相关论文: MIA-DPO: Multi-Image Augmented Direct Preference O…

Large Language Models (LLMs) have demonstrated remarkable performance across various domains, motivating researchers to investigate their potential use in recommendation systems. However, directly applying LLMs to recommendation tasks has…

Omni-modal large language models (omni LLMs) have recently achieved strong performance across audiovisual understanding tasks, yet they remain highly susceptible to cross-modal hallucinations arising from spurious correlations and dominant…

Direct preference optimization (DPO) is an effective technique to train language models to generate preferred over dispreferred responses. However, this binary "winner-takes-all" approach is suboptimal for vision-language models whose…

Current popular Large Vision-Language Models (LVLMs) are suffering from Hallucinations on Object Attributes (HoOA), leading to incorrect determination of fine-grained attributes in the input images. Leveraging significant advancements in 3D…

Large language models (LLMs) have shown great potential in natural language processing tasks, but their application to machine translation (MT) remains challenging due to pretraining on English-centric data and the complexity of…

Recent advancements in open-source multi-modal large language models (MLLMs) have primarily focused on enhancing foundational capabilities, leaving a significant gap in human preference alignment. This paper introduces OmniAlign-V, a…

A single language model, even when aligned with labelers through reinforcement learning from human feedback (RLHF), may not suit all human preferences. Recent approaches therefore prefer customization, gathering multi-dimensional feedback,…

Post-training alignment of large language models (LLMs) is a critical challenge, as not all tokens contribute equally to model performance. This paper introduces a selective alignment strategy that prioritizes high-impact tokens within…

Preference alignment methods such as RLHF and Direct Preference Optimization (DPO) improve instruction following, but they can also reinforce hallucinations when preference judgments reward fluency and confidence over factual correctness.…

Unified multimodal pretraining has emerged as a promising paradigm for jointly modeling language and vision within a single foundation model. However, existing approaches largely rely on implicit or indirect alignment signals and remain…

This paper introduces V2A-DPO, a novel Direct Preference Optimization (DPO) framework tailored for flow-based video-to-audio generation (V2A) models, incorporating key adaptations to effectively align generated audio with human preferences.…

Direct Preference Optimization (DPO) has recently been applied as a post-training technique for text-to-video diffusion models. To obtain training data, annotators are asked to provide preferences between two videos generated from…

Compound AI systems, comprising multiple interacting components such as LLMs, foundation models, and external tools, have demonstrated remarkable improvements compared to single models in various tasks. To ensure their effective deployment…

Large Vision-Language Models (LVLMs) frequently suffer from hallucinations. Existing preference learning-based approaches largely rely on proprietary models to construct preference datasets. We identify that this reliance introduces a…

Direct Preference Optimization (DPO) is broadly utilized for aligning Large Language Models (LLMs) with human values because of its flexibility. Despite its effectiveness, it has been observed that the capability of DPO to generate…

Large Visual Language Models (LVLMs) have demonstrated impressive capabilities across multiple tasks. However, their trustworthiness is often challenged by hallucinations, which can be attributed to the modality misalignment and the…

Direct preference optimization (DPO), a widely adopted offline preference optimization algorithm, aims to align large language models (LLMs) with human-desired behaviors using pairwise preference data. However, the generation of the winning…

Aligning large language models with human preferences has emerged as a critical focus in language modeling research. Yet, integrating preference learning into Text-to-Image (T2I) generative models is still relatively uncharted territory.…

Direct Preference Optimization (DPO) has become a widely used training method for the instruction fine-tuning of large language models (LLMs). In this work, we explore an under-investigated aspect of DPO - its dependency on the reference…

Human visual preferences are inherently multi-dimensional, encompassing aesthetics, detail fidelity, and semantic alignment. However, existing datasets provide only single, holistic annotations, resulting in severe label noise: images that…