HELMET: How to Evaluate Long-Context Language Models Effectively and Thoroughly

There have been many benchmarks for evaluating long-context language models (LCLMs), but developers often rely on synthetic tasks like needle-in-a-haystack (NIAH) or arbitrary subsets of tasks. It remains unclear whether they translate to the diverse downstream applications of LCLMs, and the inconsistency further complicates model comparison. We investigate the underlying reasons behind current practices and find that existing benchmarks often provide noisy signals due to low coverage of applications, insufficient lengths, unreliable metrics, and incompatibility with base models. In this work, we present HELMET (How to Evaluate Long-context Models Effectively and Thoroughly), a comprehensive benchmark encompassing seven diverse, application-centric categories. We also address many issues in previous benchmarks by adding controllable lengths up to 128k tokens, model-based evaluation for reliable metrics, and few-shot prompting for robustly evaluating base models. Consequently, we demonstrate that HELMET offers more reliable and consistent rankings of frontier LCLMs. Through a comprehensive study of 51 LCLMs, we find that (1) synthetic tasks like NIAH are not good predictors of downstream performance; (2) the diverse categories in HELMET exhibit distinct trends and low correlation with each other; and (3) while most LCLMs achieve perfect NIAH scores, open-source models significantly lag behind closed ones when the task requires full-context reasoning or following complex instructions -- the gap widens with increased lengths. Finally, we recommend using our RAG tasks for fast model development, as they are easy to run and more predictive of other downstream performance; ultimately, we advocate for a holistic evaluation across diverse tasks.

Metrics Revolutions: Groundbreaking Insights into the Implementation of Metrics for Biomedical Image Segmentation

The evaluation of segmentation performance is a common task in biomedical image analysis, with its importance emphasized in the recently released metrics selection guidelines and computing frameworks. To quantitatively evaluate the alignment of two segmentations, researchers commonly resort to counting metrics, such as the Dice similarity coefficient, or distance-based metrics, such as the Hausdorff distance, which are usually computed by publicly available open-source tools with an inherent assumption that these tools provide consistent results. In this study we questioned this assumption, and performed a systematic implementation analysis along with quantitative experiments on real-world clinical data to compare 11 open-source tools for distance-based metrics computation against our highly accurate mesh-based reference implementation. The results revealed that statistically significant differences among all open-source tools are both surprising and concerning, since they question the validity of existing studies. Besides identifying the main sources of variation, we also provide recommendations for distance-based metrics computation.

Long-Sequence Recommendation Models Need Decoupled Embeddings

Lifelong user behavior sequences, comprising up to tens of thousands of history behaviors, are crucial for capturing user interests and predicting user responses in modern recommendation systems. A two-stage paradigm is typically adopted to handle these long sequences: a few relevant behaviors are first searched from the original long sequences via an attention mechanism in the first stage and then aggregated with the target item to construct a discriminative representation for prediction in the second stage. In this work, we identify and characterize, for the first time, a neglected deficiency in existing long-sequence recommendation models: a single set of embeddings struggles with learning both attention and representation, leading to interference between these two processes. Initial attempts to address this issue using linear projections -- a technique borrowed from language processing -- proved ineffective, shedding light on the unique challenges of recommendation models. To overcome this, we propose the Decoupled Attention and Representation Embeddings (DARE) model, where two distinct embedding tables are initialized and learned separately to fully decouple attention and representation. Extensive experiments and analysis demonstrate that DARE provides more accurate search of correlated behaviors and outperforms baselines with AUC gains up to 0.9% on public datasets and notable online system improvements. Furthermore, decoupling embedding spaces allows us to reduce the attention embedding dimension and accelerate the search procedure by 50% without significant performance impact, enabling more efficient, high-performance online serving.

LLM-Pilot: Characterize and Optimize Performance of your LLM Inference Services

As Large Language Models (LLMs) are rapidly growing in popularity, LLM inference services must be able to serve requests from thousands of users while satisfying performance requirements. The performance of an LLM inference service is largely determined by the hardware onto which it is deployed, but understanding of which hardware will deliver on performance requirements remains challenging. In this work we present LLM-Pilot - a first-of-its-kind system for characterizing and predicting performance of LLM inference services. LLM-Pilot performs benchmarking of LLM inference services, under a realistic workload, across a variety of GPUs, and optimizes the service configuration for each considered GPU to maximize performance. Finally, using this characterization data, LLM-Pilot learns a predictive model, which can be used to recommend the most cost-effective hardware for a previously unseen LLM. Compared to existing methods, LLM-Pilot can deliver on performance requirements 33% more frequently, whilst reducing costs by 60% on average.

Multi-modal clothing recommendation model based on large model and VAE enhancement

Accurately recommending products has long been a subject requiring in-depth research. This study proposes a multimodal paradigm for clothing recommendations. Specifically, it designs a multimodal analysis method that integrates clothing description texts and images, utilizing a pre-trained large language model to deeply explore the hidden meanings of users and products. Additionally, a variational encoder is employed to learn the relationship between user information and products to address the cold start problem in recommendation systems. This study also validates the significant performance advantages of this method over various recommendation system methods through extensive ablation experiments, providing crucial practical guidance for the comprehensive optimization of recommendation systems.

BayesCNS: A Unified Bayesian Approach to Address Cold Start and Non-Stationarity in Search Systems at Scale

Information Retrieval (IR) systems used in search and recommendation platforms frequently employ Learning-to-Rank (LTR) models to rank items in response to user queries. These models heavily rely on features derived from user interactions, such as clicks and engagement data. This dependence introduces cold start issues for items lacking user engagement and poses challenges in adapting to non-stationary shifts in user behavior over time. We address both challenges holistically as an online learning problem and propose BayesCNS, a Bayesian approach designed to handle cold start and non-stationary distribution shifts in search systems at scale. BayesCNS achieves this by estimating prior distributions for user-item interactions, which are continuously updated with new user interactions gathered online. This online learning procedure is guided by a ranker model, enabling efficient exploration of relevant items using contextual information provided by the ranker. We successfully deployed BayesCNS in a large-scale search system and demonstrated its efficacy through comprehensive offline and online experiments. Notably, an online A/B experiment showed a 10.60% increase in new item interactions and a 1.05% improvement in overall success metrics over the existing production baseline.

Quantifying User Coherence: A Unified Framework for Cross-Domain Recommendation Analysis

The effectiveness of Recommender Systems (RS) is closely tied to the quality and distinctiveness of user profiles, yet despite many advancements in raw performance, the sensitivity of RS to user profile quality remains under-researched. This paper introduces novel information-theoretic measures for understanding recommender systems: a "surprise" measure quantifying users' deviations from popular choices, and a "conditional surprise" measure capturing user interaction coherence. We evaluate 7 recommendation algorithms across 9 datasets, revealing the relationships between our measures and standard performance metrics. Using a rigorous statistical framework, our analysis quantifies how much user profile density and information measures impact algorithm performance across domains. By segmenting users based on these measures, we achieve improved performance with reduced data and show that simpler algorithms can match complex ones for low-coherence users. Additionally, we employ our measures to analyze how well different recommendation algorithms maintain the coherence and diversity of user preferences in their predictions, providing insights into algorithm behavior. This work advances the theoretical understanding of user behavior and practical heuristics for personalized recommendation systems, promoting more efficient and adaptive architectures.

A Survey on Point-of-Interest Recommendation: Models, Architectures, and Security

The widespread adoption of smartphones and Location-Based Social Networks has led to a massive influx of spatio-temporal data, creating unparalleled opportunities for enhancing Point-of-Interest (POI) recommendation systems. These advanced POI systems are crucial for enriching user experiences, enabling personalized interactions, and optimizing decision-making processes in the digital landscape. However, existing surveys tend to focus on traditional approaches and few of them delve into cutting-edge developments, emerging architectures, as well as security considerations in POI recommendations. To address this gap, our survey stands out by offering a comprehensive, up-to-date review of POI recommendation systems, covering advancements in models, architectures, and security aspects. We systematically examine the transition from traditional models to advanced techniques such as large language models. Additionally, we explore the architectural evolution from centralized to decentralized and federated learning systems, highlighting the improvements in scalability and privacy. Furthermore, we address the increasing importance of security, examining potential vulnerabilities and privacy-preserving approaches. Our taxonomy provides a structured overview of the current state of POI recommendation, while we also identify promising directions for future research in this rapidly advancing field.

Price-guided user attention in large-scale E-commerce group recommendation

Existing group recommender systems utilize attention mechanisms to identify critical users who influence group decisions the most. We analyzed user attention scores from a widely-used group recommendation model on a real-world E-commerce dataset and found that item price and user interaction history significantly influence the selection of critical users. When item prices are low, users with extensive interaction histories are more influential in group decision-making. Conversely, their influence diminishes with higher item prices. Based on these observations, we propose a novel group recommendation approach that incorporates item price as a guiding factor for user aggregation. Our model employs an adaptive sigmoid function to adjust output logits based on item prices, enhancing the accuracy of user aggregation. Our model can be plugged into any attention-based group recommender system if the price information is available. We evaluate our model's performance on a public benchmark and a real-world dataset. We compare it with other state-of-the-art group recommendation methods. Our results demonstrate that our price-guided user attention approach outperforms the state-of-the-art methods in terms of hit ratio and mean square error.

Does Graph Prompt Work? A Data Operation Perspective with Theoretical Analysis

In recent years, graph prompting has emerged as a promising research direction, enabling the learning of additional tokens or subgraphs appended to the original graphs without requiring retraining of pre-trained graph models across various applications. This novel paradigm, shifting from the traditional pretraining and finetuning to pretraining and prompting has shown significant empirical success in simulating graph data operations, with applications ranging from recommendation systems to biological networks and graph transferring. However, despite its potential, the theoretical underpinnings of graph prompting remain underexplored, raising critical questions about its fundamental effectiveness. The lack of rigorous theoretical proof of why and how much it works is more like a dark cloud over the graph prompt area to go further. To fill this gap, this paper introduces a theoretical framework that rigorously analyzes graph prompting from a data operation perspective. Our contributions are threefold: First, we provide a formal guarantee theorem, demonstrating graph prompts capacity to approximate graph transformation operators, effectively linking upstream and downstream tasks. Second, we derive upper bounds on the error of these data operations by graph prompts for a single graph and extend this discussion to batches of graphs, which are common in graph model training. Third, we analyze the distribution of data operation errors, extending our theoretical findings from linear graph models (e.g., GCN) to non-linear graph models (e.g., GAT). Extensive experiments support our theoretical results and confirm the practical implications of these guarantees.