Pith. sign in

REVIEW 6 cited by

The Chronicles of RAG: The Retriever, the Chunk and the Generator

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2401.07883 v1 pith:M2LUBNHS submitted 2024-01-15 cs.LG cs.AIcs.CLcs.IR

classification cs.LGcs.AIcs.CLcs.IR
keywords baselinechallengesdatafocusinggenerationqualityretrievalretriever
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Retrieval Augmented Generation (RAG) has become one of the most popular paradigms for enabling LLMs to access external data, and also as a mechanism for grounding to mitigate against hallucinations. When implementing RAG you can face several challenges like effective integration of retrieval models, efficient representation learning, data diversity, computational efficiency optimization, evaluation, and quality of text generation. Given all these challenges, every day a new technique to improve RAG appears, making it unfeasible to experiment with all combinations for your problem. In this context, this paper presents good practices to implement, optimize, and evaluate RAG for the Brazilian Portuguese language, focusing on the establishment of a simple pipeline for inference and experiments. We explored a diverse set of methods to answer questions about the first Harry Potter book. To generate the answers we used the OpenAI's gpt-4, gpt-4-1106-preview, gpt-3.5-turbo-1106, and Google's Gemini Pro. Focusing on the quality of the retriever, our approach achieved an improvement of MRR@10 by 35.4% compared to the baseline. When optimizing the input size in the application, we observed that it is possible to further enhance it by 2.4%. Finally, we present the complete architecture of the RAG with our recommendations. As result, we moved from a baseline of 57.88% to a maximum relative score of 98.61%.

Discussion (0). Sign in to comment.

Forward citations

Cited by 6 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. UniC-RAG: Universal Knowledge Corruption Attacks to Retrieval-Augmented Generation

    cs.CR 2025-08 conditional novelty 6.0 of 10

    A universal knowledge-corruption attack uses as few as 100 crafted texts to hijack responses to thousands of diverse user queries in retrieval-augmented generation.

  2. EraRAG: Efficient and Incremental Retrieval Augmented Generation for Growing Corpora

    cs.IR 2025-06 conditional novelty 6.0 of 10

    EraRAG uses hyperplane-based locality-sensitive hashing to build a hierarchical retrieval graph whose affected regions only are re-summarized when new documents arrive, cutting update cost by up to an order of magnitude.

  3. Can LLMs Replace Humans During Code Chunking?

    cs.SE 2025-06 reject novelty 6.0 of 10

    LLM-generated partitions of legacy code yield documentation that LLM judges rate as up to 20% more factual and up to 10% more useful than documentation based on human expert partitions.

  4. A Deep Dive into Retrieval-Augmented Generation for Code Completion: Experience on WeChat

    cs.SE 2025-07 conditional novelty 5.0 of 10

    On WeChat's closed-source codebase, similarity-based RAG with combined BM25 and GTE-Qwen retrieval improves open-source LLM code completion more than identifier-based retrieval, with gains growing for larger models.

  5. DyG-RAG: Dynamic Graph Retrieval-Augmented Generation with Event-Centric Reasoning

    cs.IR 2025-07 conditional novelty 5.0 of 10

    DyG-RAG builds a dynamic event graph from time-anchored event units and uses timeline retrieval with Time-CoT prompting to answer temporal questions.

  6. Markov-Enhanced Clustering for Long Document Summarization: Tackling the 'Lost in the Middle' Challenge with Large Language Models

    cs.CL 2025-06 conditional novelty 5.0 of 10

    A Markov-chain ordered clustering pipeline improves reported ROUGE and coherence over direct LLM summarization on BookSum, with small unverified gains.

Pith tools