Buchumschlag

Large Language Models are Superpositions of All Characters: Attaining Arbitrary Role-play via Self-Alignment

Fuente: arXiv

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	Lu, Keming, Yu, Bowen, Zhou, Chang, Zhou, Jingren
Format:	Preprint
Veröffentlicht:	2024
Schlagworte:	Computation and Language Machine Learning
Online-Zugang:	Acceder al recurso
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Ähnliche Einträge

Self-play with Execution Feedback: Improving Instruction-following Capabilities of Large Language Models
von: Dong, Guanting, et al.
Veröffentlicht: (2024)

Online Merging Optimizers for Boosting Rewards and Mitigating Tax in Alignment
von: Lu, Keming, et al.
Veröffentlicht: (2024)

How Abilities in Large Language Models are Affected by Supervised Fine-tuning Data Composition
von: Dong, Guanting, et al.
Veröffentlicht: (2023)

Predicting Rewards Alongside Tokens: Non-disruptive Parameter Insertion for Efficient Inference Intervention in Large Language Model
von: Yuan, Chenhan, et al.
Veröffentlicht: (2024)

A Unified View of Delta Parameter Editing in Post-Trained Large-Scale Models
von: Tang, Qiaoyu, et al.
Veröffentlicht: (2024)

ProcessBench: Identifying Process Errors in Mathematical Reasoning
von: Zheng, Chujie, et al.
Veröffentlicht: (2024)

Qwen2.5-Math Technical Report: Toward Mathematical Expert Model via Self-Improvement
von: Yang, An, et al.
Veröffentlicht: (2024)

GUARD: Role-playing to Generate Natural-language Jailbreakings to Test Guideline Adherence of Large Language Models
von: Jin, Haibo, et al.
Veröffentlicht: (2024)

AIR-Bench: Benchmarking Large Audio-Language Models via Generative Comprehension
von: Yang, Qian, et al.
Veröffentlicht: (2024)

Self-Steering Optimization: Autonomous Preference Optimization for Large Language Models
von: Xiang, Hao, et al.
Veröffentlicht: (2024)

Enhancing Visual-Language Modality Alignment in Large Vision Language Models via Self-Improvement
von: Wang, Xiyao, et al.
Veröffentlicht: (2024)

Provable Scaling Laws for the Test-Time Compute of Large Language Models
von: Chen, Yanxi, et al.
Veröffentlicht: (2024)

A Survey on Training-free Alignment of Large Language Models
von: Pan, Birong, et al.
Veröffentlicht: (2025)

EE-Tuning: An Economical yet Scalable Solution for Tuning Early-Exit Large Language Models
von: Pan, Xuchen, et al.
Veröffentlicht: (2024)

On Large Language Models' Hallucination with Regard to Known Facts
von: Jiang, Che, et al.
Veröffentlicht: (2024)

Jailbreaking Large Language Models Against Moderation Guardrails via Cipher Characters
von: Jin, Haibo, et al.
Veröffentlicht: (2024)

Self-Augmented Preference Optimization: Off-Policy Paradigms for Language Model Alignment
von: Yin, Yueqin, et al.
Veröffentlicht: (2024)

ORCE: Order-Aware Alignment of Verbalized Confidence in Large Language Models
von: Li, Chen, et al.
Veröffentlicht: (2026)

Designing Algorithms Empowered by Language Models: An Analytical Framework, Case Studies, and Insights
von: Chen, Yanxi, et al.
Veröffentlicht: (2024)

Self-playing Adversarial Language Game Enhances LLM Reasoning
von: Cheng, Pengyu, et al.
Veröffentlicht: (2024)

Efficient Alignment of Large Language Models via Data Sampling
von: Khera, Amrit, et al.
Veröffentlicht: (2024)

CharED: Character-wise Ensemble Decoding for Large Language Models
von: Gu, Kevin, et al.
Veröffentlicht: (2024)

The Illusion of Superposition? A Principled Analysis of Latent Thinking in Language Models
von: Rizvi-Martel, Michael, et al.
Veröffentlicht: (2026)

Design Principle Transfer in Neural Architecture Search via Large Language Models
von: Zhou, Xun, et al.
Veröffentlicht: (2024)

Emulated Disalignment: Safety Alignment for Large Language Models May Backfire!
von: Zhou, Zhanhui, et al.
Veröffentlicht: (2024)

Unraveling Arithmetic in Large Language Models: The Role of Algebraic Structures
von: Chang, Fu-Chieh, et al.
Veröffentlicht: (2024)

Towards Scalable Automated Alignment of LLMs: A Survey
von: Cao, Boxi, et al.
Veröffentlicht: (2024)

Single Character Perturbations Break LLM Alignment
von: Lin, Leon, et al.
Veröffentlicht: (2024)

LANE: Logic Alignment of Non-tuning Large Language Models and Online Recommendation Systems for Explainable Reason Generation
von: Zhao, Hongke, et al.
Veröffentlicht: (2024)

SelfCite: Self-Supervised Alignment for Context Attribution in Large Language Models
von: Chuang, Yung-Sung, et al.
Veröffentlicht: (2025)

Revealing Behavioral Plasticity in Large Language Models: A Token-Conditional Perspective
von: Mao, Liyuan, et al.
Veröffentlicht: (2026)

Automated Alignment of Math Items to Content Standards in Large-Scale Assessments Using Language Models
von: Xu, Qingshu, et al.
Veröffentlicht: (2025)

JoPA:Explaining Large Language Model's Generation via Joint Prompt Attribution
von: Chang, Yurui, et al.
Veröffentlicht: (2024)

OCEAN: Offline Chain-of-thought Evaluation and Alignment in Large Language Models
von: Wu, Junda, et al.
Veröffentlicht: (2024)

SAIL: Self-Improving Efficient Online Alignment of Large Language Models
von: Ding, Mucong, et al.
Veröffentlicht: (2024)

How to Leverage Demonstration Data in Alignment for Large Language Model? A Self-Imitation Learning Perspective
von: Xiao, Teng, et al.
Veröffentlicht: (2024)

Not All Experts are Equal: Efficient Expert Pruning and Skipping for Mixture-of-Experts Large Language Models
von: Lu, Xudong, et al.
Veröffentlicht: (2024)

Self-Evolving Critique Abilities in Large Language Models
von: Tang, Zhengyang, et al.
Veröffentlicht: (2025)

Token-level Accept or Reject: A Micro Alignment Approach for Large Language Models
von: Zhang, Yang, et al.
Veröffentlicht: (2025)

Qwen-Scope: Turning Sparse Features into Development Tools for Large Language Models
von: Deng, Boyi, et al.
Veröffentlicht: (2026)