# Rectifying Demonstration Shortcut in In-Context Learning

arXiv: https://arxiv.org/abs/2403.09488 · HTML: https://mlsanity.com/paper/2403.09488/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 44 references that are in the map.
- First posted on arXiv 14 Mar 2024.

## Builds on (most cited first, 25 of 25)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [OPT: Open Pre-trained Transformer Language Models](https://mlsanity.com/paper/2205.01068/) (2022)
- [The Pile: An 800GB Dataset of Diverse Text for Language Modeling](https://mlsanity.com/paper/2101.00027/) (2020)
- [Character-level Convolutional Networks for Text Classification](https://mlsanity.com/paper/1509.01626/) (2015)
- [HuggingFace's Transformers: State-of-the-art Natural Language Processing](https://mlsanity.com/paper/1910.03771/) (2019)
- [Rethinking the Role of Demonstrations: What Makes In-Context Learning Work?](https://mlsanity.com/paper/2202.12837/) (2022)
- [Calibrate Before Use: Improving Few-Shot Performance of Language Models](https://mlsanity.com/paper/2102.09690/) (2021)
- [An Explanation of In-context Learning as Implicit Bayesian Inference](https://mlsanity.com/paper/2111.02080/) (2021)
- [Adversarial NLI: A New Benchmark for Natural Language Understanding](https://mlsanity.com/paper/1910.14599/) (2019)
- [GPT-NeoX-20B: An Open-Source Autoregressive Language Model](https://mlsanity.com/paper/2204.06745/) (2022)
- [Prompt Programming for Large Language Models: Beyond the Few-Shot Paradigm](https://mlsanity.com/paper/2102.07350/) (2021)
- [Larger language models do in-context learning differently](https://mlsanity.com/paper/2303.03846/) (2023)
- [Social Bias Frames: Reasoning about Social and Power Implications of Language](https://mlsanity.com/paper/1911.03891/) (2019)
- [Good Debt or Bad Debt: Detecting Semantic Orientations in Economic Texts](https://mlsanity.com/paper/1307.5336/) (2013)
- [Surface Form Competition: Why the Highest Probability Answer Isn't Always Right](https://mlsanity.com/paper/2104.08315/) (2021)
- [SemEval-2019 Task 6: Identifying and Categorizing Offensive Language in Social Media (OffensEval)](https://mlsanity.com/paper/1903.08983/) (2019)
- [Hate Speech Dataset from a White Supremacy Forum](https://mlsanity.com/paper/1809.04444/) (2018)
- [What In-Context Learning "Learns" In-Context: Disentangling Task Recognition and Task Learning](https://mlsanity.com/paper/2305.09731/) (2023)
- [What and How does In-Context Learning Learn? Bayesian Model Averaging, Parameterization, and Generalization](https://mlsanity.com/paper/2305.19420/) (2023)
- [Batch Calibration: Rethinking Calibration for In-Context Learning and Prompt Engineering](https://mlsanity.com/paper/2309.17249/) (2023)
- [Mitigating Label Biases for In-context Learning](https://mlsanity.com/paper/2305.19148/) (2023)
- [Large Language Models Can be Lazy Learners: Analyze Shortcuts in In-Context Learning](https://mlsanity.com/paper/2305.17256/) (2023)
- [Investigating Societal Biases in a Poetry Composition System](https://mlsanity.com/paper/2011.02686/) (2020)
- [Generative Calibration for In-context Learning](https://mlsanity.com/paper/2310.10266/) (2023)

## Built on by (most cited first, 9 of 9)

- [Shortcut Learning in In-Context Learning: A Survey](https://mlsanity.com/paper/2411.02018/) (2024)
- [Context Tuning for In-Context Optimization](https://mlsanity.com/paper/2507.04221/) (2025)
- [Mitigating Selection Bias in Large Language Models via Permutation-Aware GRPO](https://mlsanity.com/paper/2603.21016/) (2026)
- [Exploring Explanations Improves the Robustness of In-Context Learning](https://mlsanity.com/paper/2506.02378/) (2025)
- [PLR: Plackett-Luce for Reordering In-Context Learning Examples](https://mlsanity.com/paper/2603.21373/) (2026)
- [Limitations of Automated Simulatability: LLM Simulators Can Bypass Explanations](https://mlsanity.com/paper/2609.08585/) (2026)
- [When Context Misleads: In-context Learning with Jurisdiction in Large Language Models](https://mlsanity.com/paper/2609.27603/) (2026)
- [Lexical Redefinition Reveals Context-Sensitive Instruction Following](https://mlsanity.com/paper/2610.16952/) (2026)
- [Towards Universal Calibration for In-Context Classification](https://mlsanity.com/paper/2610.17096/) (2026)

## Abstract (arXiv)

Large language models (LLMs) are able to solve various tasks with only a few demonstrations utilizing their in-context learning (ICL) abilities. However, LLMs often rely on their pre-trained semantic priors of demonstrations rather than on the input-label relationships to proceed with ICL prediction. In this work, we term this phenomenon as the 'Demonstration Shortcut'. While previous works have primarily focused on improving ICL prediction results for predefined tasks, we aim to rectify the Demonstration Shortcut, thereby enabling the LLM to effectively learn new input-label relationships from demonstrations. To achieve this, we introduce In-Context Calibration, a demonstration-aware calibration method. We evaluate the effectiveness of the proposed method in two settings: (1) the Original ICL Task using the standard label space and (2) the Task Learning setting, where the label space is replaced with semantically unrelated tokens. In both settings, In-Context Calibration demonstrates substantial improvements, with results generalized across three LLM families (OPT, GPT, and Llama2) under various configurations.