Copertina

Preference Heads in Large Language Models: A Mechanistic Framework for Interpretable Personalization

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Zhang, Weixu, Yuan, Ye, Han, Changjiang, Tian, Yuxing, Sun, Zipeng, Du, Linfeng, Kang, Jikun, Kang, Hong, Liu, Xue, Wu, Haolun
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Computation and Language
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Beyond Message Passing: A Semantic View of Agent Communication Protocols
di: Yuan, Dun, et al.
Pubblicazione: (2026)

Optimizing User Profiles via Contextual Bandits for Retrieval-Augmented LLM Personalization
di: Du, Linfeng, et al.
Pubblicazione: (2026)

Learning to Route Queries to Heads for Attention-based Re-ranking with Large Language Models
di: Tian, Yuxing, et al.
Pubblicazione: (2026)

Support-Proximity Augmented Diffusion Estimation for Offline Black-Box Optimization
di: Yang, Yonghan, et al.
Pubblicazione: (2026)

Context-Fidelity Boosting: Enhancing Faithful Generation through Watermark-Inspired Decoding
di: Zhang, Weixu, et al.
Pubblicazione: (2026)

Training Diffusion Language Models for Black-Box Optimization
di: Sun, Zipeng, et al.
Pubblicazione: (2026)

QUACK: Questioning, Understanding, and Auditing Communicated Knowledge in Multimodal Social Deduction Agents
di: Yuan, Ye, et al.
Pubblicazione: (2026)

Diffusion Large Language Models for Black-Box Optimization
di: Yuan, Ye, et al.
Pubblicazione: (2026)

LLM Safety From Within: Detecting Harmful Content with Internal Representations
di: Jiao, Difan, et al.
Pubblicazione: (2026)

Unlocking the Future: Exploring Look-Ahead Planning Mechanistic Interpretability in Large Language Models
di: Men, Tianyi, et al.
Pubblicazione: (2024)

Interpreting Attention Heads for Image-to-Text Information Flow in Large Vision-Language Models
di: Kim, Jinyeong, et al.
Pubblicazione: (2025)

Achieving Tunable Amplified Spontaneous Emission in Rb‐Cs Alloyed Quasi‐2D Perovskites with Low Threshold and Exceptional Spectral Stability
di: Changjiang Shi, et al.
Pubblicazione: (2025)

Review-driven Personalized Preference Reasoning with Large Language Models for Recommendation
di: Kim, Jieyong, et al.
Pubblicazione: (2024)

A Survey on Test-Time Scaling in Large Language Models: What, How, Where, and How Well?
di: Zhang, Qiyuan, et al.
Pubblicazione: (2025)

ReAttn: Improving Attention-based Re-ranking via Attention Re-weighting
di: Tian, Yuxing, et al.
Pubblicazione: (2026)

A Survey on Data Contamination for Large Language Models
di: Cheng, Yuxing, et al.
Pubblicazione: (2025)

Think Before You Act: Decision Transformers with Working Memory
di: Kang, Jikun, et al.
Pubblicazione: (2023)

Geospatial Mechanistic Interpretability of Large Language Models
di: De Sabbata, Stef, et al.
Pubblicazione: (2025)

Privis: Towards Content-Aware Secure Volumetric Video Delivery
di: Hu, Kaiyuan, et al.
Pubblicazione: (2025)

BackSlash: Rate Constrained Optimized Training of Large Language Models
di: Wu, Jun, et al.
Pubblicazione: (2025)

Human Aesthetic Preference-Based Large Text-to-Image Model Personalization: Kandinsky Generation as an Example
di: Zhou, Aven-Le, et al.
Pubblicazione: (2024)

Learning to Extract Structured Entities Using Language Models
di: Wu, Haolun, et al.
Pubblicazione: (2024)

Personalized LLM Decoding via Contrasting Personal Preference
di: Bu, Hyungjune, et al.
Pubblicazione: (2025)

SSRLBot: Designing and Developing a Large Language Model-based Agent using Socially Shared Regulated Learning
di: Huang, Xiaoshan, et al.
Pubblicazione: (2025)

Multivariable $(φ_q,\mathcal{O}_K^{\times})$-modules associated to $p$-adic representations of $\mathrm{Gal}(\overline{K}/K)$
di: Du, Changjiang
Pubblicazione: (2025)

The overconvergence of multivariable $(φ_q,\mathcal{O}_K^{\times})$-modules at the perfectoid level
di: Du, Changjiang
Pubblicazione: (2026)

Mechanistic Interpretability of Emotion Inference in Large Language Models
di: Tak, Ala N., et al.
Pubblicazione: (2025)

Binary Autoencoder for Mechanistic Interpretability of Large Language Models
di: Cho, Hakaze, et al.
Pubblicazione: (2025)

Counting Circuits: Mechanistic Interpretability of Visual Reasoning in Large Vision-Language Models
di: Che, Liwei, et al.
Pubblicazione: (2026)

SafeAnchor: Preventing Cumulative Safety Erosion in Continual Domain Adaptation of Large Language Models
di: Guo, Dongxin, et al.
Pubblicazione: (2026)

AFSPP: Agent Framework for Shaping Preference and Personality with Large Language Models
di: He, Zihong, et al.
Pubblicazione: (2024)

Understanding 6G through Language Models: A Case Study on LLM-aided Structured Entity Extraction in Telecom Domain
di: Yuan, Ye, et al.
Pubblicazione: (2025)

Learning Discriminative and Generalizable Anomaly Detector for Dynamic Graph with Limited Supervision
di: Tian, Yuxing, et al.
Pubblicazione: (2026)

MechELK: A Mechanistic Interpretability Framework for Eliciting Latent Knowledge in Large Language Models
di: Park, Ji-jun, et al.
Pubblicazione: (2026)

Causal Tracing of Object Representations in Large Vision Language Models: Mechanistic Interpretability and Hallucination Mitigation
di: Li, Qiming, et al.
Pubblicazione: (2025)

Mitigating Hallucination in Multimodal Large Language Model via Hallucination-targeted Direct Preference Optimization
di: Fu, Yuhan, et al.
Pubblicazione: (2024)

IIMedGPT: Promoting Large Language Model Capabilities of Medical Tasks by Efficient Human Preference Alignment
di: Zhang, Yiming, et al.
Pubblicazione: (2025)

ViRAC: A Vision-Reasoning Agent Head Movement Control Framework in Arbitrary Virtual Environments
di: Hwang, Juyeong, et al.
Pubblicazione: (2025)

Beyond Under-Alignment: Atomic Preference Enhanced Factuality Tuning for Large Language Models
di: Yuan, Hongbang, et al.
Pubblicazione: (2024)

Can Large Language Models Understand Preferences in Personalized Recommendation?
di: Tan, Zhaoxuan, et al.
Pubblicazione: (2025)