Retrieval Augmented in Context Learning

Retrieval Augmented In-Context Learning (RA-ICL) enhances large language models (LLMs) by supplementing their context with relevant information retrieved from external knowledge bases. Current research focuses on improving the accuracy and reliability of LLMs, particularly addressing issues like hallucinations and improving performance on knowledge-intensive tasks, often employing techniques like maximum marginal relevance scoring and hierarchical graph structures to manage retrieved information. This approach shows promise in various applications, including clinical decision-making, hierarchical text classification, and autonomous driving, by improving the factual accuracy and generalizability of LLMs while reducing reliance on extensive fine-tuning.

Papers

September 16, 2024

HALO: Hallucination Analysis and Learning Optimization to Empower LLMs with Retrieval-Augmented Context for Guided Clinical Decision Making
Sumera Anjum, Hanzhi Zhang, Wenjun Zhou, Eun Jin Paek, Xiaopeng Zhao, Yunhe Feng
Large Language Model Natural Language Processing Task Content Hallucination Answer Generation Medical Question Answering Clinical Decision Support Hallucination Evaluation Based Optimization Retrieval Augmented in Context Learning

June 25, 2024

Retrieval-style In-Context Learning for Few-shot Hierarchical Text Classification
Huiyao Chen, Yu Zhao, Zulong Chen, Mengjia Wang, Liangyue Li, Meishan Zhang, Min Zhang
Shot Learning Shot Text Classification Hierarchical Text Classification Label Hierarchy Hierarchical Label Label Representation Retrieval Augmented in Context Learning

June 20, 2024

VLM Agents Generate Their Own Memories: Distilling Experience into Embodied Programs
Gabriel Sarch, Lawrence Jang, Michael J. Tarr, William W. Cohen, Kenneth Marino, Katerina Fragkiadaki
Continual LEArning Context Learning Handwritten Trajectory Cognitive Abstraction Multimodal Agent Shot in Context Learning Abstraction Learning Actionable Insight Retrieval Augmented in Context Learning

June 11, 2024

MINERS: Multilingual Language Models as Semantic Retrievers
Genta Indra Winata, Ruochen Zhang, David Ifeoluwa Adelani
Multilingual Language Model Semantic Retrieval Retrieval Augmented in Context Learning

May 24, 2024

Evaluating and Safeguarding the Adversarial Robustness of Retrieval-Based In-Context Learning
Simon Yu, Jie He, Pasquale Minervini, Jeff Z. Pan
Adversarial Attack Context Learning Adversarial Training Adversarial Robustness Retrieval Augmented Retrieval Augmented in Context Learning

February 16, 2024

RAG-Driver: Generalisable Driving Explanations with Retrieval-Augmented In-Context Learning in Multi-Modal Large Language Model
Jianhao Yuan, Shuyang Sun, Daniel Omeiza, Bo Zhao, Paul Newman, Lars Kunze, Matthew Gadd
Autonomous Driving Line by Line Explanation High Explainability Stronger Generalizability Multi Modal Large Language Model Natural Language Explanation Highway Driving Retrieval Augmented in Context Learning

February 14, 2024

HGOT: Hierarchical Graph of Thoughts for Retrieval-Augmented In-Context Learning in Factuality Evaluation
Yihao Fang, Stephen W. Thomas, Xiaodan Zhu
Large Language Model Context Learning Thought Reasoning Hierarchical Graph Thought Structure Retrieval Augmented in Context Learning

November 11, 2023

From Classification to Generation: Insights into Crosslingual Retrieval Augmented ICL
Xiaoqian Li, Ercong Nie, Sheng Liang
Classification Code Context Learning Faithful Generation DCU Insight AQ Multilingual Pre Trained Language Model Retrieval Augmented in Context Learning

May 23, 2023

Dr.ICL: Demonstration-Retrieved In-context Learning
Man Luo, Xin Xu, Zhuyun Dai, Panupong Pasupat, Mehran Kazemi, Chitta Baral, Vaiva Imbrasaite, Vincent Y Zhao
Large Language Model Context Learning Task Demonstration Retrieval Augmented in Context Learning

December 28, 2022

Demonstrate-Search-Predict: Composing retrieval and language models for knowledge-intensive NLP
Omar Khattab, Keshav Santhanam, Xiang Lisa Li, David Hall, Percy Liang, Christopher Potts, Matei Zaharia
Language Model App to App Retrieval Retrieval Model Knowledge Intensive Frozen Language Model Self Training Pipeline Retrieval Augmented in Context Learning Visual Predictive

Retrieval Augmented in Context Learning

Papers

HALO: Hallucination Analysis and Learning Optimization to Empower LLMs with Retrieval-Augmented Context for Guided Clinical Decision Making

Retrieval-style In-Context Learning for Few-shot Hierarchical Text Classification

VLM Agents Generate Their Own Memories: Distilling Experience into Embodied Programs

MINERS: Multilingual Language Models as Semantic Retrievers

Evaluating and Safeguarding the Adversarial Robustness of Retrieval-Based In-Context Learning

RAG-Driver: Generalisable Driving Explanations with Retrieval-Augmented In-Context Learning in Multi-Modal Large Language Model

HGOT: Hierarchical Graph of Thoughts for Retrieval-Augmented In-Context Learning in Factuality Evaluation

From Classification to Generation: Insights into Crosslingual Retrieval Augmented ICL

Dr.ICL: Demonstration-Retrieved In-context Learning

Demonstrate-Search-Predict: Composing retrieval and language models for knowledge-intensive NLP