Demian Inostroza, Ekaterina Vylomova, Charles Kemp, Mae Carroll, Wanchun Li, Meladel Mistica. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2026.

Abstract Human translators linger on some words and phrases more than others, and predicting this variation is a step towards explaining the underlying cognitive processes. Using data from the CRITT Translation Process Research Database, we evaluate the extent to which surprisal and attentional features derived from a Neural Machine Translation (NMT) model account for reading and production times of human translators. We find that surprisal and attention are complementary predictors of translation difficulty, and that surprisal derived from a NMT model is the single most successful predictor of production duration. Our analyses draw on data from hundreds of translators operating across 13 language pairs, and represent the most comprehensive investigation of human translation difficulty to date.

Psychologists have recently begun to develop computational accounts of how people infer others' preferences from their behavior. The inverse decision-making approach proposes that people infer preferences by inverting a generative model of decision-making. Existing data sets, however, do not provide sufficient resolution to thoroughly evaluate this approach. We introduce a new preference learning task that provides a benchmark for evaluating computational accounts and use it to compare the inverse decision-making approach to a feature-based approach, which relies on a discriminative combination of decision features. Our data support the inverse decision-making approach to preference learning. A basic principle of decision-making is that knowing people's preferences allows us to predict how they will behave: if you know your friend likes comedies and hates horror films, you can probably guess which of these options she will choose when she goes to the theater. Often, however, we do not know what other people like and we can only infer their preferences from their behavior. If you know that a different friend saw a comedy today, does that mean that he likes comedies in general? The conclusion you draw will likely depend on what else was playing and what movie choices he has made in the past. A goal for social cognition research is to develop a computational account of people's ability to infer others' preferences. One computational approach is based on inverse decision-making. This approach begins with a model of how someone's preferences lead to a decision. Then, this model is inverted to determine the most likely preferences that motivated an observed decision. An alternative approach might simply learn a functional mapping between features of an observed decision and the preferences that motivated it. For instance, in your friend's decision to see a comedy, perhaps the more movie options he turned down, the more likely it is that he has a true preference for comedies. The difference between the inverse decision-making approach and the feature-based approach maps onto the standard dichotomy between generative and discriminative models. Economists have developed an instance of the inverse decision-making approach known as the multinomial logit model [1] that has been widely used to infer consumer's preferences from their choices. This model has recently been explored as a psychological model [2, 3, 4], but there are few behavioral data sets for evaluating it as a model of how people learn others' preferences. Additionally, the data sets that do exist tend to be drawn from the developmental literature, which focuses on simple tasks that collect only one or two judgments from children [5, 6, 7]. The limitations of these data sets make it difficult to evaluate the multinomial logit model with respect to alternative accounts of preference learning like the feature-based approach. In this paper, we use data from a new experimental task that elicits a detailed set of preference judgments from a single participant in order to evaluate the predictions of several preference learning models from both the inverse decision-making and feature-based classes. Our task requires each participant to sort a large number of observed decisions on the basis of how strongly they indicate 1

Given one feature of a novel animal, humans readily make inferences about other features of the animal. For example, winged creatures often fly, and creatures that eat fish often live in the water. We explore the knowledge that supports these inferences and compare two approaches. The first approach proposes that humans rely on abstract representations of dependency relationships between features, and is formalized here as a graphical model. The second approach proposes that humans rely on specific knowledge of previously encountered animals, and is formalized here as a family of exemplar models. We evaluate these models using a task where participants reason about chimeras, or animals with pairs of features that have not previously been observed to co-occur. The results support the hypothesis that humans rely on explicit representations of relationships between features.

Communication between a speaker and hearer will be most efficient when both parties make accurate inferences about the other. We study inference and communication in a television game called Password, where speakers must convey secret words to hearers by providing one-word clues. Our working hypothesis is that human communication is relatively efficient, and we use game show data to examine three predictions. First, we predict that speakers and hearers are both considerate, and that both take the other’s perspective into account. Second, we predict that speakers and hearers are calibrated, and that both make accurate assumptions about the strategy used by the other. Finally, we predict that speakers and hearers are collaborative, and that they tend to share the cognitive burden of communication equally. We find evidence in support of all three predictions, and demonstrate in addition that efficient communication tends to break down when speakers and hearers are placed under time pressure.

Situations in which people with opposing prior beliefs observe the same evidence and then strengthen those existing beliefs are frequently offered as evidence of human irrationality. This phenomenon, termed belief polarization, is typically assumed to be non-normative. We demonstrate, however, that a variety of cases of belief polarization are consistent with a Bayesian approach to belief revision. Simulation results indicate that belief polarization is not only possible but relatively common within the class of Bayesian models that we consider.

Many researchers have suggested that the psychological complexity of a concept is related to the length of its representation in a language of thought. As yet, however, there are few concrete proposals about the nature of this language. This paper makes one such proposal: the language of thought allows first order quantification (quantification over objects) more readily than second-order quantification (quantification over features). To support this proposal we present behavioral results from a concept learning study inspired by the work of Shepard, Hovland and Jenkins."

Many categories are better described by providing relational information than listing characteristic features. We present a hierarchical generative model that helps to explain how relational categories are learned and used. Our model learns abstract schemata that specify the relational similarities shared by members of a category, and our emphasis on abstraction departs from previous theoretical proposals that focus instead on comparison of concrete instances. Our first experiment suggests that our abstraction-based account can address some of the tasks that have previously been used to support comparison-based approaches. Our second experiment focuses on one-shot schema learning, a problem that raises challenges for comparison-based approaches but is handled naturally by our abstraction-based account.

Humans are typically able to infer how many objects their environment contains and to recognize when the same object is encountered twice. We present a simple statistical model that helps to explain these abilities and evaluate it in three behavioral experiments. Our first experiment suggests that humans rely on prior knowledge when deciding whether an object token has been previously encountered. Our second and third experiments suggest that humans can infer how many objects they have seen and can learn about categories and their properties even when they are uncertain about which tokens are instances of the same object.

Before the age of 4 months, infants make inductive inferences about the motions of physical objects. Developmental psychologists have provided verbal accounts of the knowledge that supports these inferences, but often these accounts focus on categorical rather than probabilistic principles. We propose that infant object perception is guided in part by probabilistic principles like persistence: things tend to remain the same, and when they change they do so gradually. To illustrate this idea, we develop an ideal observer model that includes probabilistic formulations of rigidity and inertia. Like previous researchers, we suggest that rigid motions are expected from an early age, but we challenge the previous claim that expectations consistent with inertia are relatively slow to develop (Spelke et al., 1992). We support these arguments by modeling four experiments from the developmental literature.

Much of human knowledge is organized into sophisticated systems that are often called intuitive theories. We propose that intuitive theories are mentally repre- sented in a logical language, and that the subjective complexity of a theory is determined by the length of its representation in this language. This complexity measure helps to explain how theories are learned from relational data, and how they support inductive inferences about unobserved relations. We describe two experiments that test our approach, and show that it provides a better account of human learning and reasoning than an approach developed by Goodman [1]. What is a theory, and what makes one theory better than another? Questions like these are of obvious interest to philosophers of science but are also discussed by psychologists, who have argued that everyday knowledge is organized into rich and complex systems that are similar in many respects to scientific theories. Even young children, for instance, have systematic beliefs about domains including folk physics, folk biology, and folk psychology [2]. Intuitive theories like these play many of the same roles as scientific theories: in particular, both kinds of theories are used to explain and encode observations of the world, and to predict future observations. This paper explores the nature, use and acquisition of simple theories. Consider, for instance, an anthropologist who has just begun to study the social structure of a remote tribe, and observes that certain words are used to indicate relationships between selected pairs of individuals. Suppose that term T1(·, ·) can be glossed as ancestor(·, ·), and that T2(·, ·) can be glossed as friend(·, ·). The anthropologist might discover that the first term is transitive, and that the second term is symmetric with a few exceptions. Suppose that term T3(·, ·) can be glossed as defers to(·, ·), and that the tribe divides into two castes such that members of the second caste defer to members of the first caste. In this case the anthropologist might discover two latent concepts (caste 1(·) and caste 2(·)) along with the relationship between these concepts. As these examples suggest, a theory can be defined as a system of laws and concepts that specify the relationships between the elements in some domain [2]. We will consider how these theories are learned, how they are used to encode relational data, and how they support predictions about unob- served relations. Our approach to all three problems relies on the notion of subjective complexity. We propose that theory learners prefer simple theories, that people remember relational data in terms of the simplest underlying theory, and that people extend a partially observed data set according to the simplest theory that is consistent with their observations. There is no guarantee that a single measure of subjective complexity can do all of the work that we require [3]. This paper, however, explores the strong hypothesis that a single measure will suffice. Our formal treatment of subjective complexity begins with the question of how theories are mentally represented. We suggest that theories are represented in some logical language, and propose a spe- cific first-order language that serves as a hypothesis about the “language of thought.” We then pursue the idea that the subjective complexity of a theory corresponds to the length of its representation in this language. Our approach therefore builds on the work of Feldman [4], and is related to other psychological applications of the notion of Kolmogorov complexity [5]. The complexity measure we describe can be used to define a probability distribution over a space of theories, and we develop a model of theory acquisition by using this distribution as the prior for a Bayesian learner. We also

Everyday inductive reasoning draws on many kinds of knowledge, including knowledge about relationships between properties and knowledge about relationships between objects. Previous accounts of inductive reasoning generally focus on just one kind of knowledge: models of causal reasoning often focus on relationships between properties, and models of similarity-based reasoning often focus on similarity relationships between objects. We present a Bayesian model of inductive reasoning that incorporates both kinds of knowledge, and show that it accounts well for human inferences about the properties of biological species.

The objects in many real-world domains can be organized into hierarchies, where each internal node picks out a category of objects. Given a collection of fea- tures and relations defined over a set of objects, an annotated hierarchy includes a specification of the categories that are most useful for describing each individual feature and relation. We define a generative model for annotated hierarchies and the features and relations that they describe, and develop a Markov chain Monte Carlo scheme for learning annotated hierarchies. We show that our model discov- ers interpretable structure in several real-world data sets.

We describe a nonparametric Bayesian approach to generalizing from few labeled examples, guided by a larger set of unlabeled objects and the assumption of a latent tree-structure to the domain. The tree (or a distribution over trees) may be inferred using the unlabeled data. A prior over concepts generated by a mutation process on the inferred tree(s) allows efficient computation of the optimal Bayesian classification func- tion from the labeled examples. We test our approach on eight real-world datasets.

This paper considers how web search engines can learn from the successful searches recorded in their user logs. Document Transformation is a feasible approach that uses these logs to improve document representations. Existing test collections do not allow an adequate investigation of Document Transformation, but we show how a rigorous evaluation of this method can be carried out using the referer logs kept by web servers. We also describe a new strategy for Document Transformation that is suitable for long-term incremental learning. Our experiments show that Document Transformation improves retrieval performance over a medium sized collection of webpages. Commercial search engines may be able to achieve similar improvements by incorporating this approach. These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.