相关论文: Positive-Unlabeled Reinforcement Learning Distilla…

Large recommendation models have demonstrated substantial potential gains under scaling laws, yet these gains are difficult to realize in industrial recommendation systems because real-world deployment requires lightweight models with…

Applying reinforcement learning (RL) to real-world problems is often made challenging by the inability to interact with the environment and the difficulty of designing reward functions. Offline RL addresses the first challenge by…

Recently, Large Language Models (LLMs) have demonstrated significant potential for data annotation, markedly reducing the labor costs associated with downstream applications. However, existing methods mostly adopt an aggressive strategy by…

Positive-Unlabeled (PU) learning tries to learn binary classifiers from a few labeled positive examples with many unlabeled ones. Compared with ordinary semi-supervised learning, this task is much more challenging due to the absence of any…

Aligning small language models (SLMs) with human values typically involves distilling preference knowledge from large language models (LLMs). However, existing distillation methods model preference knowledge in teacher LLMs by comparing…

Recommender systems suffer from biases that cause the collected feedback to incompletely reveal user preference. While debiasing learning has been extensively studied, they mostly focused on the specialized (called counterfactual) test…

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…

Moving beyond simple scalar rewards toward richer world feedback is a natural path to more scalable RL post-training. On-policy self-distillation (OPSD) is a promising recent approach that uses arbitrary feedback as learning signal, yet its…

The shift toward interacting with frozen, "black-box" Large Language Models (LLMs) has transformed prompt engineering from a heuristic exercise into a critical optimization challenge. We propose a Reinforcement Learning (RL) framework for…

Reinforcement learning (RL) post-training has recently driven major gains in long chain-of-thought reasoning large language models (LLMs), but the high inference cost of such models motivates distillation into smaller students. Most…

Offline preference-based reinforcement learning (RL), which focuses on optimizing policies using human preferences between pairs of trajectory segments selected from an offline dataset, has emerged as a practical avenue for RL applications.…

Offline preference-based reinforcement learning (PbRL) provides an effective way to overcome the challenges of designing reward and the high costs of online interaction. However, since labeling preference needs real-time human feedback,…

In natural language processing (NLP) tasks, slow inference speed and huge footprints in GPU usage remain the bottleneck of applying pre-trained deep models in production. As a popular method for model compression, knowledge distillation…

Offline reinforcement learning (RL) aims to learn an optimal policy from pre-collected data. However, it faces challenges of distributional shift, where the learned policy may encounter unseen scenarios not covered in the offline data.…

R1-style Reinforcement Learning (RL) significantly enhances Large Language Models' reasoning capabilities, yet the mechanism behind rule-based RL remains unclear. We found that small-scale SFT has substantial influence on RL but shows poor…

To design rewards that align with human goals, Reinforcement Learning from Human Feedback (RLHF) has emerged as a prominent technique for learning reward functions from human preferences and optimizing policies via reinforcement learning…

Reinforcement learning (RL) has become a predominant technique to align language models (LMs) with human preferences or promote outputs which are deemed to be desirable by a given reward function. Standard RL approaches optimize average…

Dataset distillation compresses a large dataset into a small synthetic dataset such that learning on the synthetic dataset approximates learning on the original. Training on the distilled dataset can be performed in as little as one step of…

Preference-based reinforcement learning (RL) has shown potential for teaching agents to perform the target tasks without a costly, pre-defined reward function by learning the reward with a supervisor's preference between the two agent…

Reinforcement learning (RL) is a powerful tool for finding optimal policies in sequential decision processes. However, deep RL methods have two weaknesses: collecting the amount of agent experience required for practical RL problems is…