# An Entailment Tree Generation Approach for Multimodal Multi-Hop Question Answering with Mixture-of-Experts and Iterative Feedback Mechanism

arXiv: https://arxiv.org/abs/2412.05821 · HTML: https://mlsanity.com/paper/2412.05821/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in MoE large language models, one of 12 directions in Mixture-of-experts.
- Builds on 16 of its 28 references that are in the map.
- First posted on arXiv 8 Dec 2024.

## Placed in

- Mixture-of-experts / [MoE large language models](https://mlsanity.com/moe/moe-large-language-models/)

## Builds on (most cited first, 16 of 16)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [VQA: Visual Question Answering](https://mlsanity.com/paper/1505.00468/) (2015)
- [ST-MoE: Designing Stable and Transferable Sparse Expert Models](https://mlsanity.com/paper/2202.08906/) (2022)
- [An Empirical Study of GPT-3 for Few-Shot Knowledge-Based VQA](https://mlsanity.com/paper/2109.05014/) (2021)
- [MuRAG: Multimodal Retrieval-Augmented Generator for Open Question Answering over Images and Text](https://mlsanity.com/paper/2210.02928/) (2022)
- [Sparse Upcycling: Training Mixture-of-Experts from Dense Checkpoints](https://mlsanity.com/paper/2212.05055/) (2022)
- [OpenMoE: An Early Effort on Open Mixture-of-Experts Language Models](https://mlsanity.com/paper/2402.01739/) (2024)
- [MultiModalQA: Complex Question Answering over Text, Tables and Images](https://mlsanity.com/paper/2104.06039/) (2021)
- [Explaining Answers with Entailment Trees](https://mlsanity.com/paper/2104.08661/) (2021)
- [All You May Need for VQA are Image Captions](https://mlsanity.com/paper/2205.01883/) (2022)
- [Enhancing Multi-modal and Multi-hop Question Answering via Structured Knowledge and Unified Retrieval-Generation](https://mlsanity.com/paper/2212.08632/) (2022)
- [Entailment Tree Explanations via Iterative Retrieval-Generation Reasoner](https://mlsanity.com/paper/2205.09224/) (2022)
- [Unified Language Representation for Question Answering over Text, Tables, and Images](https://mlsanity.com/paper/2306.16762/) (2023)
- [MMHQA-ICL: Multimodal In-context Learning for Hybrid Question Answering over Text, Tables and Images](https://mlsanity.com/paper/2309.04790/) (2023)
- [UniGen: A Unified Generative Framework for Retrieval and Question Answering with Large Language Models](https://mlsanity.com/paper/2312.11036/) (2023)
- [RLET: A Reinforcement Learning Based Approach for Explainable QA with Entailment Trees](https://mlsanity.com/paper/2210.17095/) (2022)

## Built on by (most cited first, 3 of 3)

- [FCMR: Robust Evaluation of Financial Cross-Modal Multi-Hop Reasoning](https://mlsanity.com/paper/2412.12567/) (2024)
- [MMAPG: A Training-Free Framework for Multimodal Multi-hop Question Answering via Adaptive Planning Graphs](https://mlsanity.com/paper/2508.16051/) (2025)
- [MMRAG-RFT: Two-stage Reinforcement Fine-tuning for Explainable Multi-modal Retrieval-augmented Generation](https://mlsanity.com/paper/2512.17194/) (2025)

## Abstract (arXiv)

With the rise of large-scale language models (LLMs), it is currently popular and effective to convert multimodal information into text descriptions for multimodal multi-hop question answering. However, we argue that the current methods of multi-modal multi-hop question answering still mainly face two challenges: 1) The retrieved evidence containing a large amount of redundant information, inevitably leads to a significant drop in performance due to irrelevant information misleading the prediction. 2) The reasoning process without interpretable reasoning steps makes the model difficult to discover the logical errors for handling complex questions. To solve these problems, we propose a unified LLMs-based approach but without heavily relying on them due to the LLM's potential errors, and innovatively treat multimodal multi-hop question answering as a joint entailment tree generation and question answering problem. Specifically, we design a multi-task learning framework with a focus on facilitating common knowledge sharing across interpretability and prediction tasks while preventing task-specific errors from interfering with each other via mixture of experts. Afterward, we design an iterative feedback mechanism to further enhance both tasks by feeding back the results of the joint training to the LLM for regenerating entailment trees, aiming to iteratively refine the potential answer. Notably, our method has won the first place in the official leaderboard of WebQA (since April 10, 2024), and achieves competitive results on MultimodalQA.