Predictive Models in Sequential Recommendations: Bridging Performance Laws with Data Quality Insights

Sequential Recommendation (SR) plays a critical role in predicting users' sequential preferences. Despite its growing prominence in various industries, the increasing scale of SR models incurs substantial computational costs and unpredictability, challenging developers to manage resources efficiently. Under this predicament, Scaling Laws have achieved significant success by examining the loss as models scale up. However, there remains a disparity between loss and model performance, which is of greater concern in practical applications. Moreover, as data continues to expand, it incorporates repetitive and inefficient data. In response, we introduce the Performance Law for SR models, which aims to theoretically investigate and model the relationship between model performance and data quality. Specifically, we first fit the HR and NDCG metrics to transformer-based SR models. Subsequently, we propose Approximate Entropy (ApEn) to assess data quality, presenting a more nuanced approach compared to traditional data quantity metrics. Our method enables accurate predictions across various dataset scales and model sizes, demonstrating a strong correlation in large SR models and offering insights into achieving optimal performance for any given model configuration.

Scaling New Frontiers: Insights into Large Recommendation Models

Recommendation systems are essential for filtering data and retrieving relevant information across various applications. Recent advancements have seen these systems incorporate increasingly large embedding tables, scaling up to tens of terabytes for industrial use. However, the expansion of network parameters in traditional recommendation models has plateaued at tens of millions, limiting further benefits from increased embedding parameters. Inspired by the success of large language models (LLMs), a new approach has emerged that scales network parameters using innovative structures, enabling continued performance improvements. A significant development in this area is Meta's generative recommendation model HSTU, which illustrates the scaling laws of recommendation systems by expanding parameters to thousands of billions. This new paradigm has achieved substantial performance gains in online experiments. In this paper, we aim to enhance the understanding of scaling laws by conducting comprehensive evaluations of large recommendation models. Firstly, we investigate the scaling laws across different backbone architectures of the large recommendation models. Secondly, we conduct comprehensive ablation studies to explore the origins of these scaling laws. We then further assess the performance of HSTU, as the representative of large recommendation models, on complex user behavior modeling tasks to evaluate its applicability. Notably, we also analyze its effectiveness in ranking tasks for the first time. Finally, we offer insights into future directions for large recommendation models. Supplementary materials for our research are available on GitHub at https://github.com/USTC-StarTeam/Large-Recommendation-Models.

LIBER: Lifelong User Behavior Modeling Based on Large Language Models

CTR prediction plays a vital role in recommender systems. Recently, large language models (LLMs) have been applied in recommender systems due to their emergence abilities. While leveraging semantic information from LLMs has shown some improvements in the performance of recommender systems, two notable limitations persist in these studies. First, LLM-enhanced recommender systems encounter challenges in extracting valuable information from lifelong user behavior sequences within textual contexts for recommendation tasks. Second, the inherent variability in human behaviors leads to a constant stream of new behaviors and irregularly fluctuating user interests. This characteristic imposes two significant challenges on existing models. On the one hand, it presents difficulties for LLMs in effectively capturing the dynamic shifts in user interests within these sequences, and on the other hand, there exists the issue of substantial computational overhead if the LLMs necessitate recurrent calls upon each update to the user sequences. In this work, we propose Lifelong User Behavior Modeling (LIBER) based on large language models, which includes three modules: (1) User Behavior Streaming Partition (UBSP), (2) User Interest Learning (UIL), and (3) User Interest Fusion (UIF). Initially, UBSP is employed to condense lengthy user behavior sequences into shorter partitions in an incremental paradigm, facilitating more efficient processing. Subsequently, UIL leverages LLMs in a cascading way to infer insights from these partitions. Finally, UIF integrates the textual outputs generated by the aforementioned processes to construct a comprehensive representation, which can be incorporated by any recommendation model to enhance performance. LIBER has been deployed on Huawei's music recommendation service and achieved substantial improvements in users' play count and play time by 3.01% and 7.69%.

GUI Agents with Foundation Models: A Comprehensive Survey

Recent advances in foundation models, particularly Large Language Models (LLMs) and Multimodal Large Language Models (MLLMs), facilitate intelligent agents being capable of performing complex tasks. By leveraging the ability of (M)LLMs to process and interpret Graphical User Interfaces (GUIs), these agents can autonomously execute user instructions by simulating human-like interactions such as clicking and typing. This survey consolidates recent research on (M)LLM-based GUI agents, highlighting key innovations in data, frameworks, and applications. We begin by discussing representative datasets and benchmarks. Next, we summarize a unified framework that captures the essential components used in prior research, accompanied by a taxonomy. Additionally, we explore commercial applications of (M)LLM-based GUI agents. Drawing from existing work, we identify several key challenges and propose future research directions. We hope this paper will inspire further developments in the field of (M)LLM-based GUI agents.

Beyond Positive History: Re-ranking with List-level Hybrid Feedback

As the last stage of recommender systems, re-ranking generates a re-ordered list that aligns with the user's preference. However, previous works generally focus on item-level positive feedback as history (e.g., only clicked items) and ignore that users provide positive or negative feedback on items in the entire list. This list-level hybrid feedback can reveal users' holistic preferences and reflect users' comparison behavior patterns manifesting within a list. Such patterns could predict user behaviors on candidate lists, thus aiding better re-ranking. Despite appealing benefits, extracting and integrating preferences and behavior patterns from list-level hybrid feedback into re-ranking multiple items remains challenging. To this end, we propose Re-ranking with List-level Hybrid Feedback (dubbed RELIFE). It captures user's preferences and behavior patterns with three modules: a Disentangled Interest Miner to disentangle the user's preferences into interests and disinterests, a Sequential Preference Mixer to learn users' entangled preferences considering the context of feedback, and a Comparison-aware Pattern Extractor to capture user's behavior patterns within each list. Moreover, for better integration of patterns, contrastive learning is adopted to align the behavior patterns of candidate and historical lists. Extensive experiments show that RELIFE significantly outperforms SOTA re-ranking baselines.

RevisEval: Improving LLM-as-a-Judge via Response-Adapted References

With significant efforts in recent studies, LLM-as-a-Judge has become a cost-effective alternative to human evaluation for assessing the text generation quality in a wide range of tasks. However, there still remains a reliability gap between LLM-as-a-Judge and human evaluation. One important reason is the lack of guided oracles in the evaluation process. Motivated by the role of reference pervasively used in classic text evaluation, we introduce RevisEval, a novel text generation evaluation paradigm via the response-adapted references. RevisEval is driven by the key observation that an ideal reference should maintain the necessary relevance to the response to be evaluated. Specifically, RevisEval leverages the text revision capabilities of large language models (LLMs) to adaptively revise the response, then treat the revised text as the reference (response-adapted reference) for the subsequent evaluation. Extensive experiments demonstrate that RevisEval outperforms traditional reference-free and reference-based evaluation paradigms that use LLM-as-a-Judge across NLG tasks and open-ended instruction-following tasks. More importantly, our response-adapted references can further boost the classical text metrics, e.g., BLEU and BERTScore, compared to traditional references and even rival the LLM-as-a-Judge. A detailed analysis is also conducted to confirm RevisEval's effectiveness in bias reduction, the impact of inference cost, and reference relevance.

RethinkMCTS: Refining Erroneous Thoughts in Monte Carlo Tree Search for Code Generation

LLM agents enhanced by tree search algorithms have yielded notable performances in code generation. However, current search algorithms in this domain suffer from low search quality due to several reasons: 1) Ineffective design of the search space for the high-reasoning demands of code generation tasks, 2) Inadequate integration of code feedback with the search algorithm, and 3) Poor handling of negative feedback during the search, leading to reduced search efficiency and quality. To address these challenges, we propose to search for the reasoning process of the code and use the detailed feedback of code execution to refine erroneous thoughts during the search. In this paper, we introduce RethinkMCTS, which employs the Monte Carlo Tree Search (MCTS) algorithm to conduct thought-level searches before generating code, thereby exploring a wider range of strategies. More importantly, we construct verbal feedback from fine-grained code execution feedback to refine erroneous thoughts during the search. This ensures that the search progresses along the correct reasoning paths, thus improving the overall search quality of the tree by leveraging execution feedback. Through extensive experiments, we demonstrate that RethinkMCTS outperforms previous search-based and feedback-based code generation baselines. On the HumanEval dataset, it improves the pass@1 of GPT-3.5-turbo from 70.12 to 89.02 and GPT-4o-mini from 87.20 to 94.51. It effectively conducts more thorough exploration through thought-level searches and enhances the search quality of the entire tree by incorporating rethink operation.

ToolACE: Winning the Points of LLM Function Calling

Function calling significantly extends the application boundary of large language models, where high-quality and diverse training data is critical for unlocking this capability. However, real function-calling data is quite challenging to collect and annotate, while synthetic data generated by existing pipelines tends to lack coverage and accuracy. In this paper, we present ToolACE, an automatic agentic pipeline designed to generate accurate, complex, and diverse tool-learning data. ToolACE leverages a novel self-evolution synthesis process to curate a comprehensive API pool of 26,507 diverse APIs. Dialogs are further generated through the interplay among multiple agents, guided by a formalized thinking process. To ensure data accuracy, we implement a dual-layer verification system combining rule-based and model-based checks. We demonstrate that models trained on our synthesized data, even with only 8B parameters, achieve state-of-the-art performance on the Berkeley Function-Calling Leaderboard, rivaling the latest GPT-4 models. Our model and a subset of the data are publicly available at https://huggingface.co/Team-ACE.

Efficient and Deployable Knowledge Infusion for Open-World Recommendations via Large Language Models

Recommender systems (RSs) play a pervasive role in today's online services, yet their closed-loop nature constrains their access to open-world knowledge. Recently, large language models (LLMs) have shown promise in bridging this gap. However, previous attempts to directly implement LLMs as recommenders fall short in meeting the requirements of industrial RSs, particularly in terms of online inference latency and offline resource efficiency. Thus, we propose REKI to acquire two types of external knowledge about users and items from LLMs. Specifically, we introduce factorization prompting to elicit accurate knowledge reasoning on user preferences and items. We develop individual knowledge extraction and collective knowledge extraction tailored for different scales of scenarios, effectively reducing offline resource consumption. Subsequently, generated knowledge undergoes efficient transformation and condensation into augmented vectors through a hybridized expert-integrated network, ensuring compatibility. The obtained vectors can then be used to enhance any conventional recommendation model. We also ensure efficient inference by preprocessing and prestoring the knowledge from LLMs. Experiments demonstrate that REKI outperforms state-of-the-art baselines and is compatible with lots of recommendation algorithms and tasks. Now, REKI has been deployed to Huawei's news and music recommendation platforms and gained a 7% and 1.99% improvement during the online A/B test.

Performance Law of Large Language Models

Guided by the belief of the scaling law, large language models (LLMs) have achieved impressive performance in recent years. However, scaling law only gives a qualitative estimation of loss, which is influenced by various factors such as model architectures, data distributions, tokenizers, and computation precision. Thus, estimating the real performance of LLMs with different training settings rather than loss may be quite useful in practical development. In this article, we present an empirical equation named "Performance Law" to directly predict the MMLU score of an LLM, which is a widely used metric to indicate the general capability of LLMs in real-world conversations and applications. Based on only a few key hyperparameters of the LLM architecture and the size of training data, we obtain a quite accurate MMLU prediction of various LLMs with diverse sizes and architectures developed by different organizations in different years. Performance law can be used to guide the choice of LLM architecture and the effective allocation of computational resources without extensive experiments.