arXiv subjects

Manish Raghavan

Publications and source records attributed to Manish Raghavan.

At least 19 recordsLinked to original sources

arXiv2026

Hitting a Moving Target: Test-Time Adaptation for AI Text Detection under Continual Distribution Shift

Deployed approaches for AI text detection often rely on training-time access to labeled datasets of both human-written and AI-generated text. This approach is vulnerable to three types of distribution shifts that occur continually post-deployment, and for which labeled data is often unavailable: adversarial humanization, new LLMs being released, and temporal drift in human writing. Simultaneously, existing approaches do not leverage a key signal of LLM usage: inference-time homogeneity. We propose a test-time adaptation (TTA) approach, using semi-supervised learning, that adapts to distribution shifts by leveraging homogeneity among unlabeled samples observed at inference time. Empirically, we find that state-of-the-art supervised detectors systematically fail when they encounter distribution shifts in AI-generated and human writing, both adversarial and natural, while test-time adaptation with semi-supervised learning is largely robust; e.g., the commercial model Pangram detects just 24.1% of our adversarial AI-generated text, compared to 90.5% for our test-time approach. We establish that test-time adaptation is a promising framework for AI text detection in the wild. We publicly release our code (which includes code for model training, evaluation, and plots) at https://github.com/kkr36/llm_detection.

cs.CL↗

arXiv2026

When to Ask a Question: Understanding Communication Strategies in Generative AI Tools

Generative AI models differ from traditional machine learning tools in that they allow users to provide as much or as little information as they choose in their inputs. This flexibility often leads users to omit certain details, relying on the models to infer and fill in under-specified information based on distributional knowledge of user preferences. Such inferences may privilege majority viewpoints and disadvantage users with atypical preferences, raising concerns about fairness. Unlike more traditional recommender systems, LLMs can explicitly solicit more information from users through natural language. However, while directly eliciting user preferences could increase personalization and mitigate inequality, excessive querying places a burden on users who value efficiency. We develop a stylized model of user-LLM interaction and develop an objective that captures tradeoff between user burden and preference representation. Building on the observation that individual preferences are often correlated, we analyze how AI systems should balance inference and elicitation, characterizing the optimal amount of information to solicit before content generation. Ultimately, we show that information elicitation can mitigate the systematic biases of preference inference, enabling the design of generative tools that better incorporate diverse user perspectives while maintaining efficiency. We complement this theoretical analysis with an empirical evaluation illustrating the model's predictions and exploring their practical implications.

cs.GT↗

arXiv2026

Algorithmic Monoculture and its Critics

Algorithmic decision-making is replacing idiosyncratic human judgment in domains such as hiring, lending, and criminal justice. This shift promises increased consistency, but many scholars worry that it can go too far. They warn of the dangers of algorithmic monoculture, in which all decisions across a domain are made using a single algorithm. We systematically evaluate a range of objections to monoculture, formalizing and rigorously assessing familiar critiques alongside novel ones. These objections concern systemic exclusion, agency and gaming, and information aggregation and exploration. We conclude that monoculture is less problematic than its critics have supposed: commonly cited objections fail, and while other objections have some force, they are not decisive against monoculture in general.

cs.CY↗

arXiv2026

Incentives shape how humans co-create with generative AI

Generative AI is quickly becoming an integral part of people's everyday workflows. Early evidence has shown that while generative AI can increase individual-level productivity, it does so at the cost of collective diversity, potentially narrowing the set of ideas and perspectives produced. Our research stands in contrast to this concern: through a pre-registered randomized control trial, we show that incentives mediate AI's homogenizing force in a creative writing task where participants can use AI interactively. Participants rewarded for originality relative to peers produce collectively more diverse writing than those rewarded for quality alone. This divergence is driven not by abandoning AI, but by how participants use it: those incentivized for originality incorporate fewer AI suggestions verbatim, relying on the model more selectively for brainstorming, proofreading, and targeted edits. Our results reveal that the effects of generative AI depend not only on the technology itself, but also the behavioral strategies and incentive structures surrounding its use.

cs.HC↗

arXiv2026

Strategic Candidacy in Generative AI Arenas

AI arenas, which rank generative models from pairwise preferences of users, are a popular method for measuring the relative performance of models in the course of their organic use. Because rankings are computed from noisy preferences, there is a concern that model producers can exploit this randomness by submitting many models (e.g., multiple variants of essentially the same model) and thereby artificially improve the rank of their top models. This can lead to degradations in the quality, and therefore the usefulness, of the ranking. In this paper, we begin by establishing, both theoretically and in simulations calibrated to data from the platform Arena (formerly LMArena, Chatbot Arena), conditions under which producers can benefit from submitting clones when their goal is to be ranked highly. We then propose a new mechanism for ranking models from pairwise comparisons, called You-Rank-We-Rank (YRWR). It requires that producers submit rankings over their own models and uses these rankings to correct statistical estimates of model quality. We prove that this mechanism is approximately clone-robust, in the sense that a producer cannot improve their rank much by doing anything other than submitting each of their unique models exactly once. Moreover, to the extent that model producers are able to correctly rank their own models, YRWR improves overall ranking accuracy. In further simulations, we show that indeed the mechanism is approximately clone-robust and quantify improvements to ranking accuracy, even under producer misranking.

cs.LG↗

arXiv2026

The Subjectivity of Monoculture

Machine learning models -- including large language models (LLMs) -- are often said to exhibit monoculture, where outputs agree strikingly often. But what does it actually mean for models to agree too much? We argue that this question is inherently subjective, relying on two key decisions. First, the analyst must specify a baseline null model for what "independence" should look like. This choice is inherently subjective, and as we show, different null models result in dramatically different inferences about excess agreement. Second, we show that inferences depend on the population of models and items under consideration. Models that seem highly correlated in one context may appear independent when evaluated on a different set of questions, or against a different set of peers. Experiments on two large-scale benchmarks validate our theoretical findings. For example, we find drastically different inferences when using a null model with item difficulty compared to previous works that do not. Together, our results reframe monoculture evaluation not as an absolute property of model behavior, but as a context-dependent inference problem.

cs.CY↗

arXiv2026

Impacts of Aggregation on Model Diversity and Consumer Utility

Consider a marketplace of AI tools, each with slightly different strengths and weaknesses. By picking the right model for the task at hand, a user can do better than simply using the same model for everything. Routers operate under a similar principle, where sophisticated model selection can increase overall performance. However, aggregation is often noisy, reflecting imperfect user choices or routing decisions. This leads to two main questions: first, what does a "healthy marketplace" of models look like for maximizing consumer utility? Secondly, how can we incentivize producers to create such models? We show that winrate, a standard benchmark in LLM evaluation, can incentivize model creators to homogenize for both types of model changes, reducing consumer welfare. We propose a new mechanism, weighted winrate, which rewards models for answers that are higher quality, and show that it provably improves incentives for producers to specialize and increases consumer welfare. We conclude by exploring the impact of our theoretical results in empirical benchmark datasets and discussing implications for benchmark design.

cs.GT↗

arXiv2025

Statistical Guarantees in the Search for Less Discriminatory Algorithms

U.S. discrimination law can impose liability on firms that fail to adopt a less discriminatory alternative (LDA): a decision policy that achieves the same business objectives while reducing disparate impact on legally protected groups. Recent scholarship argues that this doctrine has direct implications for algorithmic decision-making in high-stakes domains such as employment, lending, and housing, potentially obligating firms to search for "less discriminatory algorithms" (Black et al., 2024). Regulators have at times encouraged proactive LDA searches, reinforcing the expectation of a good-faith effort to identify equally performant models with lower disparate impact. Model multiplicity makes such searches plausible: retraining with different random seeds can yield models with comparable predictive performance but materially different disparate impacts. Yet firms cannot retrain indefinitely, raising a central question: when is the search sufficient to demonstrate good faith? We formalize LDA search under multiplicity as an optimal stopping problem in which a developer seeks to produce evidence that further search is unlikely to yield meaningful improvements. Our main contribution is an adaptive stopping algorithm that provides a high-probability upper bound on the best disparate-impact gains attainable through continued retraining, enabling developers to certify (e.g., to a court) that additional search is unlikely to help. We also show how stronger distributional assumptions over the model space can yield tighter bounds, and we validate the approach on real-world credit and housing datasets.

cs.CY↗

arXiv2025

The Impossibility of Inverse Permutation Learning in Transformer Models

In this technical note, we study the problem of inverse permutation learning in decoder-only transformers. Given a permutation and a string to which that permutation has been applied, the model is tasked with producing the original (``canonical'') string. We argue that this task models a natural robustness property across a variety of reasoning tasks, including long-context retrieval, multiple choice QA and in-context learning. Our primary contribution is an impossibility result: we show that an arbitrary depth, decoder-only transformer cannot learn this task. This result concerns the expressive capacity of decoder-only transformer models and is agnostic to training dynamics or sample complexity. We give a pair of alternative constructions under which inverse permutation learning is feasible. The first of these highlights the fundamental role of the causal attention mask, and reveals a gap between the expressivity of encoder-decoder transformers and the more popular decoder-only architecture. The latter result is more surprising: we show that simply padding the input with ``scratch tokens" yields a construction under which inverse permutation learning is possible. We conjecture that this may suggest an alternative mechanism by which chain-of-thought prompting or, more generally, intermediate ``thinking'' tokens can enable reasoning in large language models, even when these tokens encode no meaningful semantic information (e.g., the results of intermediate computations).

cs.LG↗

arXiv2025

Double Machine Learning for Causal Inference under Shared-State Interference

Researchers and practitioners often wish to measure treatment effects in settings where units interact via markets and recommendation systems. In these settings, units are affected by certain shared states, like prices, algorithmic recommendations or social signals. We formalize this structure, calling it shared-state interference, and argue that our formulation captures many relevant applied settings. Our key modeling assumption is that individuals' potential outcomes are independent conditional on the shared state. We then prove an extension of a double machine learning (DML) theorem providing conditions for achieving efficient inference under shared-state interference. We also instantiate our general theorem in several models of interest where it is possible to efficiently estimate the average direct effect (ADE) or global average treatment effect (GATE).

stat.ML↗

arXiv2025

Homogeneous Algorithms Can Reduce Competition in Personalized Pricing

Firms' algorithm development practices are often homogeneous. Whether firms train algorithms on similar data, aim at similar benchmarks, or rely on similar pre-trained models, the result is correlated predictions. We model the impact of correlated algorithms on competition in the context of personalized pricing. Our analysis reveals that (1) higher correlation diminishes consumer welfare and (2) as consumers become more price sensitive, firms are increasingly incentivized to compromise on the accuracy of their predictions in exchange for coordination. We demonstrate our theoretical results in a stylized empirical study where two firms compete using personalized pricing algorithms. Our results underscore the ease with which algorithms facilitate price correlation without overt communication, which raises concerns about a new frontier of anti-competitive behavior. We analyze the implications of our results on the application and interpretation of US antitrust law.

cs.GT↗

arXiv2025

Evaluating the Impacts of Swapping on the US Decennial Census

To meet its dual burdens of providing useful statistics and ensuring privacy of individual respondents, the US Census Bureau has for decades introduced some form of "noise" into published statistics. Initially, they used a method known as "swapping" (1990-2010). In 2020, they switched to an algorithm called TopDown that ensures a form of Differential Privacy. While the TopDown algorithm has been made public, no implementation of swapping has been released and many details of the deployed swapping methodology deployed have been kept secret. Further, the Bureau has not published (even a synthetic) "original" dataset and its swapped version. It is therefore difficult to evaluate the effects of swapping, and to compare these effects to those of other privacy technologies. To address these difficulties we describe and implement a parameterized swapping algorithm based on Census publications, court documents, and informal interviews with Census employees. With this implementation, we characterize the impacts of swapping on a range of statistical quantities of interest. We provide intuition for the types of shifts induced by swapping and compare against those introduced by TopDown. We find that even when swapping and TopDown introduce errors of similar magnitude, the direction in which statistics are biased need not be the same across the two techniques. More broadly, our implementation provides researchers with the tools to analyze and potentially correct for the impacts of disclosure avoidance systems on the quantities they study.

cs.CY↗

arXiv2025

Evaluating multiple models using labeled and unlabeled data

It remains difficult to evaluate machine learning classifiers in the absence of a large, labeled dataset. While labeled data can be prohibitively expensive or impossible to obtain, unlabeled data is plentiful. Here, we introduce Semi-Supervised Model Evaluation (SSME), a method that uses both labeled and unlabeled data to evaluate machine learning classifiers. SSME is the first evaluation method to take advantage of the fact that: (i) there are frequently multiple classifiers for the same task, (ii) continuous classifier scores are often available for all classes, and (iii) unlabeled data is often far more plentiful than labeled data. The key idea is to use a semi-supervised mixture model to estimate the joint distribution of ground truth labels and classifier predictions. We can then use this model to estimate any metric that is a function of classifier scores and ground truth labels (e.g., accuracy or expected calibration error). We present experiments in four domains where obtaining large labeled datasets is often impractical: (1) healthcare, (2) content moderation, (3) molecular property prediction, and (4) image annotation. Our results demonstrate that SSME estimates performance more accurately than do competing methods, reducing error by 5.1x relative to using labeled data alone and 2.4x relative to the next best competing method. SSME also improves accuracy when evaluating performance across subsets of the test distribution (e.g., specific demographic subgroups) and when evaluating the performance of language models.

cs.LG↗

arXiv2024

What Constitutes a Less Discriminatory Algorithm?

Disparate impact doctrine offers an important legal apparatus for targeting discriminatory data-driven algorithmic decisions. A recent body of work has focused on conceptualizing one particular construct from this doctrine: the less discriminatory alternative, an alternative policy that reduces disparities while meeting the same business needs of a status quo or baseline policy. However, attempts to operationalize this construct in the algorithmic setting must grapple with some thorny challenges and ambiguities. In this paper, we attempt to raise and resolve important questions about less discriminatory algorithms (LDAs). How should we formally define LDAs, and how does this interact with different societal goals they might serve? And how feasible is it for firms or plaintiffs to computationally search for candidate LDAs? We find that formal LDA definitions face fundamental challenges when they attempt to evaluate and compare predictive models in the absence of held-out data. As a result, we argue that LDA definitions cannot be purely quantitative, and must rely on standards of "reasonableness." We then identify both mathematical and computational constraints on firms' ability to efficiently conduct a proactive search for LDAs, but we provide evidence that these limits are "weak" in a formal sense. By defining LDAs formally, we put forward a framework in which both firms and plaintiffs can search for alternative models that comport with societal goals.

cs.CY↗

arXiv2024

Competition and Diversity in Generative AI

Recent evidence, both in the lab and in the wild, suggests that the use of generative artificial intelligence reduces the diversity of content produced. The use of the same or similar AI models appears to lead to more homogeneous behavior. Our work begins with the observation that there is a force pushing in the opposite direction: competition. When producers compete with one another (e.g., for customers or attention), they are incentivized to create novel or unique content. We explore the impact competition has on both content diversity and overall social welfare. Through a formal game-theoretic model, we show that competitive markets select for diverse AI models, mitigating monoculture. We further show that a generative AI model that performs well in isolation (i.e., according to a benchmark) may fail to provide value in a competitive market. Our results highlight the importance of evaluating generative AI models across the breadth of their output distributions, particularly when they will be deployed in competitive environments. We validate our results empirically by using language models to play Scattergories, a word game in which players are rewarded for answers that are both correct and unique. Overall, our results suggest that homogenization due to generative AI is unlikely to persist in competitive markets, and instead, competition in downstream markets may drive diversification in AI model development.

cs.GT↗

arXiv2024

Integrating Expert Judgment and Algorithmic Decision Making: An Indistinguishability Framework

We introduce a novel framework for human-AI collaboration in prediction and decision tasks. Our approach leverages human judgment to distinguish inputs which are algorithmically indistinguishable, or "look the same" to any feasible predictive algorithm. We argue that this framing clarifies the problem of human-AI collaboration in prediction and decision tasks, as experts often form judgments by drawing on information which is not encoded in an algorithm's training data. Algorithmic indistinguishability yields a natural test for assessing whether experts incorporate this kind of "side information", and further provides a simple but principled method for selectively incorporating human feedback into algorithmic predictions. We show that this method provably improves the performance of any feasible algorithmic predictor and precisely quantify this improvement. We demonstrate the utility of our framework in a case study of emergency room triage decisions, where we find that although algorithmic risk scores are highly competitive with physicians, there is strong evidence that physician judgments provide signal which could not be replicated by any predictive algorithm. This insight yields a range of natural decision rules which leverage the complementary strengths of human experts and predictive algorithms.

cs.LG↗

arXiv2024

Unstable Unlearning: The Hidden Risk of Concept Resurgence in Diffusion Models

Text-to-image diffusion models rely on massive, web-scale datasets. Training them from scratch is computationally expensive, and as a result, developers often prefer to make incremental updates to existing models. These updates often compose fine-tuning steps (to learn new concepts or improve model performance) with "unlearning" steps (to "forget" existing concepts, such as copyrighted works or explicit content). In this work, we demonstrate a critical and previously unknown vulnerability that arises in this paradigm: even under benign, non-adversarial conditions, fine-tuning a text-to-image diffusion model on seemingly unrelated images can cause it to "relearn" concepts that were previously "unlearned." We comprehensively investigate the causes and scope of this phenomenon, which we term concept resurgence, by performing a series of experiments which compose "concept unlearning" with subsequent fine-tuning of Stable Diffusion v1.4 and Stable Diffusion v2.1. Our findings underscore the fragility of composing incremental model updates, and raise serious new concerns about current approaches to ensuring the safety and alignment of text-to-image diffusion models.

cs.LG↗

arXiv2024

Synthetic Census Data Generation via Multidimensional Multiset Sum

The US Decennial Census provides valuable data for both research and policy purposes. Census data are subject to a variety of disclosure avoidance techniques prior to release in order to preserve respondent confidentiality. While many are interested in studying the impacts of disclosure avoidance methods on downstream analyses, particularly with the introduction of differential privacy in the 2020 Decennial Census, these efforts are limited by a critical lack of data: The underlying "microdata," which serve as necessary input to disclosure avoidance methods, are kept confidential. In this work, we aim to address this limitation by providing tools to generate synthetic microdata solely from published Census statistics, which can then be used as input to any number of disclosure avoidance algorithms for the sake of evaluation and carrying out comparisons. We define a principled distribution over microdata given published Census statistics and design algorithms to sample from this distribution. We formulate synthetic data generation in this context as a knapsack-style combinatorial optimization problem and develop novel algorithms for this setting. While the problem we study is provably hard, we show empirically that our methods work well in practice, and we offer theoretical arguments to explain our performance. Finally, we verify that the data we produce are "close" to the desired ground truth.

cs.CY↗