Related papers: Instruction-Oriented Preference Alignment for Enha…
Reward models are pivotal for aligning Large Language Models (LLMs) with human preferences. Existing approaches face two key limitations: Discriminative reward models require large-scale annotated data, as they cannot exploit the preference…
Large language models (LLMs) have shown promise on summarization tasks, but they often produce hallucinations, which are unsupported or incorrect statements that limit their reliability in specialized healthcare applications. We introduce…
The rapid development of large language model (LLM) alignment algorithms has resulted in a complex and fragmented landscape, with limited clarity on the effectiveness of different methods and their inter-connections. This paper introduces…
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…
In the realm of large language models (LLMs), the ability of models to accurately follow instructions is paramount as more agents and applications leverage LLMs for construction, where the complexity of instructions are rapidly increasing.…
Reinforcement learning has recently improved the reasoning ability of Large Language Models and Multimodal LLMs, yet prevailing reward designs emphasise final-answer correctness and consequently tolerate process hallucinations--cases where…
Despite their significant advancements, Multimodal Large Language Models (MLLMs) often generate factually inaccurate information, referred to as hallucination. In this work, we address object hallucinations in MLLMs, where information is…
Multimodal Large Reasoning Models introduce the reasoning paradigm, demonstrating strong capabilities on complex vision-language tasks. However, they still suffer from severe hallucinations. Existing training-based methods typically…
RLHF has emerged as a predominant approach for aligning artificial intelligence systems with human preferences, demonstrating exceptional and measurable efficacy in instruction following tasks; however, it exhibits insufficient compliance…
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…
Multimodal Large Language Models (MLLMs) excel in vision-language tasks such as image captioning but remain prone to object hallucinations, where they describe objects that do not appear in the image. To mitigate this, we propose LISA, a…
Despite recent advances in Large Video Language Models (LVLMs), they still struggle with fine-grained temporal understanding, hallucinate, and often make simple mistakes on even simple video question-answering tasks, all of which pose…
Large Language Models (LLMs) are often aligned using contrastive alignment objectives and preference pair datasets. The interaction between model, paired data, and objective makes alignment a complicated procedure, sometimes producing…
The task adaptation and alignment of Large Multimodal Models (LMMs) have been significantly advanced by instruction tuning and further strengthened by recent preference optimization. Yet, most LMMs still suffer from severe modality…
Alignment of large language models (LLMs) has predominantly relied on pairwise preference optimization, where annotators select the better of two responses to a prompt. While simple, this approach overlooks the opportunity to learn from…
Large language models (LLMs) can handle a wide variety of general tasks with simple prompts, without the need for task-specific training. Multimodal Large Language Models (MLLMs), built upon LLMs, have demonstrated impressive potential in…
Preference optimization is a critical post-training technique used to align large language models (LLMs) with human preferences, typically by fine-tuning on ranked response pairs. While methods like Direct Preference Optimization (DPO) have…
Traditional alignment methods for Large Vision and Language Models (LVLMs) primarily rely on human-curated preference data. Human-generated preference data is costly; machine-generated preference data is limited in quality; and…
Large Vision-Language Models (LVLMs) extend large language models with visual understanding, but remain vulnerable to hallucination, where outputs are fluent yet inconsistent with images. Recent studies link this issue to language bias-the…
The rapidly developing Large Vision Language Models (LVLMs) have shown notable capabilities on a range of multi-modal tasks, but still face the hallucination phenomena where the generated texts do not align with the given contexts,…