Challenge: Large language models (LLMs) can perform in-context learning (ICL) with only a few demonstrations, but its mechanisms are not well-understood.
Approach: They characterize two ways in which LLMs leverage demonstrations to solve tasks with a few demonstrations.
Outcome: The proposed model achieves non-trivial performance with only TR, and TR does not improve with larger models or more demonstrations.

Similar Papers

What Do Language Models Learn in Context? The Structured Task Hypothesis. (2024.acl-long)

Copied to clipboard

Challenge: Pre-trained large language models have exhibited an impressive ability to learn in context across various domains, e.g., code generation, education, medicine and even medicine.
Approach: They taxonomize existing candidate theories into three competing hypotheses that explain LLMs’ ability to learn in context.
Outcome: The proposed model can learn a task from in-context examples presented in a demonstration and generalize it to the prompt.
Label Words as Local Task Vectors in In-Context Learning (2026.findings-acl)

Copied to clipboard

Challenge: Large Language Models (LLMs) have demonstrated remarkable abilities, one of the most important being in-context learning (ICL).
Approach: They hypothesized that the network creates a task vector in specific positions during ICL, which can be computed by averaging across the dataset.
Outcome: The proposed model can achieve zero-shot performance with dummy inputs comparable to few-shot learning by patching the global task vector.
In-Context Learning Creates Task Vectors (2023.findings-emnlp)

Copied to clipboard

Challenge: In-context learning (ICL) is a powerful new learning paradigm for Large Language Models (LLMs).
Approach: They propose to use a model with a prompt and a query to learn a mapping based on two examples to produce the output.
Outcome: The proposed model can learn functions from a simple structure based on a training set and a single task vector calculated from the training set.
Unveiling In-Context Learning: A Coordinate System to Understand Its Working Mechanism (2024.emnlp-main)

Copied to clipboard

Challenge: Large language models exhibit remarkable in-context learning (ICL) capabilities, but the underlying working mechanism of ICL remains unclear.
Approach: They propose a Two-Dimensional Coordinate System that unifies both views into a systematic framework that explains the behavior of ICL through two orthogonal variables: whether similar examples are presented in the demonstrations and whether LLMs can recognize the task.
Outcome: The proposed method can interpret ICL for generation tasks effectively.
The Mystery of In-Context Learning: A Comprehensive Survey on Interpretation and Analysis (2024.emnlp-main)

Copied to clipboard

Challenge: In-context learning (ICL) is a capability that enables large language models to excel in proficiency through demonstration examples.
Approach: They present a survey on the interpretation and analysis of in-context learning . they focus on theoretical and empirical perspectives on the concept .
Outcome: The proposed model can perform tasks with minimal examples without re-training and has demonstrated proficiency across various tasks with a minimal set of task-oriented examples.
Rethinking the Role of Demonstrations: What Makes In-Context Learning Work? (2022.emnlp-main)

Copied to clipboard

Challenge: Large language models can in-context learn by conditioning on a few input-label pairs and making predictions for new inputs.
Approach: They propose to use ground truth demonstrations to replace labels in demonstrations . they also show that other aspects of the demonstrations are key drivers of endtask performance .
Outcome: The proposed model outperforms zeroshot inference on a wide range of tasks using ground truth demonstrations.
Language Models can Exploit Cross-Task In-context Learning for Data-Scarce Novel Tasks (2024.acl-long)

Copied to clipboard

Challenge: Large Language Models (LLMs) have transformed NLP with their remarkable In-context Learning capabilities.
Approach: They propose to use large language models to generalize from labeled examples of predefined tasks to novel tasks . they use biological neurons and the Transformer architecture to study the potential for information sharing across tasks.
Outcome: The proposed model can generalize from labeled examples of predefined tasks to novel tasks despite no examples from the target task in the context.
Learning vs Retrieval: The Role of In-Context Examples in Regression with Large Language Models (2025.naacl-long)

Copied to clipboard

Challenge: Existing studies on in-context learning mechanisms are not consistent . current research identifies two main approaches to explain the ICL mechanism .
Approach: They propose a framework for evaluating in-context learning mechanisms by focusing on regression tasks.
Outcome: The proposed framework can solve regression problems and then measure the extent to which the LLM retrieves its internal knowledge versus learning from in-context examples.
Unraveling the Mechanics of Learning-Based Demonstration Selection for In-Context Learning (2025.acl-long)

Copied to clipboard

Challenge: Recent learning-based demonstration selection methods have proven beneficial to in-context learning (ICL) by choosing more useful exemplars.
Approach: They propose two methods to capture task-agnostic similarities between input and output of LLMs.
Outcome: The proposed methods integrate task-agnostic similarities of different levels between input and output of exemplars and test cases to eliminate costly data collection.
Label Words are Anchors: An Information Flow Perspective for Understanding In-Context Learning (2023.emnlp-main)

Copied to clipboard

Challenge: In-context learning (ICL) is a promising capability for large language models (LLMs) but its underlying mechanism remains unexplored.
Approach: They propose a demonstration compression technique to expedite inference and an analysis framework for diagnosing ICL errors in GPT2-XL.
Outcome: The proposed method improves ICL performance and expedites inference.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations