paper-with-me

Papers

In-Context Demonstration Selection with Cross Entropy Difference

2023-05-24 · Dan Iter, Reid Pryzant, Ruochen Xu, Shuohang Wang, Yang Liu, Yichong Xu, Chenguang Zhu

Large language models (LLMs) can use in-context demonstrations to improve performance on zero-shot tasks. However, selecting the best in-context examples is challenging because model performance can vary widely depending on the selected examples. We present a cross-entropy difference (CED) method for selecting in-context demonstrations. Our method is based on the observation that the effectiveness of in-context demonstrations negatively correlates with the perplexity of the test example by a language model that was finetuned on that demonstration. We utilize parameter efficient finetuning to train small models on training data that are used for computing the cross-entropy difference between a test example and every candidate in-context demonstration. This metric is used to rank and select in-context demonstrations independently for each test input. We evaluate our method on a mix-domain dataset that combines 8 benchmarks, representing 4 text generation tasks, showing that CED for in-context demonstration selection can improve performance for a variety of LLMs.

📄 PDF Abstract BibTeX arXiv:2305.14726

Code (1)

microsoft/lmops 공식 구현 jax

Tasks

Language ModelingLanguage ModellingText Generation

Methods 이 논문이 사용한 방법론

Test 설명 없음

Similar Papers 제목 키워드 기반

Learn to Select: Exploring Label Distribution Divergence for In-Context Demonstration Selection in Text Classification

2025-11-10 · Ye Jiang, Taihang Wang, Youzheng Liu, Yimin Wang 외 arxiv

In-context learning (ICL) for text classification, which uses a few input-label demonstrations to describe a task, has demonstrated impressive performance on large language models (LLMs). However, the selection of in-con…

Semantic SimilarityText Classification

Diversity You Can Actually Measure: A Fast, Model-Free Diversity Metric for Robotics Datasets

2026-03-12 · Sreevardhan Sirigiri, Nathan Samuel de Lara, Christopher Agia, Florian Shkurti 외 arxiv

Robotics datasets for imitation learning typically consist of long-horizon trajectories of different lengths over states, actions, and high-dimensional observations (e.g., RGB video), making it non-trivial to quantify di…

Curriculum Demonstration Selection for In-Context Learning

2024-11-27 · Duc Anh Vu, Nguyen Tran Cong Duy, Xiaobao Wu, Hoang Minh Nhat 외

Large Language Models (LLMs) have shown strong in-context learning (ICL) abilities with a few demonstrations. However, one critical challenge is how to select demonstrations to elicit the full potential of LLMs. In this …

In-Context Learning

DemoShapley: Valuation of Demonstrations for In-Context Learning

2024-10-10 · Shan Xie, Man Luo, Chadly Daniel Stern, Mengnan Du 외

Large language models (LLMs) leveraging in-context learning (ICL) have set new benchmarks in few-shot learning across various tasks without needing task-specific fine-tuning. However, extensive research has demonstrated …

FairnessFew-Shot LearningIn-Context Learning

Easier to Judge than to Find: Predicting In-Context Learning Success for Demonstration Selection

2026-05-18 · Haochun Wang, Chaofen Yang, Jiatong Liu, Jingbo Wang 외 arxiv

In-context learning (ICL) is highly sensitive to which demonstrations appear in the prompt, but selecting them is expensive because the space of possible demonstration contexts and combinations is enormous. We argue that…