Related papers: KnowPO: Knowledge-aware Preference Optimization fo…

Reinforcement Learning with Verifiable Rewards (RLVR) demonstrates significant potential in enhancing the reasoning capabilities of Large Language Models (LLMs). However, existing RLVR methods are often constrained by issues such as…

A common technique for aligning large language models (LLMs) relies on acquiring human preferences by comparing multiple generations conditioned on a fixed context. This method, however, relies solely on pairwise comparisons, where the…

Reinforcement learning with verifiable rewards (RLVR) has recently enhanced the reasoning capabilities of large language models (LLMs), particularly for mathematical problem solving. However, a fundamental limitation remains: as the…

Direct Preference Optimization (DPO) has shown effectiveness in aligning multi-modal large language models (MLLM) with human preferences. However, existing methods exhibit an imbalanced responsiveness to the data of varying hardness,…

Retrieval-augmented generation (RAG) integrates large language models ( LLM s) with retrievers to access external knowledge, improving the factuality of LLM generation in knowledge-grounded tasks. To optimize the RAG performance, most…

Recently, there has been significant interest in replacing the reward model in Reinforcement Learning with Human Feedback (RLHF) methods for Large Language Models (LLMs), such as Direct Preference Optimization (DPO) and its variants. These…

The Retrieval-Augmented Generation (RAG) framework introduces a retrieval module to dynamically inject retrieved information into the input context of large language models (LLMs), and has demonstrated significant success in various NLP…

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…

Direct Preference Optimization (DPO) is an effective framework for aligning large language models with human preferences, but it struggles with complex reasoning tasks. DPO optimizes for the likelihood of generating preferred over…

Retrieval-Augmented Generation (RAG) empowers Large Language Models (LLMs) to dynamically integrate external knowledge during inference, improving their factual accuracy and adaptability. However, adversaries can inject poisoned external…

Multimodal Retrieval-Augmented Generation (MRAG) has shown promise in mitigating hallucinations in Multimodal Large Language Models (MLLMs) by incorporating external knowledge. However, existing methods typically adhere to rigid retrieval…

The integration of external knowledge through Retrieval-Augmented Generation (RAG) has become foundational in enhancing large language models (LLMs) for knowledge-intensive tasks. However, existing RAG paradigms often overlook the cognitive…

Direct Preference Optimization (DPO) is a powerful paradigm for aligning Large Language Models (LLMs) to human preferences in Machine Translation (MT), but current methods are hindered by two fundamental challenges: (1) flawed reward…

While prompt optimization has emerged as a critical technique for enhancing language model performance, existing approaches primarily focus on elicitation-based strategies that search for optimal prompts to activate models' capabilities.…

As Large Language Models (LLMs) demonstrate remarkable capabilities learned from vast corpora, concerns regarding data privacy and safety are receiving increasing attention. LLM unlearning, which aims to remove the influence of specific…

Retrieval-Augmented Generation (RAG) systems commonly suffer from Knowledge Conflicts, where retrieved external knowledge contradicts the inherent, parametric knowledge of large language models (LLMs). It adversely affects performance on…

Machine unlearning has gained increasing attention in recent years, as a promising technique to selectively remove unwanted privacy or copyrighted information from Large Language Models that are trained on a massive scale of human data.…

Direct Preference Optimization (DPO) have emerged as a popular method for aligning Large Language Models (LLMs) with human preferences. While DPO effectively preserves the relative ordering between chosen and rejected responses through…

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…

On-policy reinforcement learning methods like GRPO suffer from mode collapse: they exhibit reduced solution diversity, concentrating probability mass on a single solution once discovered and ceasing exploration of alternative strategies. We…