# Incomplete In-context Learning

arXiv: https://arxiv.org/abs/2505.07251 · HTML: https://mlsanity.com/paper/2505.07251/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in VLM benchmarks and visual reasoning, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 36 of its 46 references that are in the map.
- First posted on arXiv 12 May 2025.

## Placed in

- Multimodal LLMs / vision-language models / [VLM benchmarks and visual reasoning](https://mlsanity.com/mllm/vlm-benchmarks-and-visual-reasoning/)

## Builds on (most cited first, 30 of 36)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms](https://mlsanity.com/paper/1708.07747/) (2017)
- [InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks](https://mlsanity.com/paper/2312.14238/) (2023)
- [Emergent Abilities of Large Language Models](https://mlsanity.com/paper/2206.07682/) (2022)
- [Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling](https://mlsanity.com/paper/2412.05271/) (2024)
- [Rethinking the Role of Demonstrations: What Makes In-Context Learning Work?](https://mlsanity.com/paper/2202.12837/) (2022)
- [What Makes Good In-Context Examples for GPT-3?](https://mlsanity.com/paper/2101.06804/) (2021)
- [Fantastically Ordered Prompts and Where to Find Them: Overcoming Few-Shot Prompt Order Sensitivity](https://mlsanity.com/paper/2104.08786/) (2021)
- [MetaICL: Learning to Learn In Context](https://mlsanity.com/paper/2110.15943/) (2021)
- [Larger language models do in-context learning differently](https://mlsanity.com/paper/2303.03846/) (2023)
- [Complexity-Based Prompting for Multi-Step Reasoning](https://mlsanity.com/paper/2210.00720/) (2022)
- [Label Words are Anchors: An Information Flow Perspective for Understanding In-Context Learning](https://mlsanity.com/paper/2305.14160/) (2023)
- [Demystifying Prompts in Language Models via Perplexity Estimation](https://mlsanity.com/paper/2212.04037/) (2022)
- [Large-scale Classification of Fine-Art Paintings: Learning The Right Metric on The Right Feature](https://mlsanity.com/paper/1505.00855/) (2015)
- [Self-Adaptive In-Context Learning: An Information Compression Perspective for In-Context Example Selection and Ordering](https://mlsanity.com/paper/2212.10375/) (2022)
- [Large Language Models Are Latent Variable Models: Explaining and Finding Good Demonstrations for In-Context Learning](https://mlsanity.com/paper/2301.11916/) (2023)
- [Visual In-Context Learning for Large Vision-Language Models](https://mlsanity.com/paper/2402.11574/) (2024)
- [Finding Support Examples for In-Context Learning](https://mlsanity.com/paper/2302.13539/) (2023)
- [Mitigating Label Biases for In-context Learning](https://mlsanity.com/paper/2305.19148/) (2023)
- [Symbol tuning improves in-context learning in language models](https://mlsanity.com/paper/2305.08298/) (2023)
- [Z-ICL: Zero-Shot In-Context Learning with Pseudo-Demonstrations](https://mlsanity.com/paper/2212.09865/) (2022)
- [Meta-in-context learning in large language models](https://mlsanity.com/paper/2305.12907/) (2023)
- [Coverage-based Example Selection for In-Context Learning](https://mlsanity.com/paper/2305.14907/) (2023)
- [In-Context Learning Learns Label Relationships but Is Not Conventional Learning](https://mlsanity.com/paper/2307.12375/) (2023)
- [Towards Robust Ranker for Text Retrieval](https://mlsanity.com/paper/2206.08063/) (2022)
- [Which Examples to Annotate for In-Context Learning? Towards Effective and Efficient Selection](https://mlsanity.com/paper/2310.20046/) (2023)

## Built on by (most cited first, 2 of 2)

- [Semantic-Space Exploration and Exploitation in RLVR for LLM Reasoning](https://mlsanity.com/paper/2509.23808/) (2025)
- [AIM-CoT: Active Information-driven Multimodal Chain-of-Thought for Vision-Language Reasoning](https://mlsanity.com/paper/2509.25699/) (2025)

## Abstract (arXiv)

Large vision language models (LVLMs) achieve remarkable performance through Vision In-context Learning (VICL), a process that depends significantly on demonstrations retrieved from an extensive collection of annotated examples (retrieval database). Existing studies often assume that the retrieval database contains annotated examples for all labels. However, in real-world scenarios, delays in database updates or incomplete data annotation may result in the retrieval database containing labeled samples for only a subset of classes. We refer to this phenomenon as an incomplete retrieval database and define the in-context learning under this condition as Incomplete In-context Learning (IICL). To address this challenge, we propose Iterative Judgments and Integrated Prediction (IJIP), a two-stage framework designed to mitigate the limitations of IICL. The Iterative Judgments Stage reformulates an (boldsymbolm)-class classification problem into a series of (boldsymbolm) binary classification tasks, effectively converting the IICL setting into a standard VICL scenario. The Integrated Prediction Stage further refines the classification process by leveraging both the input image and the predictions from the Iterative Judgments Stage to enhance overall classification accuracy. IJIP demonstrates considerable performance across two LVLMs and two datasets under three distinct conditions of label incompleteness, achieving the highest accuracy of 93.9%. Notably, even in scenarios where labels are fully available, IJIP still achieves the best performance of all six baselines. Furthermore, IJIP can be directly applied to Prompt Learning and is adaptable to the text domain.