Related papers: Simplicity Prevails: Rethinking Negative Preferenc…
The key to building trustworthy large language models (LLMs) lies in endowing them with inherent uncertainty expression capabilities, thereby mitigating overconfident errors in high-stakes applications. However, existing RL paradigms such…
It is crucial for large language models (LLMs) to follow instructions that involve multiple constraints. However, it is an unexplored area to enhance LLMs' ability to follow soft constraints. To bridge the gap, we initially design a…
Multimodal Large Language Models (MLLMs) have significantly improved the performance of various tasks, but continue to suffer from visual hallucinations, a critical issue where generated responses contradict visual evidence. While Direct…
Offline preference optimization methods, such as Direct Preference Optimization (DPO), offer significant advantages in aligning Large Language Models (LLMs) with human values. However, achieving optimal performance with these methods…
Traditional language model alignment methods, such as Direct Preference Optimization (DPO), are limited by their dependence on static, pre-collected paired preference data, which hampers their adaptability and practical applicability. To…
Given the high computational cost of preference alignment training of large language models (LLMs), exploring efficient methods to reduce the training overhead remains an important and compelling research problem. Motivated by the…
Machine unlearning (MU) aims to remove the influence of specific data from a trained model. However, approximate unlearning methods, often formulated as a single-objective optimization (SOO) problem, face a critical trade-off between…
As generative models become increasingly powerful and pervasive, the ability to unlearn specific data, whether due to privacy concerns, legal requirements, or the correction of harmful content, has become increasingly important. Unlike in…
Safety alignment of large language models remains brittle under domain shift and noisy preference supervision. Most existing robust alignment methods focus on uncertainty in alignment data, while overlooking optimization-induced fragility…
Hallucination remains a fundamental challenge in vision-language models (VLMs), where autoregressive generation may produce linguistically plausible yet physically inconsistent or visually ungrounded responses due to likelihood maximization…
Aligning large language models (LLMs) with human values is an increasingly critical step in post-training. Direct Preference Optimization (DPO) has emerged as a simple, yet effective alternative to reinforcement learning from human feedback…
Direct Preference Optimization (DPO) has been proposed as an effective and efficient alternative to reinforcement learning from human feedback (RLHF). However, neither RLHF nor DPO take into account the fact that learning certain…
The remarkable performance of Large Language Models (LLMs) highly relies on crafted prompts. However, manual prompt engineering is a laborious process, creating a core bottleneck for practical application of LLMs. This phenomenon has led to…
This paper studies post-training large language models (LLMs) using preference feedback from a powerful oracle to help a model iteratively improve over itself. The typical approach for post-training LLMs involves Reinforcement Learning from…
Large Vision-Language Models (LVLMs) or multimodal large language models represent a significant advancement in artificial intelligence, enabling systems to understand and generate content across both visual and textual modalities. While…
Recent advances in Large Language Models (LLMs) have opened new avenues for sequential recommendation by enabling natural language reasoning over user behavior sequences. A common approach formulates recommendation as a language modeling…
Recently, Large Language Models (LLMs) have rapidly evolved, approaching Artificial General Intelligence (AGI) while benefiting from large-scale reinforcement learning to enhance Human Alignment (HA) and Reasoning. Recent reward-based…
Large language models (LLMs) have achieved remarkable success across natural language processing tasks, yet their widespread deployment raises pressing concerns around privacy, copyright, security, and bias. Machine unlearning has emerged…
Recent advancements in post-training methodologies for large language models (LLMs) have highlighted reinforcement learning (RL) as a critical component for enhancing reasoning. However, the substantial computational costs associated with…
Reinforcement learning from human feedback (RLHF) has emerged as the primary method for aligning large language models (LLMs) with human preferences. While it enables LLMs to achieve human-level alignment, it often incurs significant…