Fetching the paper…

Reading the bibliography…

2024

Introducing a new hyper-parameter for RAG: Context Window Utilization

Juvekar, Kush, Purwar, Anupam

Original
PDF
Post on X

Understand

This paper introduces a new hyper-parameter for Retrieval-Augmented Generation (RAG) systems called Context Window Utilization.

RAG systems enhance generative models by incorporating relevant information retrieved from external knowledge bases, improving the factual accuracy and contextual relevance of generated responses.
The size of the text chunks retrieved and processed is a critical factor influencing RAG performance.
This study aims to identify the optimal chunk size that maximizes answer generation quality.

Introducing a new hyper-parameter for RAG: Context Window Utilization · Around

Built on

Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks
Original
Patrick Lewis, Ethan Perez, Aleksandra Piktus, Fabio Petroni, Vladimir Karpukhin, Naman Goyal, Heinrich Küttler, Mike Lewis, Wen tau Yih, Tim Rocktäschel, Sebastian Riedel, and Douwe Kiela. 2021 · 2005
Earlier work this paper cites.
MS MARCO: A Human Generated MAchine Reading COmprehension Dataset
Original
Payal Bajaj, Daniel Campos, Nick Craswell, Li Deng, Jianfeng Gao, Xiaodong Liu, Rangan Majumder, Andrew McNamara, Bhaskar Mitra, Tri Nguyen, Mir Rosenberg, Xia Song, Alina Stoica, Saurabh Tiwary, and Tong Wang. 2018 · 2018
Earlier work this paper cites.
Natural Questions: A Benchmark for Question Answering Research
Tom Kwiatkowski, Jennimaria Palomaki, Olivia Redfield, Michael Collins, Ankur Parikh, Chris Alberti, Danielle Epstein, Illia Polosukhin, Jacob Devlin, Kenton Lee, Kristina Toutanova, Llion Jones, Matthew Kelcey, Ming-Wei Chang, Andrew M. Dai, Jakob Uszkoreit, Quoc Le, and Slav Petrov. 2019 · 2019
Earlier work this paper cites.
Semantic Answer Similarity for Evaluating Question Answering Models
Original
Julian Risch, Timo Möller, Julian Gutsch, and Malte Pietsch. 2021 · 2021
Earlier work this paper cites.
BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Models
Original
Nandan Thakur, Nils Reimers, Andreas Rücklé, Abhishek Srivastava, and Iryna Gurevych. 2021 · 2021
Earlier work this paper cites.
Exploring Dual Encoder Architectures for Question Answering
Original
Zhe Dong, Jianmo Ni, Daniel M. Bikel, Enrique Alfonseca, Yuan Wang, Chen Qu, and Imed Zitouni. 2022 · 2022
Earlier work this paper cites.
Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection
Original
Akari Asai, Zeqiu Wu, Yizhong Wang, Avirup Sil, and Hannaneh Hajishirzi. 2023 · 2023
Earlier work this paper cites.
Dense X Retrieval: What Retrieval Granularity Should We Use?
Original
Tong Chen, Hongwei Wang, Sihao Chen, Wenhao Yu, Kaixin Ma, Xinran Zhao, Hongming Zhang, and Dong Yu. 2023 · 2023
Earlier work this paper cites.
MTEB: Massive Text Embedding Benchmark
Original
Niklas Muennighoff, Nouamane Tazi, Loïc Magne, and Nils Reimers. 2023 · 2023
Earlier work this paper cites.
Keyword Augmented Retrieval: Novel framework for Information Retrieval integrated with speech interface
Original
Anupam Purwar and Rahul Sundar. 2023 · 2023
Earlier work this paper cites.
C-Pack: Packaged Resources To Advance General Chinese Embedding
Original
Shitao Xiao, Zheng Liu, Peitian Zhang, and Niklas Muennighoff. 2023 · 2023
Earlier work this paper cites.
Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena
Original
Lianmin Zheng, Wei-Lin Chiang, Ying Sheng, Siyuan Zhuang, Zhanghao Wu, Yonghao Zhuang, Zi Lin, Zhuohan Li, Dacheng Li, Eric P. Xing, Hao Zhang, Joseph E. Gonzalez, and Ion Stoica. 2023 · 2023
Earlier work this paper cites.
CultureVo: The Serious Game of Utilizing Gen AI for Enhancing Cultural Intelligence
Original
Ajita Agarwala, Anupam Purwar, and Viswanadhasai Rao. 2024 · 2024
Earlier work this paper cites.

Similar

Au Large — mistral.ai
Mistral AI. 2024 · 2024
Cited alongside, same era.
Llama 3 Model Card
AI@Meta. 2024 · 2024
Cited alongside, same era.
Evaluating the Efficacy of Open-Source LLMs in Enterprise-Specific RAG Systems: A Comparative Study of Performance and Scalability
Original
Gautam B and Anupam Purwar. 2024 · 2024
Cited alongside, same era.
Seven Failure Points When Engineering a Retrieval Augmented Generation System
Original
Scott Barnett, Stefanus Kurniawan, Srikanth Thudumu, Zach Brannelly, and Mohamed Abdelrazek. 2024 · 2024
Cited alongside, same era.
BGE M3-Embedding: Multi-Lingual, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillation
Original
Jianlv Chen, Shitao Xiao, Peitian Zhang, Kun Luo, Defu Lian, and Zheng Liu. 2024 · 2024
Cited alongside, same era.

Then

BABILong: Testing the Limits of LLMs with Long Context Reasoning-in-a-Haystack
Original
Yuri Kuratov, Aydar Bulatov, Petr Anokhin, Ivan Rodkin, Dmitry Sorokin, Artyom Sorokin, and Mikhail Burtsev. 2024 · 2024
Closest in time.
Summary of a Haystack: A Challenge to Long-Context LLMs and RAG Systems
Original
Philippe Laban, Alexander R. Fabbri, Caiming Xiong, and Chien-Sheng Wu. 2024 · 2024
Closest in time.
Long Context RAG Performance of LLMs — databricks.com
Quinn Leng, Jacob Portes, Sam Havens, Matei Zaharia, and Michael Carbin. 2024 · 2024
Closest in time.
Same Task, More Tokens: the Impact of Input Length on the Reasoning Performance of Large Language Models
Original
Mosh Levy, Alon Jacoby, and Yoav Goldberg. 2024 · 2024
Closest in time.
Long-context LLMs Struggle with Long In-context Learning
Original

Beyond the bibliography

alphaXiv searches the wider corpus for related work and actual follow-ups.

Open on alphaXiv

alphaXiv is searching for related work…

LumberChunker: Long-Form Narrative Document Segmentation

André V. Duarte, João Marques, Miguel Graça, Miguel Freire, Lei Li, and Arlindo L. Oliveira. 2024 · 2024

Cited alongside, same era.

Context-augmented Retrieval: A Novel Framework for Fast Information Retrieval based Response Generation using Large Language Model

Sai Ganesh, Anupam Purwar, and Gautam B. 2024 · 2024

Cited alongside, same era.

VidyaRANG: Conversational Learning Based Platform powered by Large Language Model

Chitranshu Harbola and Anupam Purwar. 2024 · 2024

Cited alongside, same era.

RULER: What’s the Real Context Size of Your Long-Context Language Models?

Cheng-Ping Hsieh, Simeng Sun, Samuel Kriman, Shantanu Acharya, Dima Rekesh, Fei Jia, Yang Zhang, and Boris Ginsburg. 2024 · 2024

Cited alongside, same era.

Mixtral of Experts

Albert Q. Jiang, Alexandre Sablayrolles, Antoine Roux, Arthur Mensch, Blanche Savary, Chris Bamford, Devendra Singh Chaplot, Diego de las Casas, Emma Bou Hanna, Florian Bressand, Gianna Lengyel, Guillaume Bour, Guillaume Lample, Lélio Renard Lavaud, Lucile Saulnier, Marie-Anne Lachaux, Pierre Stock, Sandeep Subramanian, Sophia Yang, Szymon Antoniak, Teven Le Scao, Théophile Gervet, Thibaut Lavril, Thomas Wang, Timothée Lacroix, and William El Sayed. 2024 · 2024

Cited alongside, same era.

GitHub - microsoft/graphrag: A modular graph-based Retrieval-Augmented Generation (RAG) system — github.com

Steven Truitt Jonathan Larson. 2024 · 2024

Cited alongside, same era.

COS-Mix: Cosine Similarity and Distance Fusion for Improved Information Retrieval

Kush Juvekar and Anupam Purwar. 2024 · 2024

Cited alongside, same era.

Tianle Li, Ge Zhang, Quy Duc Do, Xiang Yue, and Wenhu Chen. 2024 · 2024

Closest in time.

Introducing Meta Llama 3: The most capable openly available LLM to date — ai.meta.com

MetaAI. 2024 · 2024

Closest in time.

Models - OpenAI API

OpenAI. 2024 · 2024

Closest in time.

RAG vs. Long Context: Examining Frontier Large Language Models for Environmental Review Document Comprehension

Hung Phan, Anurag Acharya, Sarthak Chaturvedi, Shivam Sharma, Mike Parker, Dan Nally, Ali Jannesari, Karl Pazdernik, Mahantesh Halappanavar, Sai Munikoti, and Sameera Horawalavithana. 2024 · 2024

Closest in time.

BitPeak — bitpeak.pl

Konrad Rucinski. 2024 · 2024

Closest in time.

Chunking Strategies Optimization for Retrieval Augmented Generation (RAG) in the Context of… — thallyscostalat

thallyscostalat. 2024 · 2024

Closest in time.

Utilizing Large Language Models to Generate Synthetic Data to Increase the Performance of BERT-Based Neural Networks

Chancellor R. Woolsey, Prakash Bisht, Joshua Rothman, and Gondy Leroy. 2024 · 2024

Closest in time.

Corrective Retrieval Augmented Generation

Shi-Qi Yan, Jia-Chen Gu, Yun Zhu, and Zhen-Hua Ling. 2024 · 2024

Closest in time.