Challenge: Existing methods for In-Context Learning (ICL) rely on a predetermined number of shots, leading to insufficient context or noise.
Approach: They propose a probe-based evaluation mechanism that utilizes output entropy to determine the optimal number of shots and leverages KV cache reuse for efficient inference.
Outcome: The proposed model achieves an average performance gain of 10% and a 4.64 speedup compared to state-of-the-art DBSA.

Similar Papers

On Many-Shot In-Context Learning for Long-Context Evaluation (2025.acl-long)

Copied to clipboard

Challenge: Existing benchmarks primarily evaluate long-context language models' retrieval capabilities.
Approach: They propose a benchmark to evaluate long-context language models' retrieval capabilities by using MANYICLBENCH.
Outcome: The proposed model performs better with additional demonstrations than translation and reasoning tasks.
Efficient Many-Shot In-Context Learning with Dynamic Block-Sparse Attention (2025.acl-long)

Copied to clipboard

Challenge: Many-shot in-context learning shifts computational burden from training-time to inference-time, making deployment of many-shot ICL challenging to justify in-practice.
Approach: They propose a method for retrieval-based many-shot in-context learning that uses blocks-sparse attention and retrieval of cached demonstrations to achieve comparable per-example latency to finetuning.
Outcome: The proposed method achieves comparable per-example latency to finetuning while maintaining on average >95% of the best method’s accuracy across strong ICL and finetuned baselines.
More is not always better? Enhancing Many-Shot In-Context Learning with Differentiated and Reweighting Objectives (2025.acl-long)

Copied to clipboard

Challenge: Large language models excel at few-shot in-context learning but performance plateaus as ICL demonstrations increase from a few to many.
Approach: They propose a novel optimization method that optimizes the negative log-likelihood objective and reweights the model to achieve many-shot performance.
Outcome: The proposed method achieves significant performance improvements across a large-scale dataset.
TokenSelect: Efficient Long-Context Inference and Length Extrapolation for LLMs via Dynamic Token-Level KV Cache Selection (2025.emnlp-main)

Copied to clipboard

Challenge: Rapid advances in Large Language Models have spurred demand for processing extended context sequences . however, performance degradation due to sequence lengths out-of-distribution and excessively long inference times are limiting LLMs in long-context scenarios.
Approach: They propose a training-free method for efficient and accurate long-context inference . they selectively involves a few critical KV cache tokens in attention calculation .
Outcome: The proposed method speeds up attention computation and accelerates inference time while reducing selection overhead.
Skill-Based Few-Shot Selection for In-Context Learning (2023.emnlp-main)

Copied to clipboard

Challenge: Existing methods based on pre-trained embeddings can be easily biased by surface features that are not important for the target task.
Approach: They propose a skill-based few-shot selection method for in-context learning . it generates skill-specific descriptions for each test case and candidate example .
Outcome: The proposed method significantly outperforms existing methods in five cross-domain semantic parsing datasets and six backbone models.
SCOPE: Optimizing Key-Value Cache Compression in Long-context Generation (2025.acl-long)

Copied to clipboard

Challenge: Excessive compression during the prefill phase impairs comprehension of reasoning tasks . SCOPE is a framework that performs KV cache optimization during the decoding and prefill phases .
Approach: They propose a framework that performs optimization during the prefill and decoding phases . they propose enabling a sliding strategy to select essential heavy hitters for the decoding phase .
Outcome: Experiments show that SCOPE can optimize key-value cache for long-context generation tasks . the framework can preserve essential information while minimizing memory usage and transfer .
Scaling Performance and Low-Resource Annotation with Many-Shot In-Context Learning for Named Entity Recognition (2026.findings-acl)

Copied to clipboard

Challenge: Existing studies on ICL for Named Entity Recognition (NER) have mainly explored few-shot settings, but the potential of scaling to hundreds of demonstrations has not been thoroughly investigated.
Approach: They evaluate various LLMs across multiple domains using hundreds of ICL examples and then assess the feasibility of using many-shot ICL as a data annotation framework.
Outcome: The proposed framework can be scaled to hundreds of examples and annotate and refining data for low-resource NER tasks.
C-ICL: Contrastive In-context Learning for Information Extraction (2024.findings-emnlp)

Copied to clipboard

Challenge: Existing methods for in-context learning with large language models focus on using correct or negative examples, ignoring the potential value of incorrect or negative samples.
Approach: They propose a few-shot technique that leverages both correct and incorrect sample constructions to create in-context learning demonstrations.
Outcome: The proposed technique outperforms previous few-shot in-context learning methods on a broad spectrum of related tasks.
Distilling Many-Shot In-Context Learning into a Cheat Sheet (2025.findings-emnlp)

Copied to clipboard

Challenge: Recent advances in large language models (LLMs) enable effective in-context learning with many-shot examples, but at the cost of high computational demand due to longer input tokens.
Approach: proposed cheat-sheet ICL distills information from many-shot ICL into a concise textual summary . experiment shows cheat- sheet ICL achieves comparable or better performance than many- shot ICL .
Outcome: Experiments on reasoning tasks show that cheat-sheet ICL achieves comparable or better performance than many-shot ICL with far fewer tokens.
Can Many-Shot In-Context Learning Help LLMs as Evaluators? A Preliminary Empirical Study (2025.coling-main)

Copied to clipboard

Challenge: Existing evaluation approaches to evaluate Large Language Models are affected by potential biases within LLMs.
Approach: They propose two many-shot In-Context Learning (ICL) prompt templates to help LLM evaluators mitigate potential biases.
Outcome: The proposed templates reduce biases by using in-context examples with model-generated rationales as references.

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