Unified Representation Learning for Multi-Intent Diversity and Behavioral Uncertainty in Recommender Systems

This paper addresses the challenge of jointly modeling user intent diversity and behavioral uncertainty in recommender systems. A unified representation learning framework is proposed. The framework builds a multi-intent representation module and an uncertainty modeling mechanism. It extracts multi-granularity interest structures from user behavior sequences. Behavioral ambiguity and preference fluctuation are captured using Bayesian distribution modeling. In the multi-intent modeling part, the model introduces multiple latent intent vectors. These vectors are weighted and fused using an attention mechanism to generate semantically rich representations of long-term user preferences. In the uncertainty modeling part, the model learns the mean and covariance of behavior representations through Gaussian distributions. This reflects the user's confidence in different behavioral contexts. Next, a learnable fusion strategy is used to combine long-term intent and short-term behavior signals. This produces the final user representation, improving both recommendation accuracy and robustness. The method is evaluated on standard public datasets. Experimental results show that it outperforms existing representative models across multiple metrics. It also demonstrates greater stability and adaptability under cold-start and behavioral disturbance scenarios. The approach alleviates modeling bottlenecks faced by traditional methods when dealing with complex user behavior. These findings confirm the effectiveness and practical value of the unified modeling strategy in real-world recommendation tasks.

What Would an LLM Do? Evaluating Policymaking Capabilities of Large Language Models

Large language models (LLMs) are increasingly being adopted in high-stakes domains. Their capacity to process vast amounts of unstructured data, explore flexible scenarios, and handle a diversity of contextual factors can make them uniquely suited to provide new insights for the complexity of social policymaking. This article evaluates whether LLMs' are aligned with domain experts (and among themselves) to inform social policymaking on the subject of homelessness alleviation - a challenge affecting over 150 million people worldwide. We develop a novel benchmark comprised of decision scenarios with policy choices across four geographies (South Bend, USA; Barcelona, Spain; Johannesburg, South Africa; Macau SAR, China). The policies in scope are grounded in the conceptual framework of the Capability Approach for human development. We also present an automated pipeline that connects the benchmarked policies to an agent-based model, and we explore the social impact of the recommended policies through simulated social scenarios. The paper results reveal promising potential to leverage LLMs for social policy making. If responsible guardrails and contextual calibrations are introduced in collaboration with local domain experts, LLMs can provide humans with valuable insights, in the form of alternative policies at scale.

No Thoughts Just AI: Biased LLM Recommendations Limit Human Agency in Resume Screening

In this study, we conduct a resume-screening experiment (N=528) where people collaborate with simulated AI models exhibiting race-based preferences (bias) to evaluate candidates for 16 high and low status occupations. Simulated AI bias approximates factual and counterfactual estimates of racial bias in real-world AI systems. We investigate people's preferences for White, Black, Hispanic, and Asian candidates (represented through names and affinity groups on quality-controlled resumes) across 1,526 scenarios and measure their unconscious associations between race and status using implicit association tests (IATs), which predict discriminatory hiring decisions but have not been investigated in human-AI collaboration. When making decisions without AI or with AI that exhibits no race-based preferences, people select all candidates at equal rates. However, when interacting with AI favoring a particular group, people also favor those candidates up to 90% of the time, indicating a significant behavioral shift. The likelihood of selecting candidates whose identities do not align with common race-status stereotypes can increase by 13% if people complete an IAT before conducting resume screening. Finally, even if people think AI recommendations are low quality or not important, their decisions are still vulnerable to AI bias under certain circumstances. This work has implications for people's autonomy in AI-HITL scenarios, AI and work, design and evaluation of AI hiring systems, and strategies for mitigating bias in collaborative decision-making tasks. In particular, organizational and regulatory policy should acknowledge the complex nature of AI-HITL decision making when implementing these systems, educating people who use them, and determining which are subject to oversight.

Efficient Item ID Generation for Large-Scale LLM-based Recommendation

Integrating product catalogs and user behavior into LLMs can enhance recommendations with broad world knowledge, but the scale of real-world item catalogs, often containing millions of discrete item identifiers (Item IDs), poses a significant challenge. This contrasts with the smaller, tokenized text vocabularies typically used in LLMs. The predominant view within the LLM-based recommendation literature is that it is infeasible to treat item ids as a first class citizen in the LLM and instead some sort of tokenization of an item into multiple tokens is required. However, this creates a key practical bottleneck in serving these models for real-time low-latency applications. Our paper challenges this predominant practice and integrates item ids as first class citizens into the LLM. We provide simple, yet highly effective, novel training and inference modifications that enable single-token representations of items and single-step decoding. Our method shows improvements in recommendation quality (Recall and NDCG) over existing techniques on the Amazon shopping datasets while significantly improving inference efficiency by 5x-14x. Our work offers an efficiency perspective distinct from that of other popular approaches within LLM-based recommendation, potentially inspiring further research and opening up a new direction for integrating IDs into LLMs. Our code is available here https://drive.google.com/file/d/1cUMj37rV0Z1bCWMdhQ6i4q4eTRQLURtC

LLMs for estimating positional bias in logged interaction data

Recommender and search systems commonly rely on Learning To Rank models trained on logged user interactions to order items by predicted relevance. However, such interaction data is often subject to position bias, as users are more likely to click on items that appear higher in the ranking, regardless of their actual relevance. As a result, newly trained models may inherit and reinforce the biases of prior ranking models rather than genuinely improving relevance. A standard approach to mitigate position bias is Inverse Propensity Scoring (IPS), where the model's loss is weighted by the inverse of a propensity function, an estimate of the probability that an item at a given position is examined. However, accurate propensity estimation is challenging, especially in interfaces with complex non-linear layouts. In this paper, we propose a novel method for estimating position bias using Large Language Models (LLMs) applied to logged user interaction data. This approach offers a cost-effective alternative to online experimentation. Our experiments show that propensities estimated with our LLM-as-a-judge approach are stable across score buckets and reveal the row-column effects of Viator's grid layout that simpler heuristics overlook. An IPS-weighted reranker trained with these propensities matches the production model on standard NDCG@10 while improving weighted NDCG@10 by roughly 2%. We will verify these offline gains in forthcoming live-traffic experiments.

ACT: Automated Constraint Targeting for Multi-Objective Recommender Systems

Recommender systems often must maximize a primary objective while ensuring secondary ones satisfy minimum thresholds, or "guardrails." This is critical for maintaining a consistent user experience and platform ecosystem, but enforcing these guardrails despite orthogonal system changes is challenging and often requires manual hyperparameter tuning. We introduce the Automated Constraint Targeting (ACT) framework, which automatically finds the minimal set of hyperparameter changes needed to satisfy these guardrails. ACT uses an offline pairwise evaluation on unbiased data to find solutions and continuously retrains to adapt to system and user behavior changes. We empirically demonstrate its efficacy and describe its deployment in a large-scale production environment.

DMGIN: How Multimodal LLMs Enhance Large Recommendation Models for Lifelong User Post-click Behaviors

Modeling user interest based on lifelong user behavior sequences is crucial for enhancing Click-Through Rate (CTR) prediction. However, long post-click behavior sequences themselves pose severe performance issues: the sheer volume of data leads to high computational costs and inefficiencies in model training and inference. Traditional methods address this by introducing two-stage approaches, but this compromises model effectiveness due to incomplete utilization of the full sequence context. More importantly, integrating multimodal embeddings into existing large recommendation models (LRM) presents significant challenges: These embeddings often exacerbate computational burdens and mismatch with LRM architectures. To address these issues and enhance the model's efficiency and accuracy, we introduce Deep Multimodal Group Interest Network (DMGIN). Given the observation that user post-click behavior sequences contain a large number of repeated items with varying behaviors and timestamps, DMGIN employs Multimodal LLMs(MLLM) for grouping to reorganize complete lifelong post-click behavior sequences more effectively, with almost no additional computational overhead, as opposed to directly introducing multimodal embeddings. To mitigate the potential information loss from grouping, we have implemented two key strategies. First, we analyze behaviors within each group using both interest statistics and intra-group transformers to capture group traits. Second, apply inter-group transformers to temporally ordered groups to capture the evolution of user group interests. Our extensive experiments on both industrial and public datasets confirm the effectiveness and efficiency of DMGIN. The A/B test in our LBS advertising system shows that DMGIN improves CTR by 4.7% and Revenue per Mile by 2.3%.

Benchmarking GPT-5 in Radiation Oncology: Measurable Gains, but Persistent Need for Expert Oversight

Introduction: Large language models (LLM) have shown great potential in clinical decision support. GPT-5 is a novel LLM system that has been specifically marketed towards oncology use. Methods: Performance was assessed using two complementary benchmarks: (i) the ACR Radiation Oncology In-Training Examination (TXIT, 2021), comprising 300 multiple-choice items, and (ii) a curated set of 60 authentic radiation oncologic vignettes representing diverse disease sites and treatment indications. For the vignette evaluation, GPT-5 was instructed to generate concise therapeutic plans. Four board-certified radiation oncologists rated correctness, comprehensiveness, and hallucinations. Inter-rater reliability was quantified using Fleiss' \k{appa}. Results: On the TXIT benchmark, GPT-5 achieved a mean accuracy of 92.8%, outperforming GPT-4 (78.8%) and GPT-3.5 (62.1%). Domain-specific gains were most pronounced in Dose and Diagnosis. In the vignette evaluation, GPT-5's treatment recommendations were rated highly for correctness (mean 3.24/4, 95% CI: 3.11-3.38) and comprehensiveness (3.59/4, 95% CI: 3.49-3.69). Hallucinations were rare with no case reaching majority consensus for their presence. Inter-rater agreement was low (Fleiss' \k{appa} 0.083 for correctness), reflecting inherent variability in clinical judgment. Errors clustered in complex scenarios requiring precise trial knowledge or detailed clinical adaptation. Discussion: GPT-5 clearly outperformed prior model variants on the radiation oncology multiple-choice benchmark. Although GPT-5 exhibited favorable performance in generating real-world radiation oncology treatment recommendations, correctness ratings indicate room for further improvement. While hallucinations were infrequent, the presence of substantive errors underscores that GPT-5-generated recommendations require rigorous expert oversight before clinical implementation.

I Stolenly Swear That I Am Up to (No) Good: Design and Evaluation of Model Stealing Attacks

Model stealing attacks endanger the confidentiality of machine learning models offered as a service. Although these models are kept secret, a malicious party can query a model to label data samples and train their own substitute model, violating intellectual property. While novel attacks in the field are continually being published, their design and evaluations are not standardised, making it challenging to compare prior works and assess progress in the field. This paper is the first to address this gap by providing recommendations for designing and evaluating model stealing attacks. To this end, we study the largest group of attacks that rely on training a substitute model -- those attacking image classification models. We propose the first comprehensive threat model and develop a framework for attack comparison. Further, we analyse attack setups from related works to understand which tasks and models have been studied the most. Based on our findings, we present best practices for attack development before, during, and beyond experiments and derive an extensive list of open research questions regarding the evaluation of model stealing attacks. Our findings and recommendations also transfer to other problem domains, hence establishing the first generic evaluation methodology for model stealing attacks.

NewsReX: A More Efficient Approach to News Recommendation with Keras 3 and JAX

Reproducing and comparing results in news recommendation research has become increasingly difficult. This is due to a fragmented ecosystem of diverse codebases, varied configurations, and mainly due to resource-intensive models. We introduce NewsReX, an open-source library designed to streamline this process. Our key contribution is a modern implementation built on Keras 3 and JAX, which provides an increase in computational efficiency. Experiments show that NewsReX is faster than current implementations. To support broader research, we provide a straightforward guide and scripts for training models on custom datasets. We validated this functionality using a proprietary Japanese news dataset from Nikkei News, a leading Japanese media corporation renowned for its comprehensive coverage of business, economic, and financial news. NewsReX makes reproducing complex experiments faster and more accessible to a wider range of hardware making sure the speed up it also achieved for less powerful GPUs, like an 8GB RTX 3060 Ti. Beyond the library, this paper offers an analysis of key training parameters often overlooked in the literature, including the effect of different negative sampling strategies, the varying number of epochs, the impact of random batching, and more. This supplementary analysis serves as a valuable reference for future research, aiming to reduce redundant computation when comparing baselines and guide best practices. Code available at https://github.com/igor17400/NewsReX.