Copertina

Keeping LLMs Aligned After Fine-tuning: The Crucial Role of Prompt Templates

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Lyu, Kaifeng, Zhao, Haoyu, Gu, Xinran, Yu, Dingli, Goyal, Anirudh, Arora, Sanjeev
Natura:	Preprint
Pubblicazione:	2024
Soggetti:	Machine Learning Artificial Intelligence Computation and Language
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Can Models Learn Skill Composition from Examples?
di: Zhao, Haoyu, et al.
Pubblicazione: (2024)

Data Mixing Can Induce Phase Transitions in Knowledge Acquisition
di: Gu, Xinran, et al.
Pubblicazione: (2025)

AI-Assisted Generation of Difficult Math Questions
di: Shah, Vedant, et al.
Pubblicazione: (2024)

Contextual Drag: How Errors in the Context Affect LLM Reasoning
di: Cheng, Yun, et al.
Pubblicazione: (2026)

Fine-tuned Large Language Models (LLMs): Improved Prompt Injection Attacks Detection
di: Rahman, Md Abdur, et al.
Pubblicazione: (2024)

SPAFIT: Stratified Progressive Adaptation Fine-tuning for Pre-trained Large Language Models
di: Arora, Samir, et al.
Pubblicazione: (2024)

RLSF: Fine-tuning LLMs via Symbolic Feedback
di: Jha, Piyush, et al.
Pubblicazione: (2024)

Metacognitive Reuse: Turning Recurring LLM Reasoning Into Concise Behaviors
di: Didolkar, Aniket, et al.
Pubblicazione: (2025)

AlgoVeri: An Aligned Benchmark for Verified Code Generation on Classical Algorithms
di: Zhao, Haoyu, et al.
Pubblicazione: (2026)

Generalizing from SIMPLE to HARD Visual Reasoning: Can We Mitigate Modality Imbalance in VLMs?
di: Park, Simon, et al.
Pubblicazione: (2025)

Fine-tuning and Utilization Methods of Domain-specific LLMs
di: Jeong, Cheonsu
Pubblicazione: (2024)

Ineq-Comp: Benchmarking Human-Intuitive Compositional Reasoning in Automated Theorem Proving on Inequalities
di: Zhao, Haoyu, et al.
Pubblicazione: (2025)

PromptTailor: Multi-turn Intent-Aligned Prompt Synthesis for Lightweight LLMs
di: Xu, Yizhou, et al.
Pubblicazione: (2025)

Aloe: A Family of Fine-tuned Open Healthcare LLMs
di: Gururajan, Ashwin Kumar, et al.
Pubblicazione: (2024)

SEAL: Safety-enhanced Aligned LLM Fine-tuning via Bilevel Data Selection
di: Shen, Han, et al.
Pubblicazione: (2024)

Fake Alignment: Are LLMs Really Aligned Well?
di: Wang, Yixu, et al.
Pubblicazione: (2023)

Reasoning Robustness of LLMs to Adversarial Typographical Errors
di: Gan, Esther, et al.
Pubblicazione: (2024)

Prompting or Fine-tuning? Exploring Large Language Models for Causal Graph Validation
di: Susanti, Yuni, et al.
Pubblicazione: (2024)

Fine-tuning vs Prompting, Can Language Models Understand Human Values?
di: Sun, Pingwei
Pubblicazione: (2024)

Compact Prompting in Instruction-tuned LLMs for Joint Argumentative Component Detection
di: Elguendouze, Sofiane, et al.
Pubblicazione: (2026)

ITERTL: An Iterative Framework for Fine-tuning LLMs for RTL Code Generation
di: Wu, Peiyang, et al.
Pubblicazione: (2024)

When MOE Meets LLMs: Parameter Efficient Fine-tuning for Multi-task Medical Applications
di: Liu, Qidong, et al.
Pubblicazione: (2023)

Affordably Fine-tuned LLMs Provide Better Answers to Course-specific MCQs
di: Raimondi, Bianca, et al.
Pubblicazione: (2025)

Magpie: Alignment Data Synthesis from Scratch by Prompting Aligned LLMs with Nothing
di: Xu, Zhangchen, et al.
Pubblicazione: (2024)

ArtPrompt: ASCII Art-based Jailbreak Attacks against Aligned LLMs
di: Jiang, Fengqing, et al.
Pubblicazione: (2024)

UNH at CheckThat! 2025: Fine-tuning Vs Prompting in Claim Extraction
di: Wilder, Joe, et al.
Pubblicazione: (2025)

Identity Lock: Locking API Fine-tuned LLMs With Identity-based Wake Words
di: Su, Hongyu, et al.
Pubblicazione: (2025)

KnowTuning: Knowledge-aware Fine-tuning for Large Language Models
di: Lyu, Yougang, et al.
Pubblicazione: (2024)

Multi-Party Supervised Fine-tuning of Language Models for Multi-Party Dialogue Generation
di: Wang, Xiaoyu, et al.
Pubblicazione: (2024)

SPARSEFIT: Few-shot Prompting with Sparse Fine-tuning for Jointly Generating Predictions and Natural Language Explanations
di: Solano, Jesus, et al.
Pubblicazione: (2023)

Progtuning: Progressive Fine-tuning Framework for Transformer-based Language Models
di: Ji, Xiaoshuang, et al.
Pubblicazione: (2025)

Learning Beyond Pattern Matching? Assaying Mathematical Understanding in LLMs
di: Guo, Siyuan, et al.
Pubblicazione: (2024)

Maastricht University at AMIYA: Adapting LLMs for Dialectal Arabic using Fine-tuning and MBR Decoding
di: Alali, Abdulhai, et al.
Pubblicazione: (2026)

Multitask Mayhem: Unveiling and Mitigating Safety Gaps in LLMs Fine-tuning
di: Jan, Essa, et al.
Pubblicazione: (2024)

PromptIntern: Saving Inference Costs by Internalizing Recurrent Prompt during Large Language Model Fine-tuning
di: Zou, Jiaru, et al.
Pubblicazione: (2024)

Comparing Explanation Faithfulness between Multilingual and Monolingual Fine-tuned Language Models
di: Zhao, Zhixue, et al.
Pubblicazione: (2024)

MTUncertainty: Assessing the Need for Post-editing of Machine Translation Outputs by Fine-tuning OpenAI LLMs
di: Gladkoff, Serge, et al.
Pubblicazione: (2023)

Unnatural Languages Are Not Bugs but Features for LLMs
di: Duan, Keyu, et al.
Pubblicazione: (2025)

Rethinking Thinking Tokens: LLMs as Improvement Operators
di: Madaan, Lovish, et al.
Pubblicazione: (2025)

PAFT: Prompt-Agnostic Fine-Tuning
di: Wei, Chenxing, et al.
Pubblicazione: (2025)