Pruning is a promising approach to reduce the high inference cost of large language models (LLMs), but it often comes at the expense of performance. Motivated by the "functional localization" theory in neuroscience, we hypothesize that LLMs contain task-specific expert activation paths, where specific subsets of neurons are co-activated for particular tasks. This structure allows selective activation to preserve task performance while improving inference efficiency. We introduce Sparse Expert Activation Pruning (SEAP), a training-free pruning method for large language models. SEAP identifies task-relevant activation paths by analyzing the clustering patterns of hidden states and neuron activations on a multi-task calibration dataset. Cross-task transfer evaluations confirm the existence of such expert activation structures. SEAP constructs task-aware pruning masks by leveraging a task-expert calibration dataset, which provides representative samples across diverse tasks to reveal their activation signatures. It then employs a lightweight task router to dynamically select relevant computation paths based on the input task. This design significantly reduces inference cost without compromising accuracy. Experimental results show that SEAP retains model performance with only a 1.5% drop on most tasks at 20% sparsity, and at 50% sparsity, it surpasses strong pruning baselines such as WandA and FLAP by over 20%. These results highlight SEAP as a scalable and effective solution for efficient LLM inference.

Real-time bidding (RTB) plays a pivotal role in online advertising ecosystems. Advertisers employ strategic bidding to optimize their advertising impact while adhering to various financial constraints, such as the return-on-investment (ROI) and cost-per-click (CPC). Primarily focusing on bidding with fixed budget constraints, traditional approaches cannot effectively manage the dynamic budget allocation problem where the goal is to achieve global optimization of bidding performance across multiple channels with a shared budget. In this paper, we propose a hierarchical multi-agent reinforcement learning framework for multi-channel bidding optimization. In this framework, the top-level strategy applies a CPC constrained diffusion model to dynamically allocate budgets among the channels according to their distinct features and complex interdependencies, while the bottom-level strategy adopts a state-action decoupled actor-critic method to address the problem of extrapolation errors in offline learning caused by out-of-distribution actions and a context-based meta-channel knowledge learning method to improve the state representation capability of the policy based on the shared knowledge among different channels. Comprehensive experiments conducted on a large scale real-world industrial dataset from the Meituan ad bidding platform demonstrate that our method achieves a state-of-the-art performance.

Retrieval-augmented generation (RAG) is a technique that enhances the capabilities of large language models (LLMs) by incorporating external knowledge sources. This method addresses common LLM limitations, including outdated information and the tendency to produce inaccurate “hallucinated” content. However, evaluating RAG systems is a challenge. Most benchmarks focus primarily on question-answering applications, neglecting other potential scenarios where RAG could be beneficial. Accordingly, in the experiments, these benchmarks often assess only the LLM components of the RAG pipeline or the retriever in knowledge-intensive scenarios, overlooking the impact of external knowledge base construction and the retrieval component on the entire RAG pipeline in non-knowledge-intensive scenarios. To address these issues, this article constructs a large-scale and more comprehensive benchmark and evaluates all the components of RAG systems in various RAG application scenarios. Specifically, we refer to the CRUD actions that describe interactions between users and knowledge bases and also categorize the range of RAG applications into four distinct types—create, read, update, and delete (CRUD). “Create” refers to scenarios requiring the generation of original, varied content. “Read” involves responding to intricate questions in knowledge-intensive situations. “Update” focuses on revising and rectifying inaccuracies or inconsistencies in pre-existing texts. “Delete” pertains to the task of summarizing extensive texts into more concise forms. For each of these CRUD categories, we have developed different datasets to evaluate the performance of RAG systems. We also analyze the effects of various components of the RAG system, such as the retriever, context length, knowledge base construction, and LLM. Finally, we provide useful insights for optimizing the RAG technology for different scenarios. The source code is available at GitHub: https://github.com/IAAR-Shanghai/CRUD_RAG .

Primal-dual safe RL methods commonly perform iterations between the primal update of the policy and the dual update of the Lagrange Multiplier. Such a training paradigm is highly susceptible to the error in cumulative cost estimation since this estimation serves as the key bond connecting the primal and dual update processes. We show that this problem causes significant underestimation of cost when using off-policy methods, leading to the failure to satisfy the safety constraint. To address this issue, we propose conservative policy optimization, which learns a policy in a constraint-satisfying area by considering the uncertainty in cost estimation. This improves constraint satisfaction but also potentially hinders reward maximization. We then introduce local policy convexification to help eliminate such suboptimality by gradually reducing the estimation uncertainty. We provide theoretical interpretations of the joint coupling effect of these two ingredients and further verify them by extensive experiments. Results on benchmark tasks show that our method not only achieves an asymptotic performance comparable to state-of-the-art on-policy methods while using much fewer samples, but also significantly reduces constraint violation during training. Our code is available at https://github.com/ZifanWu/CAL.

Commentary provides readers with a deep understanding of events by presenting diverse arguments and evidence. However, creating commentary is a time-consuming task, even for skilled commentators. Large language models (LLMs) have simplified the process of natural language generation, but their direct application in commentary creation still faces challenges due to unique task requirements. These requirements can be categorized into two levels: 1) fundamental requirements, which include creating well-structured and logically consistent narratives, and 2) advanced requirements, which involve generating quality arguments and providing convincing evidence. In this paper, we introduce Xinyu, an efficient LLM-based system designed to assist commentators in generating Chinese commentaries. To meet the fundamental requirements, we deconstruct the generation process into sequential steps, proposing targeted strategies and supervised fine-tuning (SFT) for each step. To address the advanced requirements, we present an argument ranking model for arguments and establish a comprehensive evidence database that includes up-to-date events and classic books, thereby strengthening the substantiation of the evidence with retrieval augmented generation (RAG) technology. To evaluate the generated commentaries more fairly, corresponding to the two-level requirements, we introduce a comprehensive evaluation metric that considers five distinct perspectives in commentary generation. Our experiments confirm the effectiveness of our proposed system. We also observe a significant increase in the efficiency of commentators in real-world scenarios, with the average time spent on creating a commentary dropping from 4 hours to 20 minutes. Importantly, such an increase in efficiency does not compromise the quality of the commentaries.

Online display advertising platforms service numerous advertisers by providing real-time bidding (RTB) for the scale of billions of ad requests every day. The bidding strategy handles ad requests cross multiple channels to maximize the number of clicks under the set financial constraints, i.e., total budget and cost-per-click (CPC), etc. Different from existing works mainly focusing on single channel bidding, we explicitly consider cross-channel constrained bidding with budget allocation. Specifically, we propose a hierarchical offline deep reinforcement learning (DRL) framework called “HiBid”, consisted of a high-level planner equipped with auxiliary loss for non-competitive budget allocation, and a data augmentation enhanced low-level executor for adaptive bidding strategy in response to allocated budgets. Additionally, a CPC-guided action selection mechanism is introduced to satisfy the cross-channel CPC constraint. Through extensive experiments on both the large-scale log data and online A/B testing, we confirm that HiBid outperforms six baselines in terms of the number of clicks, CPC satisfactory ratio, and return-on-investment (ROI). We also deploy HiBid on Meituan advertising platform to already service tens of thousands of advertisers every day.

Aiming at promoting the safe real-world deployment of Reinforcement Learning (RL), research on safe RL has made significant progress in recent years. However, most existing works in the literature still focus on the online setting where risky violations of the safety budget are likely to be incurred during training. Besides, in many realworld applications, the learned policy is required to respond to dynamically determined safety budgets (i.e., constraint threshold) in real time. In this paper, we target at the above real-time budget constraint problem under the offline setting, and propose Trajectory-based REal-time Budget Inference (TREBI) as a novel solution that approaches this problem from the perspective of trajectory distribution. Theoretically, we prove an error bound of the estimation on the episodic reward and cost under the offline setting and thus provide a performance guarantee for TREBI. Empirical results on a wide range of simulation tasks and a real-world large-scale advertising application demonstrate the capability of TREBI in solving real-time budget constraint problems under offline settings.

Recommender systems aim to recommend the most suitable items to users from a large number of candidates. Their computation cost grows as the number of user requests and the complexity of services (or models) increases. Under the limitation of computation resources (CRs), how to make a trade-off between computation cost and business revenue becomes an essential question. The existing studies focus on dynamically allocating CRs in queue truncation scenarios (i.e., allocating the size of candidates), and formulate the CR allocation problem as an optimization problem with constraints. Some of them focus on single-phase CR allocation, and others focus on multi-phase CR allocation but introduce some assumptions about queue truncation scenarios. However, these assumptions do not hold in other scenarios, such as retrieval channel selection and prediction model selection. Moreover, existing studies ignore the state transition process of requests between different phases, limiting the effectiveness of their approaches.

In large and medium-sized cities, detecting unusual changes of crowds of people on the streets is needed for public security, transportation management, emergency control, and terrorism prevention. As public transportation has the capability to bring a large number of people to an area in a short amount of time, real-time discovery of anomalies in passenger numbers is an effective way to detect crowd anomalies. In this paper, we devise an approach called Kochab. Kochab adopts a generative model and combines the prior knowledge about passenger flows. Hence, it can detect anomalies in the numbers of incoming and outgoing passengers within a certain time and spatial area, including anomalous events along with their durations and severities. Through well-designed inference algorithms, Kochab requires only a moderate amount of historical data to be sample data. As such, Kochab shows good performance in real time and makes prompt responses to user' s interactive analysis requests. In particular, based on the recognized anomalous events, we capture event patterns which give us hints to link to activities or status in cities. In addition, for the convenience of method evaluation and comparison, we create an open Stream Anomaly Benchmark on the basis of large-scale real-world data. This benchmark will prove useful for other researchers too. Using this benchmark, we compare Kochab with four other methods. The experimental results show that Kochab is sensitive to population flow anomalies and has superior accuracy in detecting anomalies in terms of precision, recall and the F1 score.