cs.AINov 1, 2026

Opening the Black Box of Neural Auction Mechanisms

Authors: Li Kong, Zilong Liu, Haoyang Zhou, Hanbing Liu, Qi Qi

Organizations: Gaoling School of Artificial Intelligence, Renmin University of China, Beijing, China

Abstract

Neural auction design has emerged as a powerful paradigm within automated mechanism design for modern Web platforms. Because these learned mechanisms directly dictate critical economic outcomes, their lack of internal transparency raises significant auditability and trust concerns. Opening this black box post-hoc is therefore essential, yet presents two distinctive challenges: (1) activation contexts are dense, correlated numerical profiles devoid of explicit semantic structure, and (2) feature interpretations can only be falsifiably audited if they map to measurable auction states or outcomes. In this paper, we propose a post-hoc white-box auditing framework for unpacking trained neural auctions. Using CITransNet as a representative testbed, we first employ sparse autoencoders to decompose hidden representations while faithfully preserving downstream auction behavior. Anchoring feature interpretations to native economic targets, we validate them through activation prediction and causal interventions to isolate verified features from the reconstruction dictionary. Finally, applying this pipeline across varied auction settings, we show that the verified features can serve as analytical instruments to examine how internal representations modulate strategic misreporting incentives, align with Myerson's optimal auction, and support the diagnosis of individual auctions. Our work highlights the potential of white-box mechanism auditing to build the foundational trust necessary for neural auctions to be deployed as widely adopted Web technologies. To enhance research transparency and facilitate independent inspection, we publicly release the experimental results supporting our findings at https://github.com/Li-Beverly-Kong/opening-neural-auctions.git

Figures & tables

Appendix figures & tables7 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

Oct 16, 2026

Extending Myerson's Optimal Auctions to Correlated Bidders via Neural Network Interpolation

We aim to design revenue-maximizing single-item auctions that are deterministic, strategy-proof, and ex post individually rational --- the quintessential fundamental model for optimal mechanism design. While Myerson's seminal work solved this model for independent bidders, straightforward extensions to correlated settings often result in non-monotonic, and therefore non-strategy-proof allocations. Critically, optimal allocation design for correlated bidders is NP-hard to approximate, rendering theoretical optimality guarantees in this domain computationally intractable. We establish a new standard of empirical rigor for this theoretically hard model by proposing an empirical pipeline. We synthesize neural interpolation of Myerson's greedy allocation based on marginal profits (the correlated variant of virtual valuation), formal neural verification to enforce exact strategy-proofness, and a constructive repair procedure. Empirically, our method is highly effective, consistently achieves near-optimal revenue across a wide range of distributions, including synthetic, adversarial, and real-world (consumer, financial, and industrial) datasets. Compared to existing manual and neural baselines, our approach shows substantial improvement, often reducing the revenue gap by an order of magnitude. Our study is also the first to introduce (unattainable) greedy revenue as a rigorous upper bound for empirical benchmarking, providing a definitive quantitative performance measure where true optima remain theoretically elusive. We demonstrate the generality of our approach by extending it to multi-unit auctions with unit demand and integrating our verification techniques into RegretNet to achieve exact strategy-proofness.
Feb 12, 2025

Randomly Wrong Signals: Bayesian Auction Design with ML Predictions

Machine learning can help sellers predict buyers' willingness to pay, but its predictions may be plausible and yet entirely unrelated to a buyer's value. We introduce a Bayesian auction model that distinguishes such hallucinations from ordinary measurement noise. We characterize revenue-maximizing auctions with publicly disclosed predictions in the benchmark where informative predictions are exact. For a single buyer, this characterization explains when the seller should follow a prediction and when to hedge against its failure by ignoring it or capping the price. These insights guide the design of simple auctions that account for both hallucinations and measurement noise. Numerical experiments show that the resulting auctions achieve near-optimal revenue.
Feb 26, 2026

AuditBench: Evaluating Alignment Auditing Techniques on Models with Hidden Behaviors

We introduce AuditBench, an alignment auditing benchmark. AuditBench consists of 56 language models with implanted hidden behaviors. Each model has one of 14 concerning behaviors--such as sycophantic deference, opposition to AI regulation, or secret geopolitical loyalties--which it does not confess to when directly asked. AuditBench models are highly diverse--some are subtle, while others are overt, and we use varying training techniques both for implanting behaviors and training models not to confess. To demonstrate AuditBench's utility, we develop an investigator agent that autonomously employs a configurable set of auditing tools. By measuring investigator agent success using different tools, we can evaluate their efficacy. Notably, we observe a tool-to-agent gap, where tools that perform well in standalone non-agentic evaluations fail to translate into improved performance when used with our investigator agent. We find that our most effective tools involve scaffolded calls to auxiliary models that generate diverse prompts for the target. White-box interpretability tools can be helpful, but the agent performs best with black-box tools. We also find that audit success varies greatly across training techniques: models trained on synthetic documents are easier to audit than models trained on demonstrations, with better adversarial training further increasing auditing difficulty. We release our models, agent, and evaluation framework to support future quantitative, iterative science on alignment auditing.