mlsanityData to 7 Oct 2026

CORAL: Adaptive Retrieval Loop for Culturally-Aligned Multilingual RAG

arXiv 2604.25676 ↗First posted 28 Apr 2026cs.CL cs.AIcited by 0

On the map: Retrieval-augmented generation → Generation and context integration

Abstract (arXiv)

Multilingual retrieval-augmented generation (mRAG) is often implemented within a fixed retrieval space, typically via query or document translation or multilingual embedding vector representations. However, this approach may be inadequate for culturally grounded queries, in which retrieval-condition misalignment may occur. Even strong retrievers and generators may struggle to produce culturally relevant answers when sourcing evidence from inappropriate linguistic or regional contexts. To this end, we introduce CORAL (COntext-aware Retrieval with Agentic Loop, an adaptive retrieval methodology for mRAG that enables iterative refinement of both the retrieval space (corpora) and the retrieval probe (query) based on the quality of the evidence. The overall process includes: (1) selecting corpora, (2) retrieving documents, (3) critiquing evidence for relevance and cultural alignment, and (4) checking sufficiency. If the retrieved documents are insufficient to answer the query correctly, the system (5) reselects corpora and rewrites the query. Across two cultural QA benchmarks, CORAL achieves up to a 3.58%p accuracy improvement on low-resource languages relative to the strongest baselines.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Generation and context integration, one of 15 directions in Retrieval-augmented generation. Builds on 27 of its 43 references that are in the map. First posted on arXiv 28 Apr 2026.

Builds on

27 of 43 references.

Closest ancestors · 6

Same direction, newest first

  1. 2025Language Drift in Multilingual Retrieval-Augmented Generation: Characterization and Decoding-Time Mitigation13 Nov
  2. 2025Quality-Aware Translation Tagging in Multilingual RAG system27 Oct
  3. 2025On the Consistency of Multilingual Context Utilization in Retrieval-Augmented Generation1 Apr
  4. 2025Investigating Language Preference of Multilingual RAG Systems16 Feb
  5. 2024Multilingual Retrieval Augmented Generation for Culturally-Sensitive Tasks: A Benchmark for Cross-lingual Robustness2 Oct
  6. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks22 May

Other references · 21

  1. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
  2. 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflectioncited by 1,800
  3. 2025gpt-oss-120b & gpt-oss-20b Model Cardcited by 1,258
  4. 2020Language (Technology) is Power: A Critical Survey of "Bias" in NLPcited by 951
  5. 2022Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questionscited by 911
  6. 2020The State and Fate of Linguistic Diversity and Inclusion in the NLP Worldcited by 789
  7. 2023Fine-Tuning or Retrieval? Comparing Knowledge Injection in LLMscited by 175
  8. 2024BLEnD: A Benchmark for LLMs on Everyday Knowledge in Diverse Cultures and Languagescited by 171
  9. 2020MKQA: A Linguistically Diverse Benchmark for Multilingual Open Domain Question Answeringcited by 151
  10. 2024RQ-RAG: Learning to Refine Queries for Retrieval Augmented Generationcited by 144
  11. 2024CLIcK: A Benchmark Dataset of Cultural and Linguistic Intelligence in Koreancited by 65
  12. 2024PlanRAG: A Plan-then-Retrieval Augmented Generation for Generative Large Language Models as Decision Makerscited by 42
9 more
  1. 2024RATT: A Thought Structure for Coherent and Correct LLM Reasoningcited by 39
  2. 2023IterCQR: Iterative Conversational Query Reformulation with Retrieval Guidancecited by 20
  3. 2024MIRAGE-Bench: Automatic Multilingual Benchmark Arena for Retrieval-Augmented Generation Systemscited by 14
  4. 2025SelfAug: Mitigating Catastrophic Forgetting in Retrieval-Augmented Generation via Distribution Self-Alignmentcited by 9
  5. 2024A Hybrid RAG System with Comprehensive Enhancement on Complex Reasoningcited by 8
  6. 2025MEMERAG: A Multilingual End-to-End Meta-Evaluation Benchmark for Retrieval Augmented Generationcited by 7
  7. 2024BRIEF: Bridging Retrieval and Inference for Multi-hop Reasoning via Compressioncited by 5
  8. 2025Towards Geo-Culturally Grounded LLM Generationscited by 5
  9. 2025Relevance Isn't All You Need: Scaling RAG Systems With Inference-Time Compute Via Multi-Criteria Rerankingcited by 3

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026All Languages Matter: Understanding and Mitigating Language Bias in Multilingual RAG
  2. 2025The Cross-Lingual Cost: Retrieval Biases in RAG over Arabic-English Corpora
  3. 2024Enhancing Multilingual Information Retrieval in Mixed Human Resources Environments: A RAG Model Implementation for Multicultural Enterprise
  4. 2024Retrieval-augmented generation in multilingual settings
  5. 2026Knowledge-Graph Based Augmentation versus Retrieval Augmented Generation for Cultural-Related Question Answering
  6. 2025M4-RAG: A Massive-Scale Multilingual Multi-Cultural Multimodal RAG
  7. 2026AlignCultura: Towards Culturally Aligned Large Language Models?
  8. 2026Simorgh at SemEval-2026 task 7: Region-Aware Hybrid Retrieval for Low-Resource Cultural Reasoning in Multilingual Question Answering