arXiv subjects

Moshe Tennenholtz

Publications and source records attributed to Moshe Tennenholtz.

At least 37 records · Page 2Linked to original sources

arXiv2025

Data Sharing with a Generative AI Competitor

As GenAI platforms grow, their dependence on content from competing providers, combined with access to alternative data sources, creates new challenges for data-sharing decisions. In this paper, we provide a model of data sharing between a content creation firm and a GenAI platform that can also acquire content from third-party experts. The interaction is modeled as a Stackelberg game: the firm first decides how much of its proprietary dataset to share with GenAI, and GenAI subsequently determines how much additional data to acquire from external experts. Their utilities depend on user traffic, monetary transfers, and the cost of acquiring additional data from external experts. We characterize the unique subgame perfect equilibrium of the game and uncover a surprising phenomenon: The firm may be willing to pay GenAI to share the firm's own data, leading to a costly data-sharing equilibrium. We further characterize the set of Pareto improving data prices, and show that such improvements occur only when the firm pays to share data. Finally, we study how the price can be set to optimize different design objectives, such as promoting firm data sharing, expert data acquisition, or a balance of both. Our results shed light on the economic forces shaping data-sharing partnerships in the age of GenAI, and provide guidance for platforms, regulators and policymakers seeking to design effective data exchange mechanisms.

cs.GT↗

arXiv2025

Human Choice Prediction in Language-based Persuasion Games: Simulation-based Off-Policy Evaluation

Recent advances in Large Language Models (LLMs) have spurred interest in designing LLM-based agents for tasks that involve interaction with human and artificial agents. This paper addresses a key aspect in the design of such agents: predicting human decisions in off-policy evaluation (OPE). We focus on language-based persuasion games, where an expert aims to influence the decision-maker through verbal messages. In our OPE framework, the prediction model is trained on human interaction data collected from encounters with one set of expert agents, and its performance is evaluated on interactions with a different set of experts. Using a dedicated application, we collected a dataset of 87K decisions from humans playing a repeated decision-making game with artificial agents. To enhance off-policy performance, we propose a simulation technique involving interactions across the entire agent space and simulated decision-makers. Our learning strategy yields significant OPE gains, e.g., improving prediction accuracy in the top 15% challenging cases by 7.1%. Our code and the large dataset we collected and generated are submitted as supplementary material and publicly available in our GitHub repository: https://github.com/eilamshapira/HumanChoicePrediction

cs.LG↗

arXiv2025

Predicting human decisions with behavioral theories and machine learning

Predicting human decisions under risk and uncertainty remains a fundamental challenge across disciplines. Existing models often struggle even in highly stylized tasks like choice between lotteries. We introduce BEAST Gradient Boosting (BEAST-GB), a hybrid model integrating behavioral theory (BEAST) with machine learning. We first present CPC18, a competition for predicting risky choice, in which BEAST-GB won. Then, using two large datasets, we demonstrate BEAST-GB predicts more accurately than neural networks trained on extensive data and dozens of existing behavioral models. BEAST-GB also generalizes robustly across unseen experimental contexts, surpassing direct empirical generalization, and helps refine and improve the behavioral theory itself. Our analyses highlight the potential of anchoring predictions on behavioral theory even in data-rich settings and even when the theory alone falters. Our results underscore how integrating machine learning with theoretical frameworks, especially those-like BEAST-designed for prediction, can improve our ability to predict and understand human behavior.

cs.AI↗

arXiv2025

Robust-IR @ SIGIR 2025: The First Workshop on Robust Information Retrieval

With the advancement of information retrieval (IR) technologies, robustness is increasingly attracting attention. When deploying technology into practice, we consider not only its average performance under normal conditions but, more importantly, its ability to maintain functionality across a variety of exceptional situations. In recent years, the research on IR robustness covers theory, evaluation, methodology, and application, and all of them show a growing trend. The purpose of this workshop is to systematize the latest results of each research aspect, to foster comprehensive communication within this niche domain while also bridging robust IR research with the broader community, and to promote further future development of robust IR. To avoid the one-sided talk of mini-conferences, this workshop adopts a highly interactive format, including round-table and panel discussion sessions, to encourage active participation and meaningful exchange among attendees.

cs.IR↗

arXiv2025

White Hat Search Engine Optimization using Large Language Models

We present novel white-hat search engine optimization techniques based on genAI and demonstrate their empirical merits.

cs.IR↗

arXiv2025

A Multi-Agent Perspective on Modern Information Retrieval

The rise of large language models (LLMs) has introduced a new era in information retrieval (IR), where queries and documents that were once assumed to be generated exclusively by humans can now also be created by automated agents. These agents can formulate queries, generate documents, and perform ranking. This shift challenges some long-standing IR paradigms and calls for a reassessment of both theoretical frameworks and practical methodologies. We advocate for a multi-agent perspective to better capture the complex interactions between query agents, document agents, and ranker agents. Through empirical exploration of various multi-agent retrieval settings, we reveal the significant impact of these interactions on system performance. Our findings underscore the need to revisit classical IR paradigms and develop new frameworks for more effective modeling and evaluation of modern retrieval systems.

cs.IR↗

arXiv2025

Towards Hybrid Traffic Laws for Mixed Flow of Human-Driven Vehicles and Connected Autonomous Vehicles

Hybrid traffic laws represent an innovative approach to managing mixed environments of connected autonomous vehicles (CAVs) and human-driven vehicles (HDVs) by introducing separate sets of regulations for each vehicle type. These laws are designed to leverage the unique capabilities of CAVs while ensuring both types of cars coexist effectively, ultimately aiming to enhance overall social welfare. This study uses the SUMO simulation platform to explore hybrid traffic laws in a restricted lane scenario. It evaluates static and dynamic lane access policies under varying traffic demands and CAV proportions. The policies aim to minimize average passenger delay and encourage the incorporation of autonomous vehicles with higher occupancy rates. Results demonstrate that dynamic policies significantly improve traffic flow, especially at low CAV proportions, compared to traditional dedicated bus lane strategies. These findings highlight the potential of hybrid traffic laws to enhance traffic efficiency and accelerate the transition to autonomous technology.

cs.MA↗

arXiv2025

CSP: A Simulator For Multi-Agent Ranking Competitions

In ranking competitions, document authors compete for the highest rankings by modifying their content in response to past rankings. Previous studies focused on human participants, primarily students, in controlled settings. The rise of generative AI, particularly Large Language Models (LLMs), introduces a new paradigm: using LLMs as document authors. This approach addresses scalability constraints in human-based competitions and reflects the growing role of LLM-generated content on the web-a prime example of ranking competition. We introduce a highly configurable ranking competition simulator that leverages LLMs as document authors. It includes analytical tools to examine the resulting datasets. We demonstrate its capabilities by generating multiple datasets and conducting an extensive analysis. Our code and datasets are publicly available for research.

cs.IR↗

arXiv2025

On the Convergence of No-Regret Dynamics in Information Retrieval Games with Proportional Ranking Functions

Publishers who publish their content on the web act strategically, in a behavior that can be modeled within the online learning framework. Regret, a central concept in machine learning, serves as a canonical measure for assessing the performance of learning agents within this framework. We prove that any proportional content ranking function with a concave activation function induces games in which no-regret learning dynamics converge. Moreover, for proportional ranking functions, we prove the equivalence of the concavity of the activation function, the social concavity of the induced games and the concavity of the induced games. We also study the empirical trade-offs between publishers' and users' welfare, under different choices of the activation function, using a state-of-the-art no-regret dynamics algorithm. Furthermore, we demonstrate how the choice of the ranking function and changes in the ecosystem structure affect these welfare measures, as well as the dynamics' convergence rate.

cs.GT↗

arXiv2025

Search results diversification in competitive search

In Web retrieval, there are many cases of competition between authors of Web documents: their incentive is to have their documents highly ranked for queries of interest. As such, the Web is a prominent example of a competitive search setting. Past work on competitive search focused on ranking functions based solely on relevance estimation. We study ranking functions that integrate a results-diversification aspect. We show that the competitive search setting with diversity-based ranking has an equilibrium. Furthermore, we theoretically and empirically show that the phenomenon of authors mimicking content in documents highly ranked in the past, which was demonstrated in previous work, is mitigated when search results diversification is applied.

cs.IR↗

arXiv2024

On the Power of Strategic Corpus Enrichment in Content Creation Games

Search and recommendation ecosystems exhibit competition among content creators. This competition has been tackled in a variety of game-theoretic frameworks. Content creators generate documents with the aim of being recommended by a content ranker for various information needs. In order for the ecosystem, modeled as a content ranking game, to be effective and maximize user welfare, it should guarantee stability, where stability is associated with the existence of pure Nash equilibrium in the corresponding game. Moreover, if the contents' ranking algorithm possesses a game in which any best-response learning dynamics of the content creators converge to equilibrium of high welfare, the system is considered highly attractive. However, as classical content ranking algorithms, employed by search and recommendation systems, rank documents by their distance to information needs, it has been shown that they fail to provide such stability properties. As a result, novel content ranking algorithms have been devised. In this work, we offer an alternative approach: corpus enrichment with a small set of fixed dummy documents. It turns out that, with the right design, such enrichment can lead to pure Nash equilibrium and even to the convergence of any best-response dynamics to a high welfare result, where we still employ the classical/current content ranking approach. We show two such corpus enrichment techniques with tight bounds on the number of documents needed to obtain the desired results. Interestingly, our study is a novel extension of Borel's Colonel Blotto game.

cs.GT↗

arXiv2024

Reputation-based Persuasion Platforms

In this paper, we introduce a two-stage Bayesian persuasion model in which a third-party platform controls the information available to the sender about users' preferences. We aim to characterize the optimal information disclosure policy of the platform, which maximizes average user utility, under the assumption that the sender also follows its own optimal policy. We show that this problem can be reduced to a model of market segmentation, in which probabilities are mapped into valuations. We then introduce a repeated variation of the persuasion platform problem in which myopic users arrive sequentially. In this setting, the platform controls the sender's information about users and maintains a reputation for the sender, punishing it if it fails to act truthfully on a certain subset of signals. We provide a characterization of the optimal platform policy in the reputation-based setting, which is then used to simplify the optimization problem of the platform.

cs.GT↗

arXiv2024

STEER: Assessing the Economic Rationality of Large Language Models

There is increasing interest in using LLMs as decision-making "agents." Doing so includes many degrees of freedom: which model should be used; how should it be prompted; should it be asked to introspect, conduct chain-of-thought reasoning, etc? Settling these questions -- and more broadly, determining whether an LLM agent is reliable enough to be trusted -- requires a methodology for assessing such an agent's economic rationality. In this paper, we provide one. We begin by surveying the economic literature on rational decision making, taxonomizing a large set of fine-grained "elements" that an agent should exhibit, along with dependencies between them. We then propose a benchmark distribution that quantitatively scores an LLMs performance on these elements and, combined with a user-provided rubric, produces a "STEER report card." Finally, we describe the results of a large-scale empirical experiment with 14 different LLMs, characterizing the both current state of the art and the impact of different model sizes on models' ability to exhibit rational behavior.

cs.CL↗

arXiv2024

Competitive Retrieval: Going Beyond the Single Query

Previous work on the competitive retrieval setting focused on a single-query setting: document authors manipulate their documents so as to improve their future ranking for a given query. We study a competitive setting where authors opt to improve their document's ranking for multiple queries. We use game theoretic analysis to prove that equilibrium does not necessarily exist. We then empirically show that it is more difficult for authors to improve their documents' rankings for multiple queries with a neural ranker than with a state-of-the-art feature-based ranker. We also present an effective approach for predicting the document most highly ranked in the next induced ranking.

cs.IR↗

arXiv2024

Prediction-sharing During Training and Inference

Two firms are engaged in a competitive prediction task. Each firm has two sources of data -- labeled historical data and unlabeled inference-time data -- and uses the former to derive a prediction model, and the latter to make predictions on new instances. We study data-sharing contracts between the firms. The novelty of our study is to introduce and highlight the differences between contracts that share prediction models only, contracts to share inference-time predictions only, and contracts to share both. Our analysis proceeds on three levels. First, we develop a general Bayesian framework that facilitates our study. Second, we narrow our focus to two natural settings within this framework: (i) a setting in which the accuracy of each firm's prediction model is common knowledge, but the correlation between the respective models is unknown; and (ii) a setting in which two hypotheses exist regarding the optimal predictor, and one of the firms has a structural advantage in deducing it. Within these two settings we study optimal contract choice. More specifically, we find the individually rational and Pareto-optimal contracts for some notable cases, and describe specific settings where each of the different sharing contracts emerge as optimal. Finally, in the third level of our analysis we demonstrate the applicability of our concepts in a synthetic simulation using real loan data.

econ.TH↗

arXiv2023

Strengthening Nash Equilibria

Nash equilibrium is often heralded as a guiding principle for rational decision-making in strategic interactions. However, it is well-known that Nash equilibrium sometimes fails as a reliable predictor of outcomes, with two of the most notable issues being the fact that it is not resilient to collusion and that there may be multiple Nash equilibria in a single game. In this paper, we show that a mechanism designer can get around these two issues for free by expanding the action sets of the original game. More precisely, given a normal-form or Bayesian game $Γ$ and a Nash equilibrium $\vecσ$ in $Γ$, a mechanism designer can construct a new game $Γ^{\vecσ}$ by expanding the action set of each player and defining appropriate utilities in the action profiles that were not already in the original game. We show that the designer can construct $Γ^{\vecσ}$ in such a way that (a) $\vecσ$ is a semi-strong Nash equilibrium of $Γ^{\vecσ}$, and (b) $\vecσ$ Pareto-dominates or quasi Pareto-dominates all other Nash equilibria of $Γ^{\vecσ}$.

cs.GT↗

arXiv2023

The Value of Mediation in Long Cheap Talk

In this paper, we study an extension of the classic long cheap talk equilibrium introduced by Aumann and Hart~\citeN{aumann-hart-03}, and ask how much can the players benefit from having a trusted mediator compared with the standard unmediated model. We focus on a setting where a fully informed sender without commitment power must disclose its information to influence the behavior of a self-interested receiver. We show that, in the case of binary actions, even though a mediator does not help neither the sender nor the receiver directly, it may still allow improving the payoff of an external decision-maker whose utility is affected by the realized state and the receiver's action. Moreover, we show that if there are more than two actions, there exist games in which both the sender and the receiver simultaneously benefit from mediation.

cs.GT↗