相关论文: Information Theoretic Guarantees For Policy Alignm…

Large language models (LLMs) alignment aims to ensure that the behavior of LLMs meets human preferences. While collecting data from multiple fine-grained, aspect-specific preferences becomes more and more feasible, existing alignment…

Large Language Models (LLMs) are increasingly deployed in business-critical domains such as finance, education, healthcare, and customer support, where users expect consistent and reliable recommendations. Yet LLMs often exhibit variability…

Can autoregressive large language models (LLMs) learn consistent probability distributions when trained on sequences in different token orders? We prove formally that for any well-defined probability distribution, sequence perplexity is…

Reinforcement Learning from Human Feedback (RLHF) has proven effective in aligning large language models with human intentions, yet it often relies on complex methodologies like Proximal Policy Optimization (PPO) that require extensive…

This paper concerns the problem of aligning samples from large language models to human preferences using best-of-$n$ sampling, where we draw $n$ samples, rank them, and return the best one. We consider two fundamental problems. First: what…

We study the post-training of large language models (LLMs) with human preference data. Recently, direct preference optimization and its variants have shown considerable promise in aligning language models, eliminating the need for reward…

Recent advancements in large language models (LLMs) have shifted the post-training paradigm from traditional instruction tuning and human preference alignment toward reinforcement learning (RL) focused on reasoning capabilities. However,…

Learning to rank (LTR) plays a crucial role in various Information Retrieval (IR) tasks. Although supervised LTR methods based on fine-grained relevance labels (e.g., document-level annotations) have achieved significant success, their…

This paper investigates Reinforcement Learning (RL) approaches to enhance the reasoning capabilities of Large Language Model (LLM) agents in long-horizon, multi-turn scenarios. Although RL algorithms such as Group Relative Policy…

Great success has been reported using Reinforcement Learning from Human Feedback (RLHF) to align large language models, with open preference datasets enabling wider experimentation, particularly for "helpfulness" in tasks like dialogue and…

While Large Language Models (LLMs) form the cornerstone of sequential decision-making agent development, they have inherent limitations in high-frequency decision tasks. Existing research mainly focuses on discrete embodied decision…

The rapid development of large language model (LLM) alignment algorithms has resulted in a complex and fragmented landscape, with limited clarity on the effectiveness of different methods and their inter-connections. This paper introduces…

Recent developments in large language models have shown advantages in reallocating a notable share of computational resource from training time to inference time. However, the principles behind inference time scaling are not well…

Inverse reinforcement learning (IRL) addresses the problem of recovering a task description given a demonstration of the optimal policy used to solve such a task. The optimal policy is usually provided by an expert or teacher, making IRL…

People tell lies when seeking rewards. Large language models (LLMs) are aligned to human values with reinforcement learning where they get rewards if they satisfy human preference. We find that this also induces dishonesty in helpful and…

In modern large language models (LLMs), LLM alignment is of crucial importance and is typically achieved through methods such as reinforcement learning from human feedback (RLHF) and direct preference optimization (DPO). However, in most…

Learning from preference labels plays a crucial role in fine-tuning large language models. There are several distinct approaches for preference fine-tuning, including supervised learning, on-policy reinforcement learning (RL), and…

Group Relative Policy Optimization (GRPO) has recently emerged as a practical recipe for aligning large language models with verifiable objectives. However, under sparse terminal rewards, GRPO often stalls because rollouts within a group…

Reinforcement learning with verifiable rewards has been used to elicit impressive performance from language models in many domains. But, broadly beneficial deployments of AI may require us to train models with strong capabilities in…

Large Language Models (LLMs) demonstrate transformative potential, yet their reasoning remains inconsistent and unreliable. Reinforcement learning (RL)-based fine-tuning is a key mechanism for improvement, but its effectiveness is…