# HIPPO: Enhancing the Table Understanding Capability of LLMs through Hybrid-Modal Preference Optimization

arXiv: https://arxiv.org/abs/2502.17315 · HTML: https://mlsanity.com/paper/2502.17315/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Placed in Process reward models for reasoning, one of 10 directions in LLM alignment / RLHF / preference optimisation.
- Builds on 47 of its 53 references that are in the map.
- First posted on arXiv 24 Feb 2025.

## Placed in

- LLM alignment / RLHF / preference optimisation / [Process reward models for reasoning](https://mlsanity.com/alignment/process-reward-models-for-reasoning/)

## Builds on (most cited first, 30 of 47)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [Qwen2.5 Technical Report](https://mlsanity.com/paper/2412.15115/) (2024)
- [Improved Baselines with Visual Instruction Tuning](https://mlsanity.com/paper/2310.03744/) (2023)
- [MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models](https://mlsanity.com/paper/2304.10592/) (2023)
- [Least-to-Most Prompting Enables Complex Reasoning in Large Language Models](https://mlsanity.com/paper/2205.10625/) (2022)
- [MiniCPM-V: A GPT-4V Level MLLM on Your Phone](https://mlsanity.com/paper/2408.01800/) (2024)
- [M3-Embedding: Multi-Linguality, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillation](https://mlsanity.com/paper/2402.03216/) (2024)
- [mPLUG-Owl: Modularization Empowers Large Language Models with Multimodality](https://mlsanity.com/paper/2304.14178/) (2023)
- [mPLUG-Owl2: Revolutionizing Multi-modal Large Language Model with Modality Collaboration](https://mlsanity.com/paper/2311.04257/) (2023)
- [Compositional Semantic Parsing on Semi-Structured Tables](https://mlsanity.com/paper/1508.00305/) (2015)
- [TabFact: A Large-scale Dataset for Table-based Fact Verification](https://mlsanity.com/paper/1909.02164/) (2019)
- [TAT-QA: A Question Answering Benchmark on a Hybrid of Tabular and Textual Content in Finance](https://mlsanity.com/paper/2105.07624/) (2021)
- [Monkey: Image Resolution and Text Label Are Important Things for Large Multi-modal Models](https://mlsanity.com/paper/2311.06607/) (2023)
- [SWIFT:A Scalable lightWeight Infrastructure for Fine-Tuning](https://mlsanity.com/paper/2408.05517/) (2024)
- [Dynamic Prompt Learning via Policy Gradient for Semi-structured Mathematical Reasoning](https://mlsanity.com/paper/2209.14610/) (2022)
- [InternLM-XComposer: A Vision-Language Large Model for Advanced Text-image Comprehension and Composition](https://mlsanity.com/paper/2309.15112/) (2023)
- [VisRAG: Vision-based Retrieval-augmented Generation on Multi-modality Documents](https://mlsanity.com/paper/2410.10594/) (2024)
- [TAPEX: Table Pre-training via Learning a Neural SQL Executor](https://mlsanity.com/paper/2107.07653/) (2021)
- [Binding Language Models in Symbolic Languages](https://mlsanity.com/paper/2210.02875/) (2022)
- [Chain-of-Table: Evolving Tables in the Reasoning Chain for Table Understanding](https://mlsanity.com/paper/2401.04398/) (2024)
- [Large Language Models are Versatile Decomposers: Decompose Evidence and Questions for Table-based Reasoning](https://mlsanity.com/paper/2301.13808/) (2023)
- [FeTaQA: Free-form Table Question Answering](https://mlsanity.com/paper/2104.00369/) (2021)
- [ChatDB: Augmenting LLMs with Databases as Their Symbolic Memory](https://mlsanity.com/paper/2306.03901/) (2023)

## Built on by (most cited first, 6 of 6)

- [TABQAWORLD: Optimizing Multimodal Reasoning for Multi-Turn Table Question Answering](https://mlsanity.com/paper/2604.03393/) (2026)
- [Decoupling Skeleton and Flesh: Efficient Multimodal Table Reasoning with Disentangled Alignment and Structure-aware Guidance](https://mlsanity.com/paper/2602.03491/) (2026)
- [Thinking with Tables: Enhancing Multi-Modal Tabular Understanding via Neuro-Symbolic Reasoning](https://mlsanity.com/paper/2603.24004/) (2026)
- [From Table to Cell: Attention for Better Reasoning with TABALIGN](https://mlsanity.com/paper/2605.14465/) (2026)
- [InterTab: Interleaved Visual-Structure Alignment for Multi-Modal Table Reasoning](https://mlsanity.com/paper/2609.32660/) (2026)
- [MERIT: Multimodal Evidence Reasoning over Image Tables](https://mlsanity.com/paper/2610.17937/) (2026)

## Abstract (arXiv)

Tabular data contains rich structural semantics and plays a crucial role in organizing and manipulating information. Recent methods employ Multi-modal Large Language Models (MLLMs) to address table-related tasks across various modalities of table representations. However, existing studies mainly focus on exploring the table understanding ability of MLLMs using unimodal representations, which limits further exploration of multi-modal representations to enable more effective table reasoning. To better capture structural semantics from the tabular data, this paper introduces the HybrId-modal Preference oPtimizatiOn (HIPPO) model, which represents tables using both text and image, optimizing MLLMs by learning more comprehensive table information from these multiple modalities. Specifically, HIPPO samples MLLM responses from hybrid-modal table representations and designs a modality-consistent sampling strategy to enhance response diversity and mitigate modality bias during Direct Preference Optimization (DPO) training. Experiments on table question answering and table fact verification tasks demonstrate the effectiveness of HIPPO, achieving a 4% improvement over various table reasoning models. Further analysis reveals that HIPPO not only enhances the table reasoning capability based on unimodal representations but also facilitates the extraction of complementary semantics across modalities. The code is available at https://github.com/NEUIR/HIPPO.