mlsanityData to 7 Oct 2026

MORE: Multi-mOdal REtrieval Augmented Generative Commonsense Reasoning

arXiv 2402.13625 ↗First posted 21 Feb 2024cs.CLcited by 12

On the map: LLM reasoning → Multimodal reasoning

also in 1 more
Abstract (arXiv)

Since commonsense information has been recorded significantly less frequently than its existence, language models pre-trained by text generation have difficulty to learn sufficient commonsense knowledge. Several studies have leveraged text retrieval to augment the models' commonsense ability. Unlike text, images capture commonsense information inherently but little effort has been paid to effectively utilize them. In this work, we propose a novel Multi-mOdal REtrieval (MORE) augmentation framework, to leverage both text and images to enhance the commonsense ability of language models. Extensive experiments on the Common-Gen task have demonstrated the efficacy of MORE based on the pre-trained models of both single and multiple modalities.

Key facts. Cited by 12 papers in the map (data through 7 Oct 2026). Placed in Multimodal reasoning, one of 17 directions in LLM reasoning. Builds on 8 of its 53 references that are in the map. First posted on arXiv 21 Feb 2024.

Builds on

8 of 53 references.

References · 8

  1. 2023GPT-4 Technical Reportcited by 18,132
  2. 2021SimCSE: Simple Contrastive Learning of Sentence Embeddingscited by 2,168
  3. 2022Atlas: Few-shot Learning with Retrieval Augmented Language Modelscited by 940
  4. 2023REPLUG: Retrieval-Augmented Black-Box Language Modelscited by 786
  5. 2023RECOMP: Improving Retrieval-Augmented LMs with Compression and Selective Augmentationcited by 253
  6. 2023TCRA-LLM: Token Compression Retrieval Augmented Large Language Model for Inference Cost Reductioncited by 34
  7. 2022Visualize Before You Write: Imagination-Guided Open-Ended Text Generationcited by 30
  8. 2023Optimizing Retrieval-augmented Reader Models via Token Eliminationcited by 10

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 4; 2025: 6; 2026: 2.

12 papers.

  1. 2024Retrieval-Augmented Generation with Graphs (GraphRAG)cited by 170
  2. 2025Ask in Any Modality: A Comprehensive Survey on Multimodal Retrieval-Augmented Generationcited by 42
  3. 2024MRAG-Bench: Vision-Centric Evaluation for Retrieval-Augmented Multimodal Modelscited by 41
  4. 2025UniversalRAG: Retrieval-Augmented Generation over Corpora of Diverse Modalities and Granularitiescited by 18
  5. 2024Retrieval Meets Reasoning: Even High-school Textbook Knowledge Benefits Multimodal Reasoningcited by 13
  6. 2025Benchmarking Retrieval-Augmented Generation in Multi-Modal Contextscited by 12
  7. 2025Revisiting Compositional Generalization Capability of Large Language Models Considering Instruction Following Abilitycited by 10
  8. 2024LaMI: Augmenting Large Language Models via Late Multi-Image Fusioncited by 1
  9. 2026From Scenes to Elements: Multi-Granularity Evidence Retrieval for Verifiable Multimodal RAGcited by 1
  10. 2025MES-RAG: Bringing Multi-modal, Entity-Storage, and Secure Enhancements to RAGcited by 0
  11. 2025Augmented Vision-Language Models: A Systematic Reviewcited by 0
  12. 2026Evolution of Multimodal Question Answering: From Modality-Adaptive Extraction to Unified Language Representationcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2022On Advances in Text Generation from Images Beyond Captioning: A Case Study in Self-Rationalization
  2. 2026CrossModalQA: A Cross-modal and Multi-hop Benchmark for Multimodal Retrieval-augmented Generation
  3. 2024Generative Cross-Modal Retrieval: Memorizing Images in Multimodal Language Models for Retrieval and Beyond
  4. 2022Retrieval-Augmented Multimodal Language Modeling
  5. 2022MuRAG: Multimodal Retrieval-Augmented Generator for Open Question Answering over Images and Text
  6. 2021Cross-Modal Retrieval Augmentation for Multi-Modal Classification
  7. 2025Towards Mixed-Modal Retrieval for Universal Retrieval-Augmented Generation
  8. 2022Retrieval Augmentation for Commonsense Reasoning: A Unified Approach