Retrieval Meets Reasoning: Even High-school Textbook Knowledge Benefits Multimodal Reasoning
- URL: http://arxiv.org/abs/2405.20834v1
- Date: Fri, 31 May 2024 14:23:49 GMT
- Title: Retrieval Meets Reasoning: Even High-school Textbook Knowledge Benefits Multimodal Reasoning
- Authors: Cheng Tan, Jingxuan Wei, Linzhuang Sun, Zhangyang Gao, Siyuan Li, Bihui Yu, Ruifeng Guo, Stan Z. Li,
- Abstract summary: We introduce a novel multimodal RAG framework named RMR (Retrieval Meets Reasoning)
The RMR framework employs a bi-modal retrieval module to identify the most relevant question-answer pairs.
It significantly boosts the performance of various vision-language models across a spectrum of benchmark datasets.
- Score: 49.3242278912771
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Large language models equipped with retrieval-augmented generation (RAG) represent a burgeoning field aimed at enhancing answering capabilities by leveraging external knowledge bases. Although the application of RAG with language-only models has been extensively explored, its adaptation into multimodal vision-language models remains nascent. Going beyond mere answer generation, the primary goal of multimodal RAG is to cultivate the models' ability to reason in response to relevant queries. To this end, we introduce a novel multimodal RAG framework named RMR (Retrieval Meets Reasoning). The RMR framework employs a bi-modal retrieval module to identify the most relevant question-answer pairs, which then serve as scaffolds for the multimodal reasoning process. This training-free approach not only encourages the model to engage deeply with the reasoning processes inherent in the retrieved content but also facilitates the generation of answers that are precise and richly interpretable. Surprisingly, utilizing solely the ScienceQA dataset, collected from elementary and high school science curricula, RMR significantly boosts the performance of various vision-language models across a spectrum of benchmark datasets, including A-OKVQA, MMBench, and SEED. These outcomes highlight the substantial potential of our multimodal retrieval and reasoning mechanism to improve the reasoning capabilities of vision-language models.
Related papers
- Retrieval-Enhanced Machine Learning: Synthesis and Opportunities [60.34182805429511]
Retrieval-enhancement can be extended to a broader spectrum of machine learning (ML)
This work introduces a formal framework of this paradigm, Retrieval-Enhanced Machine Learning (REML), by synthesizing the literature in various domains in ML with consistent notations which is missing from the current literature.
The goal of this work is to equip researchers across various disciplines with a comprehensive, formally structured framework of retrieval-enhanced models, thereby fostering interdisciplinary future research.
arXiv Detail & Related papers (2024-07-17T20:01:21Z) - SK-VQA: Synthetic Knowledge Generation at Scale for Training Context-Augmented Multimodal LLMs [6.879945062426145]
We generate SK-VQA: a large synthetic multimodal dataset containing over 2 million question-answer pairs.
We demonstrate that our synthetic dataset can not only serve as a challenging benchmark, but is also highly effective for adapting existing generative multimodal models for context-augmented generation.
arXiv Detail & Related papers (2024-06-28T01:14:43Z) - RAVEN: Multitask Retrieval Augmented Vision-Language Learning [5.1583788731239455]
The scaling of large language models to encode all the world's knowledge is unsustainable and has exacerbated resource barriers.
Retrieval-Augmented Generation (RAG) presents a potential solution, yet its application to vision-language models (VLMs) is under explored.
This paper introduces RAVEN, a retrieval augmented VLM framework that enhances base VLMs through efficient, task specific fine-tuning.
arXiv Detail & Related papers (2024-06-27T13:08:35Z) - IM-RAG: Multi-Round Retrieval-Augmented Generation Through Learning Inner Monologues [10.280113107290067]
The IM-RAG approach integrates Information Retrieval systems with Large Language Models (LLMs) to support multi-round RAG.
The entire IM process is optimized via Reinforcement Learning (RL) where a Progress Tracker is incorporated to provide mid-step rewards.
The results show that our approach achieves state-of-the-art (SOTA) performance while providing high flexibility in integrating IR modules.
arXiv Detail & Related papers (2024-05-15T12:41:20Z) - Self-RAG: Learning to Retrieve, Generate, and Critique through
Self-Reflection [74.51523859064802]
We introduce a new framework called Self-Reflective Retrieval-Augmented Generation (Self-RAG)
Self-RAG enhances an LM's quality and factuality through retrieval and self-reflection.
It significantly outperforms state-of-the-art LLMs and retrieval-augmented models on a diverse set of tasks.
arXiv Detail & Related papers (2023-10-17T18:18:32Z) - Large Language Models for Information Retrieval: A Survey [57.7992728506871]
Information retrieval has evolved from term-based methods to its integration with advanced neural models.
Recent research has sought to leverage large language models (LLMs) to improve IR systems.
We delve into the confluence of LLMs and IR systems, including crucial aspects such as query rewriters, retrievers, rerankers, and readers.
arXiv Detail & Related papers (2023-08-14T12:47:22Z) - Chain-of-Thought Prompt Distillation for Multimodal Named Entity
Recognition and Multimodal Relation Extraction [8.169359626365619]
We generate a textitchain of thought (CoT) -- a sequence of intermediate reasoning steps.
We present a novel conditional prompt distillation method to assimilate the commonsense reasoning ability from large language models.
Our approach attains state-of-the-art accuracy and manifests a plethora of advantages concerning interpretability, data efficiency, and cross-domain generalization.
arXiv Detail & Related papers (2023-06-25T04:33:56Z) - Multimodal Chain-of-Thought Reasoning in Language Models [94.70184390935661]
We propose Multimodal-CoT that incorporates language (text) and vision (images) modalities into a two-stage framework.
Experimental results on ScienceQA and A-OKVQA benchmark datasets show the effectiveness of our proposed approach.
arXiv Detail & Related papers (2023-02-02T07:51:19Z) - Named Entity and Relation Extraction with Multi-Modal Retrieval [51.660650522630526]
Multi-modal named entity recognition (NER) and relation extraction (RE) aim to leverage relevant image information to improve the performance of NER and RE.
We propose a novel Multi-modal Retrieval based framework (MoRe)
MoRe contains a text retrieval module and an image-based retrieval module, which retrieve related knowledge of the input text and image in the knowledge corpus respectively.
arXiv Detail & Related papers (2022-12-03T13:11:32Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.