arXiv subjects

Kiran Tomlinson

Publications and source records attributed to Kiran Tomlinson.

15 recordsLinked to original sources

arXiv2026

Adopt $\neq$ Adapt: Longitudinal Analyses of LLM Conversations in the Wild

Although a growing body of research has begun to describe user--LLM interactions, the picture it paints is largely static; little is known about how individual users change their behavior over time. To address this gap, we analyze the conversational trajectories of ~12,000 randomly sampled Microsoft Bing Copilot users and compare these with data from WildChat-4.8M. While the Copilot data contains significant population-level trends, we find that trends in individual user trajectories are much weaker; user habits prove to be overwhelmingly sticky. We also find stark differences between users of different activity levels: more active users have more successful conversations and use the LLM for more complex and professionally oriented tasks. Some user trends also appear in WildChat-4.8M, but we find evidence that this dataset is significantly skewed towards highly proficient "power" users. Ultimately, our results suggest that existing user behavior is difficult to change and demonstrate the extent of user heterogeneity. Our comparison between datasets highlights that WildChat does not represent typical user--AI interactions, an important caveat for downstream uses of the data.

cs.AI↗

arXiv2026

Reasoning about Reasoning: BAPO Bounds on Chain-of-Thought Token Complexity in LLMs

Inference-time scaling via chain-of-thought (CoT) reasoning is a major driver of state-of-the-art LLM performance, but it comes with substantial latency and compute costs. We address a fundamental theoretical question: how many reasoning tokens are required to solve a problem as input size grows? By extending the bounded attention prefix oracle (BAPO) model--an abstraction of LLMs that quantifies the information flow required to solve a task--we prove lower bounds on the CoT tokens required for three canonical BAPO-hard tasks: binary majority, triplet matching, and graph reachability. We show that each requires $Ω(n)$ reasoning tokens when the input size is $n$. We complement these results with matching or near-matching upper bounds via explicit constructions. Finally, our experiments with frontier reasoning models show approximately linear reasoning token scaling on these tasks and failures when constrained to smaller reasoning budgets, consistent with our theoretical lower bounds. Together, our results identify fundamental bottlenecks in inference-time compute through CoT and offer a principled tool for analyzing optimal reasoning length.

cs.AI↗

arXiv2026

AI in the Enterprise: How People Use M365 Copilot Chat

M365 Copilot is used every week by millions of people across more than a million companies around the world as part of their workflows. Uniquely positioned in the AI landscape given its near-exclusive use for work purposes, M365 Copilot can offer a clear picture of how people use AI for work and where that usage may expand next. This paper characterizes that usage through direct classification of user interactions with M365 Copilot Chat. Based on an anonymized and privacy-preserving analysis of a sample of approximately 5.5 million sessions, we combine a learned classification of user intent with a classification of O*NET work activities done with M365 Copilot Chat. We find that M365 Copilot is emerging as an everyday assistant for knowledge work: writing dominates, but users also rely on it for information retrieval, analysis, decision making and strategizing, and evaluating and diagnosing programs and systems, among others. Information seeking tasks remain common, but time trends suggest a relative shift away from ``chat as search'' and toward content and communication-related work. Comparisons across occupational groupings and to work done in the labor market further show that usage is broad but uneven, where the relative share of work done with M365 Copilot Chat cuts across jobs in some cases and is occupation-specific in others. Areas of relative underrepresentation in the labor market suggest the next frontier for enterprise AI adoption.

cs.CY↗

arXiv2026

Lost in Transmission: When and Why LLMs Fail to Reason Globally

Despite their many successes, transformer-based large language models (LLMs) continue to struggle with tasks that require complex reasoning over large parts of their input. We argue that these failures arise due to capacity limits on the accurate flow of information within LLMs. To formalize this issue, we introduce the bounded attention prefix oracle (BAPO) model, a new computational framework that models bandwidth constraints on attention heads, the mechanism for internal communication in LLMs. We show that several important reasoning problems like graph reachability require high communication bandwidth for BAPOs to solve; we call these problems BAPO-hard. Our experiments corroborate our theoretical predictions: GPT-4o, Claude, and Gemini succeed on BAPO-easy tasks and fail even on relatively small BAPO-hard tasks. BAPOs also reveal another benefit of chain of thought (CoT): we prove that breaking down a task using CoT can turn any BAPO-hard problem into a BAPO-easy one. Our results offer principled explanations for key LLM failures and suggest directions for architectures and inference methods that mitigate bandwidth limits.

cs.AI↗

arXiv2025

Working with AI: Measuring the Applicability of Generative AI to Occupations

With generative AI emerging as a general-purpose technology, understanding its economic effects is among society's most pressing questions. Existing studies of AI impact have largely relied on predictions of AI capabilities or focused narrowly on individual firms. Drawing instead on real-world AI usage, we analyze a dataset of 200k anonymized conversations with Microsoft Bing Copilot to measure AI applicability to occupations. We use an LLM-based pipeline to classify the O*NET work activities assisted or performed by AI in each conversation. We find that the most common and successful AI-assisted work activities involve information work--the creation, processing, and communication of information. At the occupation level, we find widespread AI applicability cutting across sectors, as most occupations have information work components. Our methodology also allows us to predict which occupations are more likely to delegate tasks to AI and which are more likely to use AI to assist existing workflows.

cs.AI↗

arXiv2025

When the Universe is Too Big: Bounding Consideration Probabilities for Plackett-Luce Rankings

The widely used Plackett-Luce ranking model assumes that individuals rank items by making repeated choices from a universe of items. But in many cases the universe is too big for people to plausibly consider all options. In the choice literature, this issue has been addressed by supposing that individuals first sample a small consideration set and then choose among the considered items. However, inferring unobserved consideration sets (or item consideration probabilities) in this "consider then choose" setting poses significant challenges, because even simple models of consideration with strong independence assumptions are not identifiable, even if item utilities are known. We apply the consider-then-choose framework to top-$k$ rankings, where we assume rankings are constructed according to a Plackett-Luce model after sampling a consideration set. While item consideration probabilities remain non-identified in this setting, we prove that we can infer bounds on the relative values of consideration probabilities. Additionally, given a condition on the expected consideration set size and known item utilities, we derive absolute upper and lower bounds on item consideration probabilities. We also provide algorithms to tighten those bounds on consideration probabilities by propagating inferred constraints. Thus, we show that we can learn useful information about consideration probabilities despite not being able to identify them precisely. We demonstrate our methods on a ranking dataset from a psychology experiment with two different ranking tasks (one with fixed consideration sets and one with unknown consideration sets). This combination of data allows us to estimate utilities and then learn about unknown consideration probabilities using our bounds.

cs.LG↗

arXiv2025

Exclusion Zones of Instant Runoff Voting

Recent research on instant runoff voting (IRV) shows that it exhibits a striking combinatorial property in one-dimensional preference spaces: there is an "exclusion zone" around the median voter such that if a candidate from the exclusion zone is on the ballot, then the winner must come from the exclusion zone. Thus, in one dimension, IRV cannot elect an extreme candidate as long as a sufficiently moderate candidate is running. In this work, we examine the mathematical structure of exclusion zones as a broad phenomenon in more general preference spaces. We prove that with voters uniformly distributed over any $d$-dimensional hyperrectangle (for $d > 1$), IRV has no nontrivial exclusion zone. However, we also show that IRV exclusion zones are not solely a one-dimensional phenomenon. For irregular higher-dimensional preference spaces with fewer symmetries than hyperrectangles, IRV can exhibit nontrivial exclusion zones. As a further exploration, we study IRV exclusion zones in graph voting, where nodes represent voters who prefer candidates closer to them in the graph. Here, we show that IRV exclusion zones present a surprising computational challenge: even checking whether a given set of positions is an IRV exclusion zone is NP-hard. We develop an efficient randomized approximation algorithm for checking and finding exclusion zones. We also report on computational experiments with exclusion zones in two directions: (i) applying our approximation algorithm to a collection of real-world school friendship networks, we find that about 60% of these networks have probable nontrivial IRV exclusion zones; and (ii) performing an exhaustive computer search of small graphs and trees, we also find nontrivial IRV exclusion zones in most graphs. While our focus is on IRV, the properties of exclusion zones we establish provide a novel method for analyzing voting systems in metric spaces more generally.

cs.MA↗

arXiv2025

Replicating Electoral Success

A core tension in the study of plurality elections is the clash between the classic Hotelling-Downs model, which predicts that two office-seeking candidates should position themselves at the median voter's policy, and the empirical observation that real-world democracies often have two major parties with divergent policies. Motivated by this tension and drawing from bounded rationality, we introduce a dynamic model of candidate positioning based on a simple behavioral heuristic: candidates imitate the policy of previous winners. The resulting model is closely connected to evolutionary replicator dynamics and exhibits complex behavior, despite its simplicity. For uniformly-distributed voters, we prove that when there are $k = 2$, $3$, or $4$ candidates per election, any symmetric candidate distribution converges over time to a concentration of candidates at the center. With $k \ge 5$, however, we prove that the candidate distribution does not converge to the center. For initial distributions without any extreme candidates, we prove a stronger statement than non-convergence, showing that the density in an interval around the center goes to zero when $k \ge 5$. As a matter of robustness, our conclusions are qualitatively unchanged if a small fraction of candidates are not winner-copiers and are instead positioned uniformly at random. Beyond our theoretical analysis, we illustrate our results in simulation; for five or more candidates, we find a tendency towards the emergence of two clusters, a mechanism suggestive of Duverger's Law, the empirical finding that plurality leads to two-party systems. Our simulations also explore several variations of the model, including non-uniform voter distributions and other forms of noise, which exhibit similar convergence patterns. Finally, we discuss the relationship between our model and prior work on strategic equilibria of candidate positioning games.

cs.GT↗

arXiv2024

The Moderating Effect of Instant Runoff Voting

Instant runoff voting (IRV) has recently gained popularity as an alternative to plurality voting for political elections, with advocates claiming a range of advantages, including that it produces more moderate winners than plurality and could thus help address polarization. However, there is little theoretical backing for this claim, with existing evidence focused on case studies and simulations. In this work, we prove that IRV has a moderating effect relative to plurality voting in a precise sense, developed in a 1-dimensional Euclidean model of voter preferences. We develop a theory of exclusion zones, derived from properties of the voter distribution, which serve to show how moderate and extreme candidates interact during IRV vote tabulation. The theory allows us to prove that if voters are symmetrically distributed and not too concentrated at the extremes, IRV cannot elect an extreme candidate over a moderate. In contrast, we show plurality can and validate our results computationally. Our methods provide new frameworks for the analysis of voting systems, deriving exact winner distributions geometrically and establishing a connection between plurality voting and stick-breaking processes.

cs.MA↗

arXiv2023

Graph-Based Methods for Discrete Choice

Choices made by individuals have widespread impacts--for instance, people choose between political candidates to vote for, between social media posts to share, and between brands to purchase--moreover, data on these choices are increasingly abundant. Discrete choice models are a key tool for learning individual preferences from such data. Additionally, social factors like conformity and contagion influence individual choice. Traditional methods for incorporating these factors into choice models do not account for the entire social network and require hand-crafted features. To overcome these limitations, we use graph learning to study choice in networked contexts. We identify three ways in which graph learning techniques can be used for discrete choice: learning chooser representations, regularizing choice model parameters, and directly constructing predictions from a network. We design methods in each category and test them on real-world choice datasets, including county-level 2016 US election results and Android app installation and usage data. We show that incorporating social network structure can improve the predictions of the standard econometric choice model, the multinomial logit. We provide evidence that app installations are influenced by social context, but we find no such effect on app usage among the same participants, which instead is habit-driven. In the election data, we highlight the additional insights a discrete choice framework provides over classification or regression, the typical approaches. On synthetic data, we demonstrate the sample complexity benefit of using social information in choice models.

cs.LG↗

arXiv2022

Ballot Length in Instant Runoff Voting

Instant runoff voting (IRV) is an increasingly-popular alternative to traditional plurality voting in which voters submit rankings over the candidates rather than single votes. In practice, elections using IRV often restrict the ballot length, the number of candidates a voter is allowed to rank on their ballot. We theoretically and empirically analyze how ballot length can influence the outcome of an election, given fixed voter preferences. We show that there exist preference profiles over $k$ candidates such that up to $k-1$ different candidates win at different ballot lengths. We derive exact lower bounds on the number of voters required for such profiles and provide a construction matching the lower bound for unrestricted voter preferences. Additionally, we characterize which sequences of winners are possible over ballot lengths and provide explicit profile constructions achieving any feasible winner sequence. We also examine how classic preference restrictions influence our results--for instance, single-peakedness makes $k-1$ different winners impossible but still allows at least $Ω(\sqrt k)$. Finally, we analyze a collection of 168 real-world elections, where we truncate rankings to simulate shorter ballots. We find that shorter ballots could have changed the outcome in one quarter of these elections. Our results highlight ballot length as a consequential degree of freedom in the design of IRV elections.

cs.MA↗

arXiv2021

Choice Set Confounding in Discrete Choice

Standard methods in preference learning involve estimating the parameters of discrete choice models from data of selections (choices) made by individuals from a discrete set of alternatives (the choice set). While there are many models for individual preferences, existing learning methods overlook how choice set assignment affects the data. Often, the choice set itself is influenced by an individual's preferences; for instance, a consumer choosing a product from an online retailer is often presented with options from a recommender system that depend on information about the consumer's preferences. Ignoring these assignment mechanisms can mislead choice models into making biased estimates of preferences, a phenomenon that we call choice set confounding; we demonstrate the presence of such confounding in widely-used choice datasets. To address this issue, we adapt methods from causal inference to the discrete choice setting. We use covariates of the chooser for inverse probability weighting and/or regression controls, accurately recovering individual preferences in the presence of choice set confounding under certain assumptions. When such covariates are unavailable or inadequate, we develop methods that take advantage of structured choice set assignment to improve prediction. We demonstrate the effectiveness of our methods on real-world choice data, showing, for example, that accounting for choice set confounding makes choices observed in hotel booking and commute transportation more consistent with rational utility-maximization.

cs.LG↗

arXiv2020

Learning Interpretable Feature Context Effects in Discrete Choice

The outcomes of elections, product sales, and the structure of social connections are all determined by the choices individuals make when presented with a set of options, so understanding the factors that contribute to choice is crucial. Of particular interest are context effects, which occur when the set of available options influences a chooser's relative preferences, as they violate traditional rationality assumptions yet are widespread in practice. However, identifying these effects from observed choices is challenging, often requiring foreknowledge of the effect to be measured. In contrast, we provide a method for the automatic discovery of a broad class of context effects from observed choice data. Our models are easier to train and more flexible than existing models and also yield intuitive, interpretable, and statistically testable context effects. Using our models, we identify new context effects in widely used choice datasets and provide the first analysis of choice set context effects in social network growth.

cs.LG↗

arXiv2020

Choice Set Optimization Under Discrete Choice Models of Group Decisions

The way that people make choices or exhibit preferences can be strongly affected by the set of available alternatives, often called the choice set. Furthermore, there are usually heterogeneous preferences, either at an individual level within small groups or within sub-populations of large groups. Given the availability of choice data, there are now many models that capture this behavior in order to make effective predictions--however, there is little work in understanding how directly changing the choice set can be used to influence the preferences of a collection of decision-makers. Here, we use discrete choice modeling to develop an optimization framework of such interventions for several problems of group influence, namely maximizing agreement or disagreement and promoting a particular choice. We show that these problems are NP-hard in general, but imposing restrictions reveals a fundamental boundary: promoting a choice can be easier than encouraging consensus or sowing discord. We design approximation algorithms for the hard problems and show that they work well on real-world choice data.

cs.GT↗

arXiv2020

Summarizing Diverging String Sequences, with Applications to Chain-Letter Petitions

Algorithms to find optimal alignments among strings, or to find a parsimonious summary of a collection of strings, are well studied in a variety of contexts, addressing a wide range of interesting applications. In this paper, we consider chain letters, which contain a growing sequence of signatories added as the letter propagates. The unusual constellation of features exhibited by chain letters (one-ended growth, divergence, and mutation) make their propagation, and thus the corresponding reconstruction problem, both distinctive and rich. Here, inspired by these chain letters, we formally define the problem of computing an optimal summary of a set of diverging string sequences. From a collection of these sequences of names, with each sequence noisily corresponding to a branch of the unknown tree $T$ representing the letter's true dissemination, can we efficiently and accurately reconstruct a tree $T' \approx T$? In this paper, we give efficient exact algorithms for this summarization problem when the number of sequences is small; for larger sets of sequences, we prove hardness and provide an efficient heuristic algorithm. We evaluate this heuristic on synthetic data sets chosen to emulate real chain letters, showing that our algorithm is competitive with or better than previous approaches, and that it also comes close to finding the true trees in these synthetic datasets.

cs.SI↗