCG: Measuring Comprehensive Human Value Understanding Ability of Language Models
di: Zhang, Zhaowei, et al.
Pubblicazione: (2023)

Edu-Values: Towards Evaluating the Chinese Education Values of Large Language Models
di: Zhang, Peiyi, et al.
Pubblicazione: (2024)

Under the Shadow of Babel: How Language Shapes Reasoning in LLMs
di: Wang, Chenxi, et al.
Pubblicazione: (2025)

DictLLM: Harnessing Key-Value Data Structures with Large Language Models for Enhanced Medical Diagnostics
di: Guo, YiQiu, et al.
Pubblicazione: (2024)

Implicit Values Embedded in How Humans and LLMs Complete Subjective Everyday Tasks
di: Arunasalam, Arjun, et al.
Pubblicazione: (2025)

ValueCompass: A Framework for Measuring Contextual Value Alignment Between Human and LLMs
di: Shen, Hua, et al.
Pubblicazione: (2024)

ValueSim: Generating Backstories to Model Individual Value Systems
di: Du, Bangde, et al.
Pubblicazione: (2025)

Mind the Value-Action Gap: Do LLMs Act in Alignment with Their Values?
di: Shen, Hua, et al.
Pubblicazione: (2025)

Specifying Genericity through Inclusiveness and Abstractness Continuous Scales
di: Collacciani, Claudia, et al.
Pubblicazione: (2024)

Length Value Model: Scalable Value Pretraining for Token-Level Length Modeling
di: Zhang, Zhen, et al.
Pubblicazione: (2026)

Do LLMs Align Human Values Regarding Social Biases? Judging and Explaining Social Biases with LLMs
di: Liu, Yang, et al.
Pubblicazione: (2025)

Language Shapes Mental Health Evaluations in Large Language Models
di: Xu, Jiayi, et al.
Pubblicazione: (2026)

How Value Induction Reshapes LLM Behaviour
di: Arora, Arnav, et al.
Pubblicazione: (2026)

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