mlsanityData to 14 Oct 2026

In-Context Alignment: Chat with Vanilla Language Models Before Fine-Tuning

arXiv 2308.04275 ↗First posted 8 Aug 2023cs.CL cs.AI cs.LGcited by 19

Not on the map. Why?

Abstract (arXiv)

In this note, we explore inference-time alignment through in-context learning. We consider a vanilla pretrained language model Llama-2 before any fine-tuning and retrieve an average of 9 demonstration alignment examples when the model is prompted to follow chat-style instructions. Compared to direct prompting, the in-context alignment without changing model weights leads to a 7x increase in win-rate w.r.t. the text-davinci-003 model from OpenAI, making the vanilla language model comparable to strong baselines with alignment fine-tuning.

Key facts. Cited by 19 papers in the map (data through 14 Oct 2026). Builds on 12 of its 18 references that are in the map. First posted on arXiv 8 Aug 2023.

Builds on

12 of 18 references.

References · 12

  1. 2023GPT-4 Technical Reportcited by 18,396
  2. 2022Training language models to follow instructions with human feedbackcited by 15,971
  3. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 14,132
  4. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 13,028
  5. 2020Measuring Massive Multitask Language Understandingcited by 7,963
  6. 2022Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedbackcited by 3,720
  7. 2023QLoRA: Efficient Finetuning of Quantized LLMscited by 3,418
  8. 2022Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Themcited by 1,807
  9. 2021Unsupervised Dense Information Retrieval with Contrastive Learningcited by 1,216
  10. 2023LIMA: Less Is More for Alignmentcited by 1,100
  11. 2023OpenAssistant Conversations -- Democratizing Large Language Model Alignmentcited by 721
  12. 2023How Far Can Camels Go? Exploring the State of Instruction Tuning on Open Resourcescited by 408

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 1; 2024: 15; 2025: 2; 2026: 1.

19 papers.

Sort:

By area:

  1. 2024LESS: Selecting Influential Data for Targeted Instruction Tuningcited by 532
  2. 2023The Unlocking Spell on Base LLMs: Rethinking Alignment via In-Context Learningcited by 257
  3. 2024Tuning Language Models by Proxycited by 89
  4. 2024A Theoretical Understanding of Self-Correction through In-context Alignmentcited by 44
  5. 2024Controllable Safety Alignment: Inference-Time Adaptation to Diverse Safety Requirementscited by 36
  6. 2024From Distributional to Overton Pluralism: Investigating Large Language Model Alignmentcited by 33
  7. 2024Human-Instruction-Free LLM Self-Alignment with Limited Samplescited by 25
  8. 2024Nudging: Inference-time Alignment of LLMs via Guided Decodingcited by 23
  9. 2024On the Essence and Prospect: An Investigation of Alignment Approaches for Big Modelscited by 21
  10. 2024Is In-Context Learning Sufficient for Instruction Following in LLMs?cited by 19
  11. 2024Dynamic Rewarding with Prompt Optimization Enables Tuning-free Self-Alignment of Language Modelscited by 13
  12. 2024Compute-Constrained Data Selectioncited by 12
7 more
  1. 2024Do Large Language Models Mirror Cognitive Language Processing?cited by 9
  2. 2024Unveiling the Misuse Potential of Base Large Language Models via In-Context Learningcited by 6
  3. 2024How Far Can In-Context Alignment Go? Exploring the State of In-Context Alignmentcited by 6
  4. 2024SPICA: Retrieving Scenarios for Pluralistic In-Context Alignmentcited by 6
  5. 2025In-context Learning vs. Instruction Tuning: The Case of Small and Multilingual Language Modelscited by 3
  6. 2025PICACO: Pluralistic In-Context Value Alignment of LLMs via Total Correlation Optimizationcited by 3
  7. 2026Unified Data Selection for LLM Reasoningcited by 3

Similar, not cited

Close in wording, no citation either way

  1. 2025RIDE: Enhancing Large Language Model Alignment through Restyled In-Context Learning Demonstration Exemplars
  2. 2025A Survey on Training-free Alignment of Large Language Models
  3. 2024Aligner: Efficient Alignment by Learning to Correct
  4. 2026AlignTune: Modular Toolkit for Post-Training Alignment of Large Language Models
  5. 2024LongAlign: A Recipe for Long Context Alignment of Large Language Models
  6. 2024Inference-Time Language Model Alignment via Integrated Value Guidance
  7. 2024DeAL: Decoding-time Alignment for Large Language Models
  8. 2024Aligning Large Language Models via Fine-grained Supervision