Align2LLaVA: Cascaded Human and Large Language Model Preference Alignment for Multi-modal Instruction Curation (2025.findings-acl)
Copied to clipboard
Hongzhe Huang, Jiang Liu, Zhewen Yu, Li Cai, Dian Jiao, Wenqiao Zhang, Siliang Tang, Juncheng Li, Hao Jiang, Haoyuan Li, Yueting Zhuang
| Challenge: | Recent advances in Multi-modal Large Language Models (MLLMs) introduce significant variability in data quality. |
| Approach: | They propose to use human and LLM preference alignment to compress large corpus of machine-generated multimodal instructions into a compact and high-quality form. |
| Outcome: | The proposed algorithm outperforms LLaVA-series models in MLLM benchmarks by 90% . it uses human and LLM preference alignment to compress a large dataset . |
Similar Papers
Multi-modal Preference Alignment Remedies Degradation of Visual Instruction Tuning on Language Models (2024.acl-long)
Copied to clipboard
| Challenge: | Multi-modal large language models (MLLMs) are expected to support multi-turn queries of interchanging image and text modalities in production. |
| Approach: | They propose to use visual-question-answering (VQA) datasets to annotate a 5k-sample VQA preference dataset and to investigate the degradation of VQA datasets. |
| Outcome: | The proposed model surpasses the instruction-following capabilities of the language model with DPO and SteerLM. |
CodecLM: Aligning Language Models with Tailored Synthetic Data (2024.findings-naacl)
Copied to clipboard
Zifeng Wang, Chun-Liang Li, Vincent Perot, Long Le, Jin Miao, Zizhao Zhang, Chen-Yu Lee, Tomas Pfister
| Challenge: | Recent work on generating diverse instructions and applying LLM to increase instruction complexity neglects downstream use cases. |
| Approach: | They propose a framework for generating high-quality synthetic data for LLM alignment with different downstream instruction distributions and LLMs. |
| Outcome: | Experiments on four open-domain instruction using the proposed framework validate the effectiveness of CodecLM over the current state-of-the-art. |
OmniAlign-V: Towards Enhanced Alignment of MLLMs with Human Preference (2025.acl-long)
Copied to clipboard
Xiangyu Zhao, Shengyuan Ding, Zicheng Zhang, Haian Huang, Maosongcao Maosongcao, Jiaqi Wang, Weiyun Wang, Xinyu Fang, Wenhai Wang, Guangtao Zhai, Hua Yang, Haodong Duan, Kai Chen
| Challenge: | Existing open-source multi-modal large language models (MLLMs) focus on enhancing foundational capabilities, leaving a significant gap in human preference alignment. |
| Approach: | They propose a dataset of 200K high-quality training samples featuring diverse images, complex questions, and varied response formats to improve MLLMs’ alignment with human preferences. |
| Outcome: | The proposed dataset of 200K high-quality training samples improves human preference alignment while maintaining or enhancing performance on standard VQA benchmarks. |
Pedagogical Alignment of Large Language Models (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) are often used without pedagogical fine-tuning and provide immediate answers rather than guiding students through the problem-solving process. |
| Approach: | They propose a method for constructing large-scale preference datasets using synthetic data generation techniques that eliminates the need for manual annotation. |
| Outcome: | The proposed methods outperform standard supervised fine-tuning (SFT) and improve alignment accuracy by 13.1% and 8.7% respectively. |
A Survey on Training-free Alignment of Large Language Models (2025.findings-emnlp)
Copied to clipboard
Birong Pan, Yongqi Li, Weiyu Zhang, Wenpeng Lu, Mayi Xu, Shen Zhou, Yuanyuan Zhu, Ming Zhong, Tieyun Qian
| Challenge: | a survey of large language models (LLMs) aims to ensure outputs adhere to human values, ethical standards, and legal norms. |
| Approach: | They present the first systematic review of TF alignment methods . they categorize them by stages of pre-decoding, in-decoder and post-decoration . |
| Outcome: | The proposed methods are based on training-free (TF) alignment techniques . they are able to be used in open-source and closed-source environments without retraining . |
Direct Large Language Model Alignment Through Self-Rewarding Contrastive Prompt Distillation (2024.acl-long)
Copied to clipboard
| Challenge: | Existing methods to evaluate preference data without human annotations are difficult . et al., 2022b) is effective for aligning large language models with human expectations . |
| Approach: | They propose a method to evaluate the response preference using output probabilities under contrastive prompts. |
| Outcome: | The proposed method could surpass the RLHF method without human-annotated preference data. |
Don’t Forget Your Reward Values: Language Model Alignment via Value-based Calibration (2024.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for generating large language models have been criticized for their complexity and instability. |
| Approach: | They propose a value-based calibration method to better align Large Language Models with human preferences. |
| Outcome: | The proposed method surpasses existing methods on AI assistant and summarization datasets, providing impressive generalizability, robustness, and diversity in different settings. |
HiDe-LLaVA: Hierarchical Decoupling for Continual Instruction Tuning of Multimodal Large Language Model (2025.acl-long)
Copied to clipboard
| Challenge: | Existing methods to improve instructionfollowing performance of MLLMs often trade off memory efficiency for performance gains, compromising overall efficiency. |
| Approach: | They propose a task-specific expansion and task-general fusion framework based on variations in Centered Kernel Alignment (CKA) similarity across different model layers when trained on diverse datasets. |
| Outcome: | The proposed framework improves performance compared to existing benchmarks. |
From 1,000,000 Users to Every User: Scaling Up Personalized Preference for User-level Alignment (2026.acl-long)
Copied to clipboard
| Challenge: | Current approaches to align large language models assume uniform human preferences, overlooking the diversity inherent in human populations. |
| Approach: | They propose a framework for scalable personalized alignment of large language models . they establish a preference space characterizing psychological and behavioral dimensions . |
| Outcome: | The proposed framework improves on existing methods with an average of 17.06% accuracy gain across four benchmarks and a strong adaptation capability to novel preferences. |
Re-Align: Aligning Vision Language Models via Retrieval-Augmented Direct Preference Optimization (2025.emnlp-main)
Copied to clipboard
Shuo Xing, Peiran Li, Yuping Wang, Ruizheng Bai, Yueqi Wang, Chan-Wei Hu, Chengxuan Qian, Huaxiu Yao, Zhengzhong Tu
| Challenge: | emergence of large Vision Language Models (VLMs) has broadened the capabilities of single-modal Large Language Model (LLM) but VLMs are prone to significant hallucinations, especially in the form of cross-modal inconsistencies. |
| Approach: | They propose a new alignment framework that leverages image retrieval to integrate both textual and visual preference signals. |
| Outcome: | The proposed framework mitigates hallucinations more effectively than previous methods . it maintains robustness and scalability across a wide range of VLM sizes and architectures . |