mlsanityData to 7 Oct 2026

MARAGS: A Multi-Adapter System for Multi-Task Retrieval Augmented Generation Question Answering

arXiv 2409.03171 ↗First posted 5 Sep 2024cs.CLcited by 0

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

Abstract (arXiv)

In this paper we present a multi-adapter retrieval augmented generation system (MARAGS) for Meta's Comprehensive RAG (CRAG) competition for KDD CUP 2024. CRAG is a question answering dataset contains 3 different subtasks aimed at realistic question and answering RAG related tasks, with a diverse set of question topics, question types, time dynamic answers, and questions featuring entities of varying popularity. Our system follows a standard setup for web based RAG, which uses processed web pages to provide context for an LLM to produce generations, while also querying API endpoints for additional information. MARAGS also utilizes multiple different adapters to solve the various requirements for these tasks with a standard cross-encoder model for ranking candidate passages relevant for answering the question. Our system achieved 2nd place for Task 1 as well as 3rd place on Task 2.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in RAG robustness and adaptive retrieval, one of 15 directions in Retrieval-augmented generation. Builds on 3 of its 12 references that are in the map. First posted on arXiv 5 Sep 2024.

Builds on

3 of 12 references.

References · 3

  1. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,049
  2. 2019Parameter-Efficient Transfer Learning for NLPcited by 4,195
  3. 2018Iterative Learning with Open-set Noisy Labelscited by 108

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025QuIM-RAG: Advancing Retrieval-Augmented Generation with Inverted Question Matching for Enhanced QA Performance
  2. 2024CRAG -- Comprehensive RAG Benchmark
  3. 2024Revisiting the Solution of Meta KDD Cup 2024: CRAG
  4. 2026Augmenting Question Answering with A Hybrid RAG Approach
  5. 2024Retrieval-Augmented Generation for Domain-Specific Question Answering: A Case Study on Pittsburgh and CMU
  6. 2024A Comprehensive Survey of Retrieval-Augmented Generation (RAG): Evolution, Current Landscape and Future Directions
  7. 2024Know Your RAG: Dataset Taxonomy and Generation Strategies for Evaluating RAG Systems
  8. 2025A Systematic Review of Key Retrieval-Augmented Generation (RAG) Systems: Progress, Gaps, and Future Directions