Retrieval Augmented LLM

Retrieval-Augmented Language Models (RALMs) enhance large language models (LLMs) by incorporating external knowledge sources to address limitations like factual inaccuracies and a lack of specialized knowledge. Current research focuses on improving efficiency through context compression techniques, optimizing retrieval strategies (e.g., using keyword-based or emotion-aware retrieval), and developing methods to intelligently decide when to utilize retrieved information versus the LLM's internal knowledge. This approach significantly improves performance on various tasks, including question answering, misinformation detection, and scientific reasoning, offering a powerful paradigm for building more accurate and reliable AI systems across diverse domains.

Papers

November 1, 2024

Provenance: A Light-weight Fact-checker for Retrieval Augmented LLM Generation Output
Hithesh Sankararaman, Mohammed Nasheed Yasin, Tanner Sorensen, Alessandro Di Bari, Andreas Stolcke
Fact Checking Data Provenance Generation Capability Retrieval Augmented LLM

October 11, 2024

Enhancing Long Context Performance in LLMs Through Inner Loop Query Mechanism
Yimin Tang, Yurong Xu, Ning Yan, Masood Mortazavi
Large Language Model Medical LLM Long Context Functional Mechanism Short Term Memory Retrieval Augmented LLM

September 11, 2024

Learning to Compress Contexts for Efficient Knowledge-based Visual Question Answering
Weixi Weng, Jieming Zhu, Hao Zhang, Xiaojun Meng, Rui Zhang, Chun Yuan
LeArning Abstract High Efficiency Multimodal Large Language Model Knowledge Based Visual Question Answering Context Compression Retrieval Augmented LLM

August 21, 2024

Ancient Wisdom, Modern Tools: Exploring Retrieval-Augmented LLMs for Ancient Indian Philosophy
Priyanka Mandikal
Information Retrieval Deriving Wisdom Ancient Text Retrieval Augmented LLM

June 16, 2024

RAEmoLLM: Retrieval Augmented LLMs for Cross-Domain Misinformation Detection Using In-Context Learning based on Emotional Information
Zhiwei Liu, Kailai Yang, Qianqian Xie, Christine de Kock, Sophia Ananiadou, Eduard Hovy
Context Learning Target Emotion Misinformation Detection Misinformation Campaign Fact Checking Benchmark Domain Fake News Detection Retrieval Augmented LLM

April 30, 2024

When to Retrieve: Teaching LLMs to Utilize Information Retrieval Effectively
Tiziano Labruna, Jon Ander Campos, Gorka Azkune
Large Language Model Question Answering HotPotQA Dataset Retrieval Augmented LLM Ad Hoc Retrieval

January 22, 2024

Blinded by Generated Contexts: How Language Models Merge Generated and Retrieved Contexts When Knowledge Conflicts?
Hexiang Tan, Fei Sun, Wanli Yang, Yuanzhuo Wang, Qi Cao, Xueqi Cheng
Language Model Context Information Knowledge Conflict Context Retrieval Context Generation LLM Based Augmentation Retrieval Augmented LLM

November 15, 2023

Pearl: Personalizing Large Language Model Writing Assistants with Generation-Calibrated Retrievers
Sheshera Mysore, Zhuoran Lu, Mengting Wan, Longqi Yang, Bahareh Sarrafzadeh, Steve Menezes, Tina Baghaee, Emmanuel Barajas Gonzalez, Jennifer Neville, Tara Safavi
Social Medium Preference Based Reinforcement Learning Historical Document Writing Assistant Personalized Generation Retrieval Augmented LLM

November 7, 2023

Evaluating the Effectiveness of Retrieval-Augmented Large Language Models in Scientific Document Reasoning
Sai Munikoti, Anurag Acharya, Sridevi Wagle, Sameera Horawalavithana
Large Language Model Large Corpus Retrieval Augmented LLM

October 11, 2023

InstructRetro: Instruction Tuning post Retrieval-Augmented Pretraining
Boxin Wang, Wei Ping, Lawrence McAfee, Peng Xu, Bo Li, Mohammad Shoeybi, Bryan Catanzaro
Zero Shot Human Instruction Retrieval Augmented Augmentation Method MPT 7b Instruct POST Exploration Retrieval Augmented LLM Better GPT

October 4, 2023

Retrieval meets Long Context Large Language Models
Peng Xu, Wei Ping, Xianchao Wu, Lawrence McAfee, Chen Zhu, Zihan Liu, Sandeep Subramanian, Evelina Bakhturina, Mohammad Shoeybi, Bryan Catanzaro
Large Language Model App to App Retrieval Retrieval Augmentation Long Context Large Language Model Long Range Context Retrieval Augmented LLM

May 23, 2023

Query Rewriting for Retrieval-Augmented Large Language Models
Xinbei Ma, Yeyun Gong, Pengcheng He, Hai Zhao, Nan Duan
Large Language Model Language Model Query Information Retrieval Augmented LLM

Retrieval Augmented LLM

Papers

Provenance: A Light-weight Fact-checker for Retrieval Augmented LLM Generation Output

Enhancing Long Context Performance in LLMs Through Inner Loop Query Mechanism

Learning to Compress Contexts for Efficient Knowledge-based Visual Question Answering

Ancient Wisdom, Modern Tools: Exploring Retrieval-Augmented LLMs for Ancient Indian Philosophy

RAEmoLLM: Retrieval Augmented LLMs for Cross-Domain Misinformation Detection Using In-Context Learning based on Emotional Information

When to Retrieve: Teaching LLMs to Utilize Information Retrieval Effectively

Blinded by Generated Contexts: How Language Models Merge Generated and Retrieved Contexts When Knowledge Conflicts?

Pearl: Personalizing Large Language Model Writing Assistants with Generation-Calibrated Retrievers

Evaluating the Effectiveness of Retrieval-Augmented Large Language Models in Scientific Document Reasoning

InstructRetro: Instruction Tuning post Retrieval-Augmented Pretraining

Retrieval meets Long Context Large Language Models

Query Rewriting for Retrieval-Augmented Large Language Models