CLSep 16, 2023

Multimodal Multi-Hop Question Answering Through a Conversation Between Tools and Efficiently Finetuned Large Language Models

arXiv:2309.08922v18 citationsh-index: 9
Originality Incremental advance
AI Analysis

This addresses the problem of answering complex multimodal questions for AI systems, but it is incremental as it builds on existing LLM and tool-based methods.

The paper tackles complex multimodal multi-hop question answering by using a tool-interacting divide-and-conquer strategy with large language models (LLMs), achieving substantial improvements over state-of-the-art solutions on two datasets.

We employ a tool-interacting divide-and-conquer strategy enabling large language models (LLMs) to answer complex multimodal multi-hop questions. In particular, we harness the power of large language models to divide a given multimodal multi-hop question into unimodal single-hop sub-questions to be answered by the appropriate tool from a predefined set of tools. After all corresponding tools provide the LLM with their answers, the LLM generates the next relevant unimodal single-hop question. To increase the reasoning ability of LLMs, we prompt chatGPT to generate a tool-interacting divide-and-conquer dataset. This dataset is then used to efficiently finetune the corresponding LLM. To assess the effectiveness of this approach, we conduct an evaluation on two recently introduced complex question-answering datasets. The experimental analysis demonstrate substantial improvements over existing state-of-the-art solutions, indicating the efficacy and generality of our strategy

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes