相关论文: Quality-constrained Entropy Maximization Policy Op…

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.…

Policy gradient algorithms have driven many recent advancements in language model reasoning. An appealing property is their ability to learn from exploration on their own trajectories, a process crucial for fostering diverse and creative…

Recently, test-time scaling Large Language Models (LLMs) have demonstrated exceptional reasoning capabilities across scientific and professional tasks by generating long chains-of-thought (CoT). As a crucial component for developing these…

Large Language Model (LLM)-based optimization has recently shown promise for autonomous problem solving, yet most approaches still cast LLMs as passive constraint checkers rather than proactive strategy designers, limiting their…

Alignment has greatly improved large language models (LLMs)' output quality at the cost of diversity, yielding highly similar outputs across generations. We propose Base-Aligned Model Collaboration (BACo), an inference-time token-level…

In user-agent interaction scenarios such as recommendation, brainstorming, and code suggestion, Large Language Models (LLMs) often generate sets of candidate recommendations where the objective is to maximize the collective utility of the…

Inferring a quantum system from incomplete information is a common problem in many aspects of quantum information science and applications, where the principle of maximum entropy (MaxEnt) plays an important role. The quantum state…

Large language models (LLMs) exhibit varying levels of confidence across input prompts (questions): some lead to consistent, semantically similar answers, while others yield diverse or contradictory outputs. This variation reflects LLM's…

Tool-using agents based on Large Language Models (LLMs) excel in tasks such as mathematical reasoning and multi-hop question answering. However, in long trajectories, agents often trigger excessive and low-quality tool calls, increasing…

Large Language Models (LLMs) have shown impressive reasoning capabilities in well-defined problems with clear solutions, such as mathematics and coding. However, they still struggle with complex real-world scenarios like business…

Large Language Models (LLMs) often suffer from mode collapse, repeatedly generating the same few completions even when many valid answers exist, limiting their diversity across a wide range of tasks. We introduce Group-Aware Policy…

Existing methods to enhance the reasoning capability of large language models predominantly rely on supervised fine-tuning (SFT) followed by reinforcement learning (RL) on reasoning-specific data. These approaches critically depend on…

Large Language Models (LLMs) have shown significant capability across various tasks, with their real-world effectiveness often driven by prompt design. While recent research has focused on optimizing prompt content, the role of prompt…

How can Large Language Models (LLMs) be aligned with human intentions and values? A typical solution is to gather human preference on model outputs and finetune the LLMs accordingly while ensuring that updates do not deviate too far from a…

Large Visual Language Models (LVLMs) have demonstrated impressive capabilities across multiple tasks. However, their trustworthiness is often challenged by hallucinations, which can be attributed to the modality misalignment and the…

The rapid development of Large Language Models (LLMs) has intensified concerns about content traceability and potential misuse. Existing watermarking schemes for sampled text often face trade-offs between maintaining text quality and…

Reinforcement learning (RL) has become a powerful paradigm for optimizing large language models (LLMs) to handle complex reasoning tasks. A core challenge in this process lies in managing policy entropy, which reflects the balance between…

Large language models (LLMs) have shown great potential in natural language processing tasks, but their application to machine translation (MT) remains challenging due to pretraining on English-centric data and the complexity of…

Iterative preference optimization has recently become one of the de-facto training paradigms for large language models (LLMs), but the performance is still underwhelming due to too much noisy preference data yielded in the loop. To combat…

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…