Related papers: Enhancing the Reasoning Ability of Multimodal Larg…

Lead optimization in drug discovery requires efficiently navigating vast chemical space through iterative cycles to enhance molecular properties while preserving structural similarity to the original lead compound. Despite recent advances,…

Multimodal large language models (MLLMs) have shown promising capabilities in reasoning tasks, yet still struggle with complex problems requiring explicit self-reflection and self-correction, especially compared to their unimodal text-based…

Large reasoning models (LRMs) generate intermediate reasoning traces before producing final answers, yielding strong gains on multi-step and mathematical tasks. Yet aligning LRMs with human preferences, a crucial prerequisite for model…

Neural metrics for machine translation (MT) evaluation have become increasingly prominent due to their superior correlation with human judgments compared to traditional lexical metrics. Researchers have therefore utilized neural metrics…

As large language models (LLMs) see greater use in academic and commercial settings, there is increasing interest in methods that allow language models to generate texts aligned with human preferences. In this paper, we present an initial…

Bootstrapping large language models (LLMs) through preference-based policy optimization offers a promising direction for aligning model behavior with human preferences without relying on extensive manual annotations. In this work, we…

Recent advances in preference optimization have demonstrated significant potential for improving mathematical reasoning capabilities in large language models (LLMs). While current approaches leverage high-quality pairwise preference data…

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…

Group relative policy optimization (GRPO) has become a standard post-training paradigm for improving reasoning and preference alignment in large language models (LLMs), and has recently shown strong effectiveness in LLM-based recommender…

Large Vision-Language Models (LVLMs) hold significant promise for medical applications, yet their deployment is often constrained by insufficient alignment and reliability. While Direct Preference Optimization (DPO) has emerged as a potent…

Preference alignment is pivotal for empowering large language models (LLMs) to generate helpful and harmless responses. However, the performance of preference alignment is highly sensitive to the prevalent noise in the preference data.…

Large Language Models (LLMs) show potential in medicine, yet clinical adoption is hindered by concerns over factual accuracy, language-specific limitations (e.g., Japanese), and critically, their reliability when required to generate…

Process Reward Models (PRMs) have shown promise in enhancing the mathematical reasoning capabilities of Large Language Models (LLMs) through Test-Time Scaling (TTS). However, their integration into multimodal reasoning remains largely…

Reinforcement Learning from Human Feedback (RLHF) has been proven to be an effective method for preference alignment of large language models (LLMs) and is widely used in the post-training process of LLMs. However, RLHF struggles with…

As large language models (LLMs) are increasingly applied across various domains, enhancing safety while maintaining the helpfulness of LLMs has become a critical challenge. Recent studies solve this problem through safety-constrained online…

Large Language Models (LLMs) have demonstrated significant potential in handling complex reasoning tasks through step-by-step rationale generation. However, recent studies have raised concerns regarding the hallucination and flaws in their…

This paper presents Perceptual Preference Optimization (PerPO), a perception alignment method aimed at addressing the visual discrimination challenges in generative pre-trained multimodal large language models (MLLMs). To align MLLMs with…

As language models continue to scale, Large Language Models (LLMs) have exhibited emerging capabilities in In-Context Learning (ICL), enabling them to solve language tasks by prefixing a few in-context demonstrations (ICDs) as context.…

Through alignment with human preferences, Large Language Models (LLMs) have advanced significantly in generating honest, harmless, and helpful responses. However, collecting high-quality preference data is a resource-intensive and…

Post-training of LLMs with RLHF, and subsequently preference optimization algorithms such as DPO, IPO, etc., made a big difference in improving human alignment. However, all such techniques can only work with a single (human) objective. In…