arXiv subjects

David Dai

Publications and source records attributed to David Dai.

5 recordsLinked to original sources

arXiv2026

Settlement Manipulation in Prediction Markets

Prediction markets increasingly list contracts settling on an asset price that holders can move by trading the underlying. We build a model showing that such contracts transfer wealth from prediction-market liquidity traders to manipulators and harm price discovery in the underlying, even as it becomes more liquid. After the launch of Polymarket's five-minute Bitcoin contract, settlement-time spot order flow spikes, causing large price reversals after settlement. Manipulators capture a large amount of profit, mostly from retail. Manipulation is largely absent in the fifteen-minute contracts: lengthening the contract horizon removes it, providing the market-design remedy our model and evidence support.

q-fin.TR↗

arXiv2026

Understanding the Behaviors of Environment-aware Information Retrieval

Recent retrieval-augmented generation (RAG) approaches have demonstrated strong capability in handling complex queries, yet current research overlooks a critical challenge: different retrievers require fundamentally different query formulation strategies for optimal performance. In this work, we present the first systematic analysis of how LLMs can learn to adapt their query formulation strategies for different retrievers via reinforcement learning (RL). Our empirical study reveals that RL effectively teaches an LLM to tailor its queries to specific retriever characteristics. We discover that different retrievers exhibit surprisingly distinct optimal query styles (e.g., descriptive vs. question-like), suggesting strategies learned for one retriever ineffective for another. We further show that performance can be enhanced by incorporating retriever-specific human guidance and by scaling model size. To facilitate learning over multi-retrieval-step trajectories, we introduce a branching-based rollout technique that improves training stability. Our work provides the first empirical evidence and actionable insights for building truly retriever-aware RAG systems. Code and resources are available at https://github.com/LCO-Embedding/Envs-aware-Information-Retrieval.

cs.CL↗

arXiv2026

AdNanny: One Reasoning LLM for All Offline Ads Recommendation Tasks

Large Language Models (LLMs) have shown strong capabilities in Natural Language Understanding and Generation, but deploying them directly in online advertising systems is often impractical due to strict millisecond-level latency constraints. This has motivated the use of LLMs offline to improve retrieval, ranking, and recommendation models. Existing solutions typically fine-tune separate LLMs for individual tasks such as query-ad relevance labeling, keyword-based query generation, and user profiling. This results in redundant models, high maintenance cost, and limited performance gains despite substantial overlap in domain knowledge and reasoning patterns. We introduce AdNanny, a unified reasoning-centric LLM that serves as a shared backbone for offline advertising tasks. AdNanny is obtained by fine-tuning a public 671B-parameter DeepSeek-R1 checkpoint using a scalable training system that supports hybrid dense-MoE parallelism. We construct reasoning-augmented corpora that pair structured supervision with step-by-step natural language explanations. A multi-task supervised fine-tuning stage with adaptive reweighting enables AdNanny to handle diverse labeling and generation tasks in a consistent reasoning format. This is followed by reinforcement learning using downstream advertising metrics to align model behavior with online retrieval and ranking objectives. AdNanny is deployed in production within Bing Ads, where it significantly reduces manual labeling effort and improves accuracy across multiple offline tasks. By consolidating many task-specific models into a single reasoning-centric foundation model, AdNanny provides a scalable and cost-effective solution for large-scale advertising systems.

cs.SE↗

arXiv2026

Prediction-Guided Control in Data Center Networks

In this paper, we design, implement, and evaluate Polyphony, a system to give network operators a new way to control and reduce the frequency of poor tail latency events in multi-class data center networks, on the time scale of minutes. Polyphony is designed to be complementary to other adaptive mechanisms like congestion control and traffic engineering, but targets different aspects of network operation that have previously been considered static. By contrast to Polyphony, prior model-free optimization methods work best when there are only a few relevant degrees of freedom and where workloads and measurements are stable, assumptions not present in modern data center networks. Polyphony develops novel methods for measuring, predicting, and controlling network quality of service metrics for a dynamically changing workload. First, we monitor and aggregate workloads on a network-wide basis; we use the result as input to an approximate counterfactual prediction engine that estimates the effect of potential network configuration changes on network quality of service; we apply the best candidate and repeat in a closed-loop manner aimed at rapidly and stably converging to a configuration that meets operator goals. Using CloudLab on a simple topology, we observe that Polyphony converges to tight SLOs within ten minutes, and re-stabilizes after large workload shifts within fifteen minutes, while the prior state of the art fails to adapt.

cs.NI↗

arXiv2017

Multipath IP Routing on End Devices: Motivation, Design, and Performance

Most end devices are now equipped with multiple network interfaces. Applications can exploit all available interfaces and benefit from multipath transmission. Recently Multipath TCP (MPTCP) was proposed to implement multipath transmission at the transport layer and has attracted lots of attention from academia and industry. However, MPTCP only supports TCP-based applications and its multipath routing flexibility is limited. In this paper, we investigate the possibility of orchestrating multipath transmission from the network layer of end devices, and develop a Multipath IP (MPIP) design consisting of signaling, session and path management, multipath routing, and NAT traversal. We implement MPIP in Linux and Android kernels. Through controlled lab experiments and Internet experiments, we demonstrate that MPIP can effectively achieve multipath gains at the network layer. It not only supports the legacy TCP and UDP protocols, but also works seamlessly with MPTCP. By facilitating user-defined customized routing, MPIP can route traffic from competing applications in a coordinated fashion to maximize the aggregate user Quality-of-Experience.

cs.NI↗