mlsanityData to 14 Oct 2026

RIDE: Enhancing Large Language Model Alignment through Restyled In-Context Learning Demonstration Exemplars

arXiv 2502.11681 ↗First posted 17 Feb 2025cs.CL cs.AIcited by 2

On the map: LLM alignment / RLHF / preference optimisation → LLM preference optimization methods

Abstract (arXiv)

Alignment tuning is crucial for ensuring large language models (LLMs) behave ethically and helpfully. Current alignment approaches require high-quality annotations and significant training resources. This paper proposes a low-cost, tuning-free method using in-context learning (ICL) to enhance LLM alignment. Through an analysis of high-quality ICL demos, we identified style as a key factor influencing LLM alignment capabilities and explicitly restyled ICL exemplars based on this stylistic framework. Additionally, we combined the restyled demos to achieve a balance between the two conflicting aspects of LLM alignment--factuality and safety. We packaged the restyled examples as prompts to trigger few-shot learning, improving LLM alignment. Compared to the best baseline approach, with an average score of 5.00 as the maximum, our method achieves a maximum 0.10 increase on the Alpaca task (from 4.50 to 4.60), a 0.22 enhancement on the Just-eval benchmark (from 4.34 to 4.56), and a maximum improvement of 0.32 (from 3.53 to 3.85) on the MT-Bench dataset. We release the code and data at https://github.com/AnonymousCode-ComputerScience/RIDE.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Placed in LLM preference optimization methods, one of 10 directions in LLM alignment / RLHF / preference optimisation. Builds on 33 of its 86 references that are in the map. First posted on arXiv 17 Feb 2025.

Builds on

33 of 86 references.

Closest ancestors · 4

Same direction, newest first

  1. 2023The Unlocking Spell on Base LLMs: Rethinking Alignment via In-Context Learning4 Dec
  2. 2023Large Language Model Alignment: A Survey26 Sep
  3. 2023LIMA: Less Is More for Alignment18 May
  4. 2022Training language models to follow instructions with human feedback4 Mar

Other references · 29

  1. 2020Language Models are Few-Shot Learnerscited by 32,419
  2. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 13,028
  3. 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,626
  4. 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Modelcited by 8,065
  5. 2022Rethinking the Role of Demonstrations: What Makes In-Context Learning Work?cited by 1,434
  6. 2021What Makes Good In-Context Examples for GPT-3?cited by 1,195
  7. 2023Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!cited by 1,154
  8. 2024Length-Controlled AlpacaEval: A Simple Way to Debias Automatic Evaluatorscited by 897
  9. 2023BeaverTails: Towards Improved Safety Alignment of LLM via a Human-Preference Datasetcited by 860
  10. 2023Enhancing Chat Language Models by Scaling High-quality Instructional Conversationscited by 839
  11. 2023Aligning Large Multimodal Models with Factually Augmented RLHFcited by 712
  12. 2023Safe RLHF: Safe Reinforcement Learning from Human Feedbackcited by 656
17 more
  1. 2024OLMo: Accelerating the Science of Language Modelscited by 613
  2. 2024Safety Alignment Should Be Made More Than Just a Few Tokens Deepcited by 472
  3. 2023How Far Can Camels Go? Exploring the State of Instruction Tuning on Open Resourcescited by 408
  4. 2024SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusalcited by 240
  5. 2024Self-Play Preference Optimization for Language Model Alignmentcited by 232
  6. 2023Compositional Exemplars for In-context Learningcited by 144
  7. 2024Refuse Whenever You Feel Unsafe: Improving Safety in LLMs via Decoupled Refusal Trainingcited by 69
  8. 2023Learning to Retrieve In-Context Examples for Large Language Modelscited by 60
  9. 2024Revisiting Demonstration Selection Strategies in In-Context Learningcited by 58
  10. 2021Causal Effect Inference for Structured Treatmentscited by 39
  11. 2024PICLe: Eliciting Diverse Behaviors from Large Language Models with Persona In-Context Learningcited by 29
  12. 2022Empirical Analysis of Model Selection for Heterogeneous Causal Effect Estimationcited by 25
  13. 2024Assistive Large Language Model Agents for Socially-Aware Negotiation Dialoguescited by 18
  14. 2024Retrieval-style In-Context Learning for Few-shot Hierarchical Text Classificationcited by 16
  15. 2024SafeAligner: Safety Alignment against Jailbreak Attacks via Response Disparity Guidancecited by 9
  16. 2024Se2: Sequential Example Selection for In-Context Learningcited by 8
  17. 2024SCAR: Data Selection via Style Consistency-Aware Response Ranking for Efficient Instruction-Tuning of Large Language Modelscited by 6

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 1; 2026: 1.

2 papers.

  1. 2025Beyond Keywords: Evaluating Large Language Model Classification of Nuanced Ableismcited by 1
  2. 2026LLMdoctor: Token-Level Flow-Guided Preference Optimization for Efficient Test-Time Alignment of Large Language Modelscited by 1

Similar, not cited

Close in wording, no citation either way

  1. 2025A Survey on Training-free Alignment of Large Language Models
  2. 2024Efficient Alignment of Large Language Models via Data Sampling
  3. 2026AlignTune: Modular Toolkit for Post-Training Alignment of Large Language Models
  4. 2025Towards Efficient and Effective Alignment of Large Language Models
  5. 2025A Comprehensive Evaluation framework of Alignment Techniques for LLMs
  6. 2024LongAlign: A Recipe for Long Context Alignment of Large Language Models
  7. 2024Understanding Layer Significance in LLM Alignment
  8. 2023Aligner: One Global Token is Worth Millions of Parameters When Aligning Large Language Models