相关论文: PKG-DPO: Optimizing Domain-Specific AI systems wit…

Direct preference optimization (\texttt{DPO}) has emerged as a promising approach for solving the alignment problem in AI. In this paper, we make two counter-intuitive observations about \texttt{DPO}. First, we show that \texttt{DPO} loss…

Direct Preference Optimization (DPO) improves the alignment of large language models (LLMs) with human values by training directly on human preference datasets, eliminating the need for reward models. However, due to the presence of…

In this paper, we present a novel diagnostic framework that integrates Knowledge Graphs (KGs) and Large Language Models (LLMs) to support system diagnostics in high-reliability systems such as nuclear power plants. Traditional diagnostic…

With the rapid development of Large Language Models (LLMs), numerous Reinforcement Learning from Human Feedback (RLHF) algorithms have been introduced to improve model safety and alignment with human preferences. These algorithms can be…

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…

Reinforcement Learning with Human Feedback (RLHF) enhances the alignment of Large Language Models (LLMs). However, its limitations have led to the development of Direct Preference Optimization (DPO), an RL-free approach designed to overcome…

In mathematical reasoning, data selection strategies predominantly rely on static, externally defined metrics, which fail to adapt to the evolving capabilities of models during training. This misalignment limits the efficiency of Supervised…

The evolution of Large Language Models (LLMs) has catalyzed a paradigm shift from superficial instruction following to rigorous long-horizon reasoning. While Group Relative Policy Optimization (GRPO) has emerged as a pivotal mechanism for…

To adapt large language models (LLMs) to ranking tasks, existing list-wise methods, represented by list-wise Direct Preference Optimization (DPO), focus on optimizing partial-order or full-order list ranking consistency for LLMs to enhance…

Visual preference alignment involves training Large Vision-Language Models (LVLMs) to predict human preferences between visual inputs. This is typically achieved by using labeled datasets of chosen/rejected pairs and employing optimization…

Preference based alignment objectives implicitly assume that all human preferences are expressed with equal strength. In practice, however, preference strength varies across individuals and contexts -- a phenomenon established in behavioral…

Knowledge Graphs (KGs) can serve as reliable knowledge sources for question answering (QA) due to their structured representation of knowledge. Existing research on the utilization of KG for large language models (LLMs) prevalently relies…

Aligning large language models (LLMs) with human preferences is commonly done via reinforcement learning from human feedback (RLHF) with Proximal Policy Optimization (PPO) or, more simply, via Direct Preference Optimization (DPO). While DPO…

Direct Preference Optimization (DPO) has shown promising results in aligning generative outputs with human preferences by distinguishing between chosen and rejected samples. However, a critical limitation of DPO is likelihood displacement,…

Modern alignment pipelines are increasingly replacing expensive human preference labels with evaluations from large language models (LLM-as-Judge). However, AI labels can be systematically biased compared to high-quality human feedback…

Aligning large language models (LLMs) is a central objective of post-training, often achieved through reward modeling and reinforcement learning methods. Among these, direct preference optimization (DPO) has emerged as a widely adopted…

The widespread application of large language models (LLMs) raises increasing demands on ensuring safety or imposing constraints, such as reducing harmful content and adhering to predefined rules. While there have been several works studying…

Automated Theorem Proving (ATP) represents a fundamental challenge in Artificial Intelligence (AI), requiring the construction of machine-verifiable proofs in formal languages such as Lean to evaluate AI reasoning capabilities.…

Reasoning over knowledge graphs (KGs) with first-order logic (FOL) queries is challenging due to the inherent incompleteness of real-world KGs and the compositional complexity of logical query structures. Most existing methods rely on…

The project of physics discovery is often equivalent to finding the most concise description of a physical system. The description with optimum predictive capability for a dataset generated by a physical system is one that minimizes both…