Although applying Mixture of Experts to large language models for learning new tasks is widely regarded as an effective strategy for continuous learning, there still remain two major challenges: (1) As the number of tasks grows, simple parameter expansion strategies can lead to excessively large models. (2) Modifying the parameters of the existing router results in the erosion of previously acquired knowledge. In this paper, we present an innovative framework named LLaVA-CMoE, which is a continuous Mixture of Experts (MoE) architecture without any replay data. Specifically, we have developed a method called Probe-Guided Knowledge Extension (PGKE), which employs probe experts to assess whether additional knowledge is required for a specific layer. This approach enables the model to adaptively expand its network parameters based on task distribution, thereby significantly improving the efficiency of parameter expansion. Additionally, we introduce a hierarchical routing algorithm called Probabilistic Task Locator (PTL), where high-level routing captures inter-task information and low-level routing focuses on intra-task details, ensuring that new task experts do not interfere with existing ones. Our experiments shows that our efficient architecture has substantially improved model performance on the Coin benchmark while maintaining a reasonable parameter count.

Huawei has always been committed to exploring the AI application in historical research. Biography generation, as a specialized form of abstractive summarization, plays a crucial role in historical research but faces unique challenges that existing large language models (LLMs) struggle to address. These challenges include maintaining stylistic adherence to historical writing conventions, ensuring factual fidelity, and handling fragmented information across multiple documents. We present AIstorian, a novel end-to-end agentic system featured with a knowledge graph (KG)-powered retrieval-augmented generation (RAG) and anti-hallucination multi-agents. Specifically, AIstorian introduces an in-context learning based chunking strategy and a KG-based index for accurate and efficient reference retrieval. Meanwhile, AIstorian orchestrates multi-agents to conduct on-the-fly hallucination detection and error-type-aware correction. Additionally, to teach LLMs a certain language style, we finetune LLMs based on a two-step training approach combining data augmentation-enhanced supervised fine-tuning with stylistic preference optimization. Extensive experiments on a real-life historical Jinshi dataset demonstrate that AIstorian achieves a 3.8x improvement in factual accuracy and a 47.6% reduction in hallucination rate compared to existing baselines. The data and code are available at: https://github.com/ZJU-DAILY/AIstorian.

Evaluating the performance of Grammatical Error Correction (GEC) models has become increasingly challenging, as large language model (LLM)-based GEC systems often produce corrections that diverge from provided gold references. This discrepancy undermines the reliability of traditional reference-based evaluation metrics. In this study, we propose a novel evaluation framework for GEC models, DSGram, integrating Semantic Coherence, Edit Level, and Fluency, and utilizing a dynamic weighting mechanism. Our framework employs the Analytic Hierarchy Process (AHP) in conjunction with large language models to ascertain the relative importance of various evaluation criteria. Additionally, we develop a dataset incorporating human annotations and LLM-simulated sentences to validate our algorithms and fine-tune more cost-effective models. Experimental results indicate that our proposed approach enhances the effectiveness of GEC model evaluations.

In two-sided marketplaces such as online flea markets, recommender systems for providing consumers with personalized item rankings play a key role in promoting transactions between providers and consumers. Meanwhile, two-sided marketplaces face the problem of balancing consumer satisfaction and fairness among items to stimulate activity of item providers. Saito and Joachims (2022) devised an impact-based fair ranking method for maximizing the Nash social welfare based on fair division; however, this method, which requires solving a large-scale constrained nonlinear optimization problem, is very difficult to apply to practical-scale recommender systems. We thus propose a fast solution to the impact-based fair ranking problem. We first transform the fair ranking problem into an unconstrained optimization problem and then design a gradient ascent method that repeatedly executes the Sinkhorn algorithm. Experimental results demonstrate that our algorithm provides fair rankings of high quality and is about 1000 times faster than application of commercial optimization software.

Weakly supervised text classification (WSTC), also called zero-shot or dataless text classification, has attracted increasing attention due to its applicability in classifying a mass of texts within the dynamic and open Web environment, since it requires only a limited set of seed words (label names) for each category instead of labeled data. With the help of recently popular prompting Pre-trained Language Models (PLMs), many studies leveraged manually crafted and/or automatically identified verbalizers to estimate the likelihood of categories, but they failed to differentiate the effects of these category-indicative words, let alone capture their correlations and realize adaptive adjustments according to the unlabeled corpus. In this paper, in order to let the PLM effectively understand each category, we at first propose a novel form of rule-based knowledge using logical expressions to characterize the meanings of categories. Then, we develop a prompting PLM-based approach named RulePrompt for the WSTC task, consisting of a rule mining module and a rule-enhanced pseudo label generation module, plus a self-supervised fine-tuning module to make the PLM align with this task. Within this framework, the inaccurate pseudo labels assigned to texts and the imprecise logical rules associated with categories mutually enhance each other in an alternative manner. That establishes a self-iterative closed loop of knowledge (rule) acquisition and utilization, with seed words serving as the starting point. Extensive experiments validate the effectiveness and robustness of our approach, which markedly outperforms state-of-the-art weakly supervised methods. What is more, our approach yields interpretable category rules, proving its advantage in disambiguating easily-confused categories.

In real-world scenarios, the application of reinforcement learning is significantly challenged by complex non-stationarity. Most existing methods attempt to model changes in the environment explicitly, often requiring impractical prior knowledge. In this paper, we propose a new perspective, positing that non-stationarity can propagate and accumulate through complex causal relationships during state transitions, thereby compounding its sophistication and affecting policy learning. We believe that this challenge can be more effectively addressed by tracing the causal origin of non-stationarity. To this end, we introduce the Causal-Origin REPresentation (COREP) algorithm. COREP primarily employs a guided updating mechanism to learn a stable graph representation for states termed as causal-origin representation. By leveraging this representation, the learned policy exhibits impressive resilience to non-stationarity. We supplement our approach with a theoretical analysis grounded in the causal interpretation for non-stationary reinforcement learning, advocating for the validity of the causal-origin representation. Experimental results further demonstrate the superior performance of COREP over existing methods in tackling non-stationarity.

In the era of big data, the explosive growth of multi-source heterogeneous data offers many exciting challenges and opportunities for improving the inference of conditional average treatment effects. In this paper, we investigate homogeneous and heterogeneous causal data fusion problems under a general setting that allows for the presence of source-specific covariates. We provide a direct learning framework for integrating multi-source data that separates the treatment effect from other nuisance functions, and achieves double robustness against certain misspecification. To improve estimation precision and stability, we propose a causal information-aware weighting function motivated by theoretical insights from the semiparametric efficiency theory; it assigns larger weights to samples containing more causal information with high interpretability. We introduce a two-step algorithm, the weighted multi-source direct learner, based on constructing a pseudo-outcome and regressing it on covariates under a weighted least square criterion; it offers us a powerful tool for causal data fusion, enjoying the advantages of easy implementation, double robustness and model flexibility. In simulation studies, we demonstrate the effectiveness of our proposed methods in both homogeneous and heterogeneous causal data fusion scenarios.

Promotions have been trending in the e-commerce marketplace to build up customer relationships and guide customers towards the desired actions. Since incentives are effective to engage customers and customers have different preferences for different types of incentives, the demand for personalized promotion decision making is increasing over time. However, research on promotion decision making has focused specifically on purchase conversion during the promotion period (the direct effect), while generally disregarding the enduring effect in the post promotion period. To achieve a better lift return on investment (lift ROI) on the enduring effect of the promotion and improve customer retention and loyalty, we propose a framework of multiple treatment promotion decision making by modeling each customer's direct and enduring response. First, we propose a customer direct and enduring effect (CDEE) model which predicts the customer direct and enduring response. With the help of the predictions of the CDEE, we personalize incentive allocation to optimize the enduring effect while keeping the cost under the budget. To estimate the effect of decision making, we apply an unbiased evaluation approach of business metrics with randomized control trial (RCT) data. We compare our method with benchmarks using two promotions in Mercari and achieve significantly better results.