mlsanityData to 7 Oct 2026

Optimization of Retrieval-Augmented Generation Context with Outlier Detection

arXiv 2407.01403 ↗First posted 1 Jul 2024cs.IR cs.AI cs.CLcited by 1

On the map: Retrieval-augmented generation → RAG robustness and adaptive retrieval

Abstract (arXiv)

In this paper, we focus on methods to reduce the size and improve the quality of the prompt context required for question-answering systems. Attempts to increase the number of retrieved chunked documents and thereby enlarge the context related to the query can significantly complicate the processing and decrease the performance of a Large Language Model (LLM) when generating responses to queries. It is well known that a large set of documents retrieved from a database in response to a query may contain irrelevant information, which often leads to hallucinations in the resulting answers. Our goal is to select the most semantically relevant documents, treating the discarded ones as outliers. We propose and evaluate several methods for identifying outliers by creating features that utilize the distances of embedding vectors, retrieved from the vector database, to both the centroid and the query vectors. The methods were evaluated by comparing the similarities of the retrieved LLM responses to ground-truth answers obtained using the OpenAI GPT-4o model. It was found that the greatest improvements were achieved with increasing complexity of the questions and answers.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Placed in RAG robustness and adaptive retrieval, one of 15 directions in Retrieval-augmented generation. Builds on 5 of its 9 references that are in the map. First posted on arXiv 1 Jul 2024.

Builds on

5 of 9 references.

References · 5

  1. 2023Is ChatGPT Good at Search? Investigating Large Language Models as Re-Ranking Agentscited by 356
  2. 2024Retrieval-Augmented Generation for AI-Generated Content: A Surveycited by 352
  3. 2024xRAG: Extreme Context Compression for Retrieval-augmented Generation with One Tokencited by 123
  4. 2024Grounding Language Model with Chunking-Free In-Context Retrievalcited by 30
  5. 2024Dimensionality Reduction in Sentence Transformer Vector Databases with Fast Fourier Transformcited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Benchmarking Reward Hack Detection in Code Environments via Contrastive Analysiscited by 15

Similar, not cited

Close in wording, no citation either way

  1. 2024Improving Retrieval Augmented Open-Domain Question-Answering with Vectorized Contexts
  2. 2024Context Awareness Gate For Retrieval Augmented Generation
  3. 2024Context-augmented Retrieval: A Novel Framework for Fast Information Retrieval based Response Generation using Large Language Model ↗
  4. 2024Context Quality Matters in Training Fusion-in-Decoder for Extractive Open-Domain Question Answering
  5. 2025Retrieval Augmented Question Answering: When Should LLMs Admit Ignorance?
  6. 2024RE-RAG: Improving Open-Domain QA Performance and Interpretability with Relevance Estimator in Retrieval-Augmented Generation
  7. 2024ELOQ: Resources for Enhancing LLM Detection of Out-of-Scope Questions
  8. 2026Towards Unsupervised Adversarial Document Detection in Retrieval Augmented Generation Systems