Challenge: Recent studies have explored the working mechanisms of In-Context Learning (ICL) however, they mainly focus on classification and simple generation tasks, limiting their broader application to more complex generation tasks in practice.
Approach: They propose an efficient Progressive In-Context Alignment method that embeds the task function learned from demonstrations into the separator token representation.
Outcome: The proposed method surpasses vanilla ICL and achieves comparable performance to other alignment tuning methods.

Similar Papers

How Far Can In-Context Alignment Go? Exploring the State of In-Context Alignment (2024.findings-emnlp)

Copied to clipboard

Challenge: Recent studies have demonstrated that In-Context Learning (ICA) can align Large Language Models (LLMs) with human preferences without requiring parameter adjustments.
Approach: They investigate the effectiveness of each part in enabling ICA to function effectively and examine how variants in these parts impact alignment performance.
Outcome: The proposed model can comprehend human instructions without parameter adjustments.
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.
FiD-ICL: A Fusion-in-Decoder Approach for Efficient In-Context Learning (2023.acl-long)

Copied to clipboard

Challenge: Large pre-trained models are capable of few-shot in-context learning (ICL) however, concatenated demonstrations are often excessively long and require additional computation.
Approach: They propose to apply fusion-in-decoder (FiD) models to perform few-shot in-context learning (ICL) they propose to use concatenation-based, early-fusion, intermediate- and late-fusion methods to improve efficiency .
Outcome: The proposed methods outperform concatenation-based models on 11 held-out tasks.
DeCoVec: Building Decoding Space based Task Vector for Large Language Models via In-Context Learning (2026.findings-acl)

Copied to clipboard

Challenge: Existing approaches to steering large language models require fine-tuning or manipulation of internal states, limiting their flexibility and scalability.
Approach: They propose a framework that constructs task vectors directly in the decoding space by leveraging in-context learning.
Outcome: The proposed framework outperforms standard few-shot baselines on TruthfulQA, Math-500, and AQUA-RAT with gains up to +5.50 accuracy.
Beyond Output Matching: Bidirectional Alignment for Enhanced In-Context Learning (2025.acl-long)

Copied to clipboard

Challenge: Existing methods to train student models on the generated outputs of teacher models are not efficient for ICL.
Approach: They propose to align the output of smaller (student) models with that of larger (teacher) models by incorporating a ranking loss and aligning the token-level output distribution.
Outcome: The proposed model outperforms baseline models on a variety of tasks involving language understanding, reasoning, and coding.
Beyond Demonstrations: Dynamic Vector Construction from Latent Representations (2025.emnlp-main)

Copied to clipboard

Challenge: Existing methods for In-Context Learning (ICL) are sensitive to ICL-specific factors and rely on heuristic-based injection positions.
Approach: They propose a method that extracts task-relevant representations from large language models and reinjects them during inference.
Outcome: The proposed method outperforms few-shot In-Context Learning (ICL) and LoRA methods without repeated demonstration processing.
Pre-Training to Learn in Context (2023.acl-long)

Copied to clipboard

Challenge: Pre-trained language models are not explicitly trained to learn in context.
Approach: They propose a framework to enhance in-context learning by pre-training language models on a large collection of "intrinsic tasks" they evaluate the in-constitution learning performance of the model trained with PICL on seven widely-used text classification datasets and the Super-NaturalInstrctions benchmark .
Outcome: The proposed framework outperforms larger language models with nearly 4x parameters on seven widely-used datasets and the Super-NaturalInstrctions benchmark.
SADA: Bridging In-Context Learning and Fine-Tuning via State-Aligned Distillation Adapters (2026.acl-long)

Copied to clipboard

Challenge: Prompt-based in-context learning and parameter fine-tuning are dominant paradigms for incorporating external information into large language models, but they incur high inference costs or require expensive retraining.
Approach: They propose to convert prompts into temporary adapter weights to bridge this gap by converting prompts to temporary adapters.
Outcome: The proposed model outperforms baselines on long-context language modeling and downstream NLU and summarization benchmarks while significantly reducing memory footprint and latency.
Enhancing In-Context Learning via Implicit Demonstration Augmentation (2024.acl-long)

Copied to clipboard

Challenge: In-context learning (ICL) is a new paradigm for pre-trained language models that can make predictions for unseen inputs without updating parameters.
Approach: They propose a method that enables a model to augmented copies of a demonstration by leveraging their deep feature distribution and a logit calibration mechanism.
Outcome: The proposed method significantly improves the average and worst-case accuracy across diverse PLMs and tasks.
What In-Context Learning “Learns” In-Context: Disentangling Task Recognition and Task Learning (2023.findings-acl)

Copied to clipboard

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.

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