Search for: All records

Traditional recommender systems based on revealed preferences often fail to capture the fundamental duality in user behavior, where consumption choices are driven by both inherent value (enrichment) and instant appeal (temptation). Consequently, these systems may generate recommendations that prioritize short-term engagement over long-lasting user satisfaction. We propose a novel recommender design that explicitly models the tension between enrichment and temptation. We introduce a behavioral model that accounts for how both enrichment and temptation influence user choices, while incorporating the reality of off-platform alternatives. Building on this model, we formulate a novel recommendation objective aligned with maximizing consumed enrichment and prove the optimality of a locally greedy recommendation strategy. Finally, we present an estimation framework that leverages the distinction between explicit user feedback and implicit choice data while making minimal assumptions about off-platform options. Through comprehensive evaluation using both synthetic simulations and real-world data from the MovieLens dataset, we demonstrate that our approach consistently outperforms competitive baselines that ignore temptation dynamics either by assuming revealed preferences or recommending solely based on enrichment. Our work represents a paradigm shift toward more nuanced and user-centric recommender design, with significant implications for developing responsible AI systems that genuinely serve users’ long-term interests rather than merely maximizing engagement. 

We introduce the GEM (Generative Estimator for Mutual Information), an evaluation metric for assessing language generation by large language models (LLMs), particularly in generating informative judgments, without the need for a gold standard reference. GEM broadens the scenarios where we can benchmark LLM generation performance-from traditional ones, like machine translation and summarization, where gold standard references are readily available, to subjective tasks without clear gold standards, such as academic peer review. GEM uses a generative model to estimate mutual information between candidate and reference responses, without requiring the reference to be a gold standard. In experiments on two human-annotated datasets, GEM demonstrates competitive correlations with human scores compared to the state-of-the-art GPT-4o Examiner, and outperforms all other baselines. Additionally, GEM is more robust against strategic manipulation, such as rephrasing or elongation, which can artificially inflate scores under a GPT-4o Examiner. We also present GRE-bench (Generating Review Evaluation Benchmark) which evaluates LLMs based on how well they can generate high-quality peer reviews for academic research papers. Because GRE-bench is based upon GEM, it inherits its robustness properties. Additionally, GRE-bench circumvents data contamination problems (or data leakage) by using the continuous influx of new open-access research papers and peer reviews each year. We show GRE-bench results of various popular LLMs on their peer review capabilities using the ICLR2023 dataset. 

Do common assumptions about the way that crowd workers make mistakes in microtask (labeling) applications manifest in real crowdsourcing data? Prior work only addresses this question indirectly. Instead, it primarily focuses on designing new label aggregation algorithms, seeming to imply that better performance justifies any additional assumptions. However, empirical evidence in past instances has raised significant challenges to common assumptions. We continue this line of work, using crowdsourcing data itself as directly as possible to interrogate several basic assumptions about workers and tasks. We find strong evidence that the assumption that workers respond correctly to each task with a constant probability, which is common in theoretical work, is implausible in real data. We also illustrate how heterogeneity among tasks and workers can take different forms, which have different implications for the design and evaluation of label aggregation algorithms. 

In the setting of conference peer review, the conference aims to accept high-quality papers and reject low-quality papers based on noisy review scores. A recent work proposes the isotonic mechanism, which can elicit the ranking of paper qualities from an author with multiple submissions to help improve the conference's decisions. However, the isotonic mechanism relies on the assumption that the author's utility is both an increasing and a convex function with respect to the review score, which is often violated in realistic settings (e.g.~when authors aim to maximize the number of accepted papers). In this paper, we propose a sequential review mechanism that can truthfully elicit the ranking information from authors while only assuming the agent's utility is increasing with respect to the true quality of her accepted papers. The key idea is to review the papers of an author in a sequence based on the provided ranking and conditioning the review of the next paper on the review scores of the previous papers. Advantages of the sequential review mechanism include: 1) eliciting truthful ranking information in a more realistic setting than prior work; 2) reducing the reviewing workload and increasing the average quality of papers being reviewed; 3) incentivizing authors to write fewer papers of higher quality. 

We propose measurement integrity, a property related to ex post reward fairness, as a novel desideratum for peer prediction mechanisms in many natural applications. Like robustness against strategic reporting, the property that has been the primary focus of the peer prediction literature, measurement integrity is an important consideration for understanding the practical performance of peer prediction mechanisms. We perform computational experiments, both with an agent-based model and with real data, to empirically evaluate peer prediction mechanisms according to both of these important properties. Our evaluations simulate the application of peer prediction mechanisms to peer assessment---a setting in which ex post fairness concerns are particularly salient. We find that peer prediction mechanisms, as proposed in the literature, largely fail to demonstrate significant measurement integrity in our experiments. We also find that theoretical properties concerning robustness against strategic reporting are somewhat noisy predictors of empirical performance. Further, there is an apparent trade-off between our two dimensions of analysis. The best-performing mechanisms in terms of measurement integrity are highly susceptible to strategic reporting. Ultimately, however, we show that supplementing mechanisms with realistic parametric statistical models can, in some cases, improve performance along both dimensions of our analysis and result in mechanisms that strike the best balance between them.