arXiv subjects

Celestine Mendler-Dünner

Publications and source records attributed to Celestine Mendler-Dünner.

At least 19 recordsLinked to original sources

arXiv2026

Partition, Prompt, Aggregate: Statistical Self-Consistency in Language Models

In-context learning is commonly interpreted as a form of conditional inference, in which the prompt specifies a context and the model's output is treated as an estimate of the corresponding conditional distribution. If this interpretation holds, then LLM estimates should satisfy basic probabilistic identities. In particular, the law of total probability asserts that prior-weighted conditional distributions aggregate into population-level marginals over any valid partition of the population. In this work, we investigate to what extent LLM estimates adhere to this self-consistency principle. We use binary trees as an evaluation scaffold to recursively partition a population into increasingly fine-grained subpopulations. We then prompt LLMs with verbalized subpopulation descriptions in context, aggregate the resulting estimates back into population-level estimates, and compare them across partitions of varying granularity. Applying this protocol across problem domains and state-of-the-art frontier models, we show widespread violations of basic consistency properties. An in-depth study of persona prompting reveals a pattern we call the macro fallacy: estimates reconstructed from more fine-grained subpopulation responses are often better aligned with human reference data than direct population-level estimates. This effect persists across variations in tree structure and estimation task, and can be partially recovered through implicit prompting. Together, these findings suggest that models possess relevant subpopulation knowledge but do not reliably propagate it into aggregate estimates. This gap establishes statistical self-consistency as an unsaturated, reference-free criterion for evaluating LLMs.

cs.CL↗

arXiv2026

Reaching a Consensus in Predictive Loops

Predictions in digital platforms must adapt over time as individuals update their beliefs through social interactions. At the same time, changing predictions alter the content people are exposed to and, consequently, the very beliefs they aim to forecast. This recursive coupling between predictions and individuals complicates the analysis of the long-term societal impact of predictive systems. In this work, we propose a minimal model where predictions and opinions co-evolve, combining insights from network science with concepts from performative prediction. In our model a platform's predictions influence individual opinions, which then evolve through peer interactions and form the training data for future platform model updates. We demonstrate that this co-evolution induces a novel equilibrium that qualitatively differs from standard network equilibria. In particular, we show how standard predictive objectives can drive networks toward consensus even under conditions where classical opinion-dynamics models lead to disagreement. This emerges because predictive systems dynamically adapt to changing opinions, and learning objectives create spillover effects among individuals beyond the topology of the network. We further analyze systematic deviations from standard prediction and demonstrate amplified effects of targeted platform interventions on equilibrium outcomes, compared to classical network intervention analyses. Together, our results illustrate performativity as an important, yet so far neglected, qualifying factor in social networks.

cs.SI↗

arXiv2025

Look-Ahead Reasoning on Learning Platforms

On many learning platforms, the optimization criteria guiding model training reflect the priorities of the designer rather than those of the individuals they affect. Consequently, users may act strategically to obtain more favorable outcomes. While past work has studied strategic user behavior on learning platforms, the focus has largely been on strategic responses to a deployed model, without considering the behavior of other users. In contrast, look-ahead reasoning takes into account that user actions are coupled, and -- at scale -- impact future predictions. Within this framework, we first formalize level-k thinking, a concept from behavioral economics, where users aim to outsmart their peers by looking one step ahead. We show that, while convergence to an equilibrium is accelerated, the equilibrium remains the same, providing no benefit of higher-level reasoning for individuals in the long run. Then, we focus on collective reasoning, where users take coordinated actions by optimizing through their joint impact on the model. By contrasting collective with selfish behavior, we characterize the benefits and limits of coordination; a new notion of alignment between the learner's and the users' utilities emerges as a key concept. Look-ahead reasoning can be seen as a generalization of algorithmic collective action; we thus offer the first results characterizing the utility trade-offs of coordination when contesting algorithmic systems.

cs.LG↗

arXiv2025

Performative Validity of Recourse Explanations

When applicants get rejected by an algorithmic decision system, recourse explanations provide actionable suggestions for how to change their input features to get a positive evaluation. A crucial yet overlooked phenomenon is that recourse explanations are performative: When many applicants act according to their recommendations, their collective behavior may change statistical regularities in the data and, once the model is refitted, also the decision boundary. Consequently, the recourse algorithm may render its own recommendations invalid, such that applicants who make the effort of implementing their recommendations may be rejected again when they reapply. In this work, we formally characterize the conditions under which recourse explanations remain valid under performativity. A key finding is that recourse actions may become invalid if they are influenced by or if they intervene on non-causal variables. Based on our analysis, we caution against the use of standard counterfactual explanations and causal recourse methods, and instead advocate for recourse methods that recommend actions exclusively on causal variables.

stat.ML↗

arXiv2025

Performative Prediction: Past and Future

Predictions in the social world generally influence the target of prediction, a phenomenon known as performativity. Self-fulfilling and self-negating predictions are examples of performativity. Of fundamental importance to economics, finance, and the social sciences, the notion has been absent from the development of machine learning that builds on the static perspective of pattern recognition. In machine learning applications, however, performativity often surfaces as distribution shift. A predictive model deployed on a digital platform, for example, influences behavior and thereby changes the data-generating distribution. We discuss the recently founded area of performative prediction that provides a definition and conceptual framework to study performativity in machine learning. A key element of performative prediction is a natural equilibrium notion that gives rise to new optimization challenges. What emerges is a distinction between learning and steering, two mechanisms at play in performative prediction. Steering is in turn intimately related to questions of power in digital markets. The notion of performative power that we review gives an answer to the question how much a platform can steer participants through its predictions. We end on a discussion of future directions, such as the role that performativity plays in contesting algorithmic systems.

cs.LG↗

arXiv2025

Algorithmic Collective Action in Recommender Systems: Promoting Songs by Reordering Playlists

We investigate algorithmic collective action in transformer-based recommender systems. Our use case is a music streaming platform where a collective of fans aims to promote the visibility of an underrepresented artist by strategically placing one of their songs in the existing playlists they control. We introduce two easily implementable strategies to select the position at which to insert the song with the goal to boost recommendations at test time. The strategies exploit statistical properties of the learner by targeting discontinuities in the recommendations, and leveraging the long-tail nature of song distributions. We evaluate the efficacy of our strategies using a publicly available recommender system model released by a major music streaming platform. Our findings reveal that through strategic placement even small collectives (controlling less than 0.01\% of the training data) can achieve up to $40\times$ more test time recommendations than an average song with the same number of training set occurrences. Focusing on the externalities of the strategy, we find that the recommendations of other songs are largely preserved, and the newly gained recommendations are distributed across various artists. Together, our findings demonstrate how carefully designed collective action strategies can be effective while not necessarily being adversarial.

cs.IR↗

arXiv2024

Questioning the Survey Responses of Large Language Models

Surveys have recently gained popularity as a tool to study large language models. By comparing survey responses of models to those of human reference populations, researchers aim to infer the demographics, political opinions, or values best represented by current language models. In this work, we critically examine this methodology on the basis of the well-established American Community Survey by the U.S. Census Bureau. Evaluating 43 different language models using de-facto standard prompting methodologies, we establish two dominant patterns. First, models' responses are governed by ordering and labeling biases, for example, towards survey responses labeled with the letter "A". Second, when adjusting for these systematic biases through randomized answer ordering, models across the board trend towards uniformly random survey responses, irrespective of model size or pre-training data. As a result, in contrast to conjectures from prior work, survey-derived alignment measures often permit a simple explanation: models consistently appear to better represent subgroups whose aggregate statistics are closest to uniform for any survey under consideration.

cs.CL↗

arXiv2024

An engine not a camera: Measuring performative power of online search

The power of digital platforms is at the center of major ongoing policy and regulatory efforts. To advance existing debates, we designed and executed an experiment to measure the performative power of online search providers. Instantiated in our setting, performative power quantifies the ability of a search engine to steer web traffic by rearranging results. To operationalize this definition we developed a browser extension that performs unassuming randomized experiments in the background. These randomized experiments emulate updates to the search algorithm and identify the causal effect of different content arrangements on clicks. Analyzing tens of thousands of clicks, we discuss what our robust quantitative findings say about the power of online search engines, using the Google Shopping antitrust investigation as a case study. More broadly, we envision our work to serve as a blueprint for how the recent definition of performative power can help integrate quantitative insights from online experiments with future investigations into the economic power of digital platforms.

cs.CY↗

arXiv2024

Decline Now: A Combinatorial Model for Algorithmic Collective Action

Drivers on food delivery platforms often run a loss on low-paying orders. In response, workers on DoorDash started a campaign, #DeclineNow, to purposefully decline orders below a certain pay threshold. For each declined order, the platform returns the request to other available drivers with slightly increased pay. While contributing to overall pay increase the implementation of the strategy comes with the risk of missing out on orders for each individual driver. In this work, we propose a first combinatorial model to study the strategic interaction between workers and the platform. Within our model, we formalize key quantities such as the average worker benefit of the strategy, the benefit of freeriding, as well as the benefit of participation. We extend our theoretical results with simulations. Our key insights show that the average worker gain of the strategy is always positive, while the benefit of participation is positive only for small degrees of labor oversupply. Beyond this point, the utility of participants decreases faster with increasing degree of oversupply, compared to the utility of non-participants. Our work highlights the significance of labor supply levels for the effectiveness of collective action on gig platforms. We suggest organizing in shifts as a means to reduce oversupply and empower collectives.

cs.GT↗

arXiv2024

Adjusting Pretrained Backbones for Performativity

With the widespread deployment of deep learning models, they influence their environment in various ways. The induced distribution shifts can lead to unexpected performance degradation in deployed models. Existing methods to anticipate performativity typically incorporate information about the deployed model into the feature vector when predicting future outcomes. While enjoying appealing theoretical properties, modifying the input dimension of the prediction task is often not practical. To address this, we propose a novel technique to adjust pretrained backbones for performativity in a modular way, achieving better sample efficiency and enabling the reuse of existing deep learning assets. Focusing on performative label shift, the key idea is to train a shallow adapter module to perform a Bayes-optimal label shift correction to the backbone's logits given a sufficient statistic of the model to be deployed. As such, our framework decouples the construction of input-specific feature embeddings from the mechanism governing performativity. Motivated by dynamic benchmarking as a use-case, we evaluate our approach under adversarial sampling, for vision and language tasks. We show how it leads to smaller loss along the retraining trajectory and enables us to effectively select among candidate models to anticipate performance degradations. More broadly, our work provides a first baseline for addressing performativity in deep learning.

cs.LG↗

arXiv2024

Evaluating language models as risk scores

Current question-answering benchmarks predominantly focus on accuracy in realizable prediction tasks. Conditioned on a question and answer-key, does the most likely token match the ground truth? Such benchmarks necessarily fail to evaluate LLMs' ability to quantify ground-truth outcome uncertainty. In this work, we focus on the use of LLMs as risk scores for unrealizable prediction tasks. We introduce folktexts, a software package to systematically generate risk scores using LLMs, and evaluate them against US Census data products. A flexible API enables the use of different prompting schemes, local or web-hosted models, and diverse census columns that can be used to compose custom prediction tasks. We evaluate 17 recent LLMs across five proposed benchmark tasks. We find that zero-shot risk scores produced by multiple-choice question-answering have high predictive signal but are widely miscalibrated. Base models consistently overestimate outcome uncertainty, while instruction-tuned models underestimate uncertainty and produce over-confident risk scores. In fact, instruction-tuning polarizes answer distribution regardless of true underlying data uncertainty. This reveals a general inability of instruction-tuned LLMs to express data uncertainty using multiple-choice answers. A separate experiment using verbalized chat-style risk queries yields substantially improved calibration across instruction-tuned models. These differences in ability to quantify data uncertainty cannot be revealed in realizable settings, and highlight a blind-spot in the current evaluation ecosystem that folktexts covers.

cs.LG↗

arXiv2024

Algorithmic Collective Action in Machine Learning

We initiate a principled study of algorithmic collective action on digital platforms that deploy machine learning algorithms. We propose a simple theoretical model of a collective interacting with a firm's learning algorithm. The collective pools the data of participating individuals and executes an algorithmic strategy by instructing participants how to modify their own data to achieve a collective goal. We investigate the consequences of this model in three fundamental learning-theoretic settings: the case of a nonparametric optimal learning algorithm, a parametric risk minimizer, and gradient-based optimization. In each setting, we come up with coordinated algorithmic strategies and characterize natural success criteria as a function of the collective's size. Complementing our theory, we conduct systematic experiments on a skill classification task involving tens of thousands of resumes from a gig platform for freelancers. Through more than two thousand model training runs of a BERT-like language model, we see a striking correspondence emerge between our empirical observations and the predictions made by our theory. Taken together, our theory and experiments broadly support the conclusion that algorithmic collectives of exceedingly small fractional size can exert significant control over a platform's learning algorithm.

cs.LG↗

arXiv2023

Collaborative Learning via Prediction Consensus

We consider a collaborative learning setting where the goal of each agent is to improve their own model by leveraging the expertise of collaborators, in addition to their own training data. To facilitate the exchange of expertise among agents, we propose a distillation-based method leveraging shared unlabeled auxiliary data, which is pseudo-labeled by the collective. Central to our method is a trust weighting scheme that serves to adaptively weigh the influence of each collaborator on the pseudo-labels until a consensus on how to label the auxiliary data is reached. We demonstrate empirically that our collaboration scheme is able to significantly boost the performance of individual models in the target domain from which the auxiliary data is sampled. By design, our method adeptly accommodates heterogeneity in model architectures and substantially reduces communication overhead compared to typical collaborative learning methods. At the same time, it can provably mitigate the negative impact of bad models on the collective.

cs.LG↗

arXiv2023

Causal Inference out of Control: Estimating the Steerability of Consumption

Regulators and academics are increasingly interested in the causal effect that algorithmic actions of a digital platform have on consumption. We introduce a general causal inference problem we call the steerability of consumption that abstracts many settings of interest. Focusing on observational designs and exploiting the structure of the problem, we exhibit a set of assumptions for causal identifiability that significantly weaken the often unrealistic overlap assumptions of standard designs. The key novelty of our approach is to explicitly model the dynamics of consumption over time, viewing the platform as a controller acting on a dynamical system. From this dynamical systems perspective, we are able to show that exogenous variation in consumption and appropriately responsive algorithmic control actions are sufficient for identifying steerability of consumption. Our results illustrate the fruitful interplay of control theory and causal inference, which we illustrate with examples from econometrics, macroeconomics, and machine learning.

cs.LG↗

arXiv2022

Performative Power

We introduce the notion of performative power, which measures the ability of a firm operating an algorithmic system, such as a digital content recommendation platform, to cause change in a population of participants. We relate performative power to the economic study of competition in digital economies. Traditional economic concepts struggle with identifying anti-competitive patterns in digital platforms not least due to the complexity of market definition. In contrast, performative power is a causal notion that is identifiable with minimal knowledge of the market, its internals, participants, products, or prices. Low performative power implies that a firm can do no better than to optimize their objective on current data. In contrast, firms of high performative power stand to benefit from steering the population towards more profitable behavior. We confirm in a simple theoretical model that monopolies maximize performative power. A firm's ability to personalize increases performative power, while competition and outside options decrease performative power. On the empirical side, we propose an observational causal design to identify performative power from discontinuities in how digital platforms display content. This allows to repurpose causal effects from various studies about digital platforms as lower bounds on performative power. Finally, we speculate about the role that performative power might play in competition policy and antitrust enforcement in digital marketplaces.

cs.LG↗

arXiv2022

Anticipating Performativity by Predicting from Predictions

Predictions about people, such as their expected educational achievement or their credit risk, can be performative and shape the outcome that they aim to predict. Understanding the causal effect of these predictions on the eventual outcomes is crucial for foreseeing the implications of future predictive models and selecting which models to deploy. However, this causal estimation task poses unique challenges: model predictions are usually deterministic functions of input features and highly correlated with outcomes. This can make the causal effects of predictions on outcomes impossible to disentangle from the direct effect of the covariates. We study this problem through the lens of causal identifiability, and despite the hardness of this problem in full generality, we highlight three natural scenarios where the causal relationship between covariates, predictions and outcomes can be identified from observational data: randomization in predictions, overparameterization of the predictive model deployed during data collection, and discrete prediction outputs. Empirically we show that given our identifiability conditions hold, standard variants of supervised learning that predict from predictions by treating the prediction as an input feature can indeed find transferable functional relationships that allow for conclusions about newly deployed predictive models. These positive results fundamentally rely on model predictions being recorded during data collection, bringing forward the importance of rethinking standard data collection practices to enable progress towards a better understanding of social outcomes and performative feedback loops.

stat.ML↗

arXiv2022

Regret Minimization with Performative Feedback

In performative prediction, the deployment of a predictive model triggers a shift in the data distribution. As these shifts are typically unknown ahead of time, the learner needs to deploy a model to get feedback about the distribution it induces. We study the problem of finding near-optimal models under performativity while maintaining low regret. On the surface, this problem might seem equivalent to a bandit problem. However, it exhibits a fundamentally richer feedback structure that we refer to as performative feedback: after every deployment, the learner receives samples from the shifted distribution rather than only bandit feedback about the reward. Our main contribution is an algorithm that achieves regret bounds scaling only with the complexity of the distribution shifts and not that of the reward function. The algorithm only relies on smoothness of the shifts and does not assume convexity. Moreover, its final iterate is guaranteed to be near-optimal. The key algorithmic idea is careful exploration of the distribution shifts that informs a novel construction of confidence bounds on the risk of unexplored models. More broadly, our work establishes a conceptual approach for leveraging tools from the bandits literature for the purpose of regret minimization with performative feedback.

cs.LG↗

arXiv2021

Alternative Microfoundations for Strategic Classification

When reasoning about strategic behavior in a machine learning context it is tempting to combine standard microfoundations of rational agents with the statistical decision theory underlying classification. In this work, we argue that a direct combination of these standard ingredients leads to brittle solution concepts of limited descriptive and prescriptive value. First, we show that rational agents with perfect information produce discontinuities in the aggregate response to a decision rule that we often do not observe empirically. Second, when any positive fraction of agents is not perfectly strategic, desirable stable points -- where the classifier is optimal for the data it entails -- cease to exist. Third, optimal decision rules under standard microfoundations maximize a measure of negative externality known as social burden within a broad class of possible assumptions about agent behavior. Recognizing these limitations we explore alternatives to standard microfoundations for binary classification. We start by describing a set of desiderata that help navigate the space of possible assumptions about how agents respond to a decision rule. In particular, we analyze a natural constraint on feature manipulations, and discuss properties that are sufficient to guarantee the robust existence of stable points. Building on these insights, we then propose the noisy response model. Inspired by smoothed analysis and empirical observations, noisy response incorporates imperfection in the agent responses, which we show mitigates the limitations of standard microfoundations. Our model retains analytical tractability, leads to more robust insights about stable points, and imposes a lower social burden at optimality.

cs.LG↗