Robert D. Hawkins

Catherine Wong, William P. McCarthy, Gabriel Grand et al. · microsoft-research, mit

Our understanding of the visual world goes beyond naming objects, encompassing our ability to parse objects into meaningful parts, attributes, and relations. In this work, we leverage natural language descriptions for a diverse set of 2K procedurally generated objects to identify the parts people use and the principles leading these parts to be favored over others. We formalize our problem as search over a space of program libraries that contain different part concepts, using tools from machine translation to evaluate how well programs expressed in each library align to human language. By combining naturalistic language at scale with structured program representations, we discover a fundamental information-theoretic tradeoff governing the part concepts people name: people favor a lexicon that allows concise descriptions of each object, while also minimizing the size of the lexicon itself.

Takateru Yamakoshi, James L. McClelland, Adele E. Goldberg et al. · stanford

Accounts of human language processing have long appealed to implicit ``situation models'' that enrich comprehension with relevant but unstated world knowledge. Here, we apply causal intervention techniques to recent transformer models to analyze performance on the Winograd Schema Challenge (WSC), where a single context cue shifts interpretation of an ambiguous pronoun. We identify a relatively small circuit of attention heads that are responsible for propagating information from the context word that guides which of the candidate noun phrases the pronoun ultimately attends to. We then compare how this circuit behaves in a closely matched ``syntactic'' control where the situation model is not strictly necessary. These analyses suggest distinct pathways through which implicit situation models are constructed to guide pronoun resolution.

Anya Ji, Noriyuki Kojima, Noah Rush et al. · berkeley

We introduce KiloGram, a resource for studying abstract visual reasoning in humans and machines. Drawing on the history of tangram puzzles as stimuli in cognitive science, we build a richly annotated dataset that, with >1k distinct stimuli, is orders of magnitude larger and more diverse than prior resources. It is both visually and linguistically richer, moving beyond whole shape descriptions to include segmentation maps and part labels. We use this resource to evaluate the abstract visual reasoning capacities of recent multi-modal models. We observe that pre-trained weights demonstrate limited abstract reasoning, which dramatically improves with fine-tuning. We also observe that explicitly describing parts aids abstract reasoning for both humans and models, especially when jointly encoding the linguistic and visual inputs. KiloGram is available at https://lil.nlp.cornell.edu/kilogram .

Sreejan Kumar, Carlos G. Correa, Ishita Dasgupta et al.

Strong inductive biases give humans the ability to quickly learn to perform a variety of tasks. Although meta-learning is a method to endow neural networks with useful inductive biases, agents trained by meta-learning may sometimes acquire very different strategies from humans. We show that co-training these agents on predicting representations from natural language task descriptions and programs induced to generate such tasks guides them toward more human-like inductive biases. Human-generated language descriptions and program induction models that add new learned primitives both contain abstract concepts that can compress description length. Co-training on these representations result in more human-like behavior in downstream meta-reinforcement learning agents than less abstract controls (synthetic language descriptions, program induction without learned primitives), suggesting that the abstraction supported by these representations is key.

Theodore R. Sumers, Robert D. Hawkins, Mark K. Ho et al.

Natural language is an intuitive and expressive way to communicate reward information to autonomous agents. It encompasses everything from concrete instructions to abstract descriptions of the world. Despite this, natural language is often challenging to learn from: it is difficult for machine learning methods to make appropriate inferences from such a wide range of input. This paper proposes a generalization of reward design as a unifying principle to ground linguistic communication: speakers choose utterances to maximize expected rewards from the listener's future behaviors. We first extend reward design to incorporate reasoning about unknown future states in a linear bandit setting. We then define a speaker model which chooses utterances according to this objective. Simulations show that short-horizon speakers (reasoning primarily about a single, known state) tend to use instructions, while long-horizon speakers (reasoning primarily about unknown, future states) tend to describe the reward function. We then define a pragmatic listener which performs inverse reward design by jointly inferring the speaker's latent horizon and rewards. Our findings suggest that this extension of reward design to linguistic communication, including the notion of a latent speaker horizon, is a promising direction for achieving more robust alignment outcomes from natural language supervision.

Leonardo Hernandez Cano, Yewen Pu, Robert D. Hawkins et al.

A typical way in which a machine acquires knowledge from humans is by programming. Compared to learning from demonstrations or experiences, programmatic learning allows the machine to acquire a novel skill as soon as the program is written, and, by building a library of programs, a machine can quickly learn how to perform complex tasks. However, as programs often take their execution contexts for granted, they are brittle when the contexts change, making it difficult to adapt complex programs to new contexts. We present natural programming, a library learning system that combines programmatic learning with a hierarchical planner. Natural programming maintains a library of decompositions, consisting of a goal, a linguistic description of how this goal decompose into sub-goals, and a concrete instance of its decomposition into sub-goals. A user teaches the system via curriculum building, by identifying a challenging yet not impossible goal along with linguistic hints on how this goal may be decomposed into sub-goals. The system solves for the goal via hierarchical planning, using the linguistic hints to guide its probability distribution in proposing the right plans. The system learns from this interaction by adding newly found decompositions in the successful search into its library. Simulated studies and a human experiment (n=360) on a controlled environment demonstrate that natural programming can robustly compose programs learned from different users and contexts, adapting faster and solving more complex tasks when compared to programmatic baselines.

Sunny Yu, Myra Cheng, Ahmad Jabbar et al.

Large language models (LLMs) have the potential to boost human productivity by speeding up task completion -- provided users know when to offload cognitive work to them. But we do not know if users are well-calibrated in estimating these potential time savings. We conducted a preregistered large-scale behavioral study (N = 1237) to characterize mismatches between expectations and reality, with a focus on simple cognitive tasks. While actual completion times between independent completion and AI-assisted completion did not differ, participants predicted AI to be significantly faster. The same bias was not observed when imagining help from another human participant. We identify a speedup illusion where people have accurate forecasts of independent completion times but significantly underestimate AI-assisted times. Additionally, time and effort dissociate: participants reported lower subjective effort with AI despite equivalent completion times. This suggests that completion time itself is not sufficient to characterize efficiency gains.

Sunny Yu, Myra Cheng, Ahmad Jabbar et al.

People are increasingly turning to AI assistance for simple tasks, e.g., arithmetic, spell-check, and answering simple questions. But does AI assistance actually save users time and effort? We investigate people's propensity to use AI for cognitively simple tasks and assess whether their reliance is well-calibrated. Across three pre-registered user studies (N = 2691), we find that people frequently choose to use AI even when doing so is inefficient (i.e. provides no meaningful time or effort savings). We identify systematic miscalibration at two levels: (1) a self-estimate miscalibration where people on average believe that they are using AI less than they actually are, and (2) efficiency-gain illusions where people overestimate how much time and effort savings AI use affords. We also identify a session-level carryover effect where a participant's prior AI use leads to further AI adoption and entrenches their miscalibration about time savings. Our results shed light on the mechanisms and biases underlying people's choice of whether to use AI as well as the risk of an overreliance feedback loop.

Kiyosu Maeda, William P. McCarthy, Ching-Yi Tsai et al.

A quintessential feature of human intelligence is the ability to create ad hoc conventions over time to achieve shared goals efficiently. We investigate how communication strategies evolve through repeated collaboration as people coordinate on shared procedural abstractions. To this end, we conducted an online unimodal study (n = 98) using natural language to probe abstraction hierarchies. In a follow-up lab study (n = 40), we examined how multimodal communication (speech and gestures) changed during physical collaboration. Pairs used augmented reality to isolate their partner's hand and voice; one participant viewed a 3D virtual tower and sent instructions to the other, who built the physical tower. Participants became faster and more accurate by establishing linguistic and gestural abstractions and using cross-modal redundancy to emphasize key changes from previous interactions. Based on these findings, we extend probabilistic models of convention formation to multimodal settings, capturing shifts in modality preferences. Our findings and model provide building blocks for designing convention-aware intelligent agents situated in the physical world.

Chelsea Zou, Yiheng Yao, Selena She et al.

We introduce CalBench, a controlled evaluation environment for studying multi-agent coordination through calendar scheduling. In CalBench, N agents each manage a private calendar containing pre-existing commitments and must coordinate to schedule a stream of M incoming meetings while minimizing disruption costs. Because agents observe only their own calendars, successful scheduling requires communication across private information boundaries. Each scenario is generated with an oracle solution, enabling precise measurement of coordination quality via realized-to-optimal cost, as well as a Distributed Constraint Optimization (DCOP) baseline to provide a fair comparison under the same private-information constraints. CalBench enables precise verification of task success, communication efficiency, and fairness in the distribution of disruption costs. Our environment also studies privacy-preserving coordination by augmenting calendar entries with private semantic contexts of varying sensitivity and measuring whether agents reveal task-irrelevant private information during negotiation. Unlike multi-agent benchmarks where a single capable agent can often substitute for the group, CalBench is inherently decentralized: no agent has access to another agent's private calendar, yet agents must still reach mutually consistent decisions over shared meeting scheduling. CalBench therefore provides a practical and verifiable setting for studying coordination protocols, communication efficiency, negotiation strategies, fairness, and privacy leakage in multi-agent systems.

Yiheng Yao, Chelsea Zou, Robert D. Hawkins

Grounding is the collaborative process of establishing mutual belief sufficient for the current communicative purpose. While static grounding maps language to a shared, externally observable context, dynamic grounding is a joint activity where meaning is negotiated through interaction. Current multi-agent Large Language Model (LLM) benchmarks focus on static, one-shot tasks, overlooking the ability to repair grounding breakdowns across turns. We introduce an iterated, multi-turn negotiation game in which two agents allocate shared resources toward private projects with verifiable jointly optimal outcomes. While individual agents can identify Pareto-optimal allocations in isolation, agent dyads consistently fail to reach them across open- and closed-source models. Our investigation reveals four failure modes: (1) coordination degrades when shared interaction history is absent; (2) yet accumulated context can itself become a liability through stubborn anchoring, where initial proposals are treated as axiomatic rather than negotiable; (3) a reliance on perfunctory fairness (equal resource splits) over reward-maximizing coordination; and (4) failures in referential binding, where agents lose track of commitments across turns. These results highlight dynamic grounding as a critical and understudied axis of multi-agent coordination. Our framework decomposes the coordination gap into measurable components: the oracle baseline establishes that the gap is not attributable to individual reasoning limitations; the no-talk baseline establishes that communication is necessary; and a full-transparency intervention establishes that information exchange alone is insufficient: the bottleneck lies in the interactive processes of joint plan formation, commitment, and execution that constitute dynamic grounding.

Haoran Zhao, Robert D. Hawkins

Polite speech poses a fundamental alignment challenge for large language models (LLMs). Humans deploy a rich repertoire of linguistic strategies to balance informational and social goals -- from positive approaches that build rapport (compliments, expressions of interest) to negative strategies that minimize imposition (hedging, indirectness). We investigate whether LLMs employ a similarly context-sensitive repertoire by comparing human and LLM responses in both constrained and open-ended production tasks. We find that larger models ($\ge$70B parameters) successfully replicate key preferences from the computational pragmatics literature, and human evaluators surprisingly prefer LLM-generated responses in open-ended contexts. However, further linguistic analyses reveal that models disproportionately rely on negative politeness strategies even in positive contexts, potentially leading to misinterpretations. While modern LLMs demonstrate an impressive handle on politeness strategies, these subtle differences raise important questions about pragmatic alignment in AI systems.

Ilia Sucholutsky, Katherine M. Collins, Nori Jacoby et al.

LLMs are already transforming the study of individual cognition, but their application to studying collective cognition has been underexplored. We lay out how LLMs may be able to address the complexity that has hindered the study of collectives and raise possible risks that warrant new methods.

Myra Cheng, Robert D. Hawkins, Dan Jurafsky

Large language models (LLMs) frequently fail to challenge users' harmful beliefs in domains ranging from medical advice to social reasoning. We argue that these failures can be understood and addressed pragmatically as consequences of LLMs defaulting to accommodating users' assumptions and exhibiting insufficient epistemic vigilance. We show that social and linguistic factors known to influence accommodation in humans (at-issueness, linguistic encoding, and source reliability) similarly affect accommodation in LLMs, explaining performance differences across three safety benchmarks that test models' ability to challenge harmful beliefs, spanning misinformation (Cancer-Myth, SAGE-Eval) and sycophancy (ELEPHANT). We further show that simple pragmatic interventions, such as adding the phrase "wait a minute", significantly improve performance on these benchmarks while preserving low false-positive rates. Our results highlight the importance of considering pragmatics for evaluating LLM behavior and improving LLM safety.

Polina Tsvilodub, Karl Mulligan, Todd Snider et al.

When deciding how to act under uncertainty, agents may choose to act to reduce uncertainty or they may act despite that uncertainty.In communicative settings, an important way of reducing uncertainty is by asking clarification questions (CQs). We predict that the decision to ask a CQ depends on both contextual uncertainty and the cost of alternative actions, and that these factors interact: uncertainty should matter most when acting incorrectly is costly. We formalize this interaction in a computational model based on expected regret: how much an agent stands to lose by acting now rather than with full information. We test these predictions in two experiments, one examining purely linguistic responses to questions and another extending to choices between clarification and non-linguistic action. Taken together, our results suggest a rational tradeoff: humans tend to seek clarification proportional to the risk of substantial loss when acting under uncertainty.

Anya Ji, Claire Augusta Bergey, Ron Eliav et al.

How do people talk about things they've never talked about before? One view suggests that a new shared naming system establishes an arbitrary link to a specific target, like proper names that cannot extend beyond their bearers. An alternative view proposes that forming a shared way of describing objects involves broader conceptual alignment, reshaping each individual's semantic space in ways that should generalize to new referents. We test these competing accounts in a dyadic communication study (N=302) leveraging the recently-released KiloGram dataset containing over 1,000 abstract tangram images. After pairs of participants coordinated on referential conventions for one set of images through repeated communication, we measured the extent to which their descriptions aligned for undiscussed images. We found strong evidence for generalization: partners showed increased alignment relative to their pre-test labels. Generalization also decayed nonlinearly with visual similarity (consistent with Shepard's law) and was robust across levels of the images' nameability. These findings suggest that ad hoc conventions are not arbitrary labels but reflect genuine conceptual coordination, with implications for theories of reference and the design of more adaptive language agents.

Yuka Machino, Matthias Hofer, Max Siegel et al.

Misunderstandings in cross-cultural communication often arise from subtle differences in interpretation, but it is unclear whether these differences arise from the literal meanings assigned to words or from more general pragmatic factors such as norms around politeness and brevity. In this paper, we report three experiments examining how speakers of British and American English interpret intensifiers like "quite" and "very." To better understand these cross-cultural differences, we developed a computational cognitive model where listeners recursively reason about speakers who balance informativity, politeness, and utterance cost. Our model comparisons suggested that cross-cultural differences in intensifier interpretation stem from a combination of (1) different literal meanings, (2) different weights on utterance cost. These findings challenge accounts based purely on semantic variation or politeness norms, demonstrating that cross-cultural differences in interpretation emerge from an intricate interplay between the two.

Polina Tsvilodub, Robert D. Hawkins, Michael Franke

Computational models of pragmatic language use have traditionally relied on hand-specified sets of utterances and meanings, limiting their applicability to real-world language use. We propose a neuro-symbolic framework that enhances probabilistic cognitive models by integrating LLM-based modules to propose and evaluate key components in natural language, eliminating the need for manual specification. Through a classic case study of pragmatic question-answering, we systematically examine various approaches to incorporating neural modules into the cognitive model -- from evaluating utilities and literal semantics to generating alternative utterances and goals. We find that hybrid models can match or exceed the performance of traditional probabilistic models in predicting human answer patterns. However, the success of the neuro-symbolic model depends critically on how LLMs are integrated: while they are particularly effective for proposing alternatives and transforming abstract goals into utilities, they face challenges with truth-conditional semantic evaluation. This work charts a path toward more flexible and scalable models of pragmatic language use while illuminating crucial design considerations for balancing neural and symbolic components.

Polina Tsvilodub, Michael Franke, Robert D. Hawkins et al.

When faced with a polar question, speakers often provide overinformative answers going beyond a simple "yes" or "no". But what principles guide the selection of additional information? In this paper, we provide experimental evidence from two studies suggesting that overinformativeness in human answering is driven by considerations of relevance to the questioner's goals which they flexibly adjust given the functional context in which the question is uttered. We take these human results as a strong benchmark for investigating question-answering performance in state-of-the-art neural language models, conducting an extensive evaluation on items from human experiments. We find that most models fail to adjust their answering behavior in a human-like way and tend to include irrelevant information. We show that GPT-3 is highly sensitive to the form of the prompt and only achieves human-like answer patterns when guided by an example and cognitively-motivated explanation.

Ron Eliav, Anya Ji, Yoav Artzi et al.

A long tradition of studies in psycholinguistics has examined the formation and generalization of ad hoc conventions in reference games, showing how newly acquired conventions for a given target transfer to new referential contexts. However, another axis of generalization remains understudied: how do conventions formed for one target transfer to completely distinct targets, when specific lexical choices are unlikely to repeat? This paper presents two dyadic studies (N = 240) that address this axis of generalization, focusing on the role of nameability -- the a priori likelihood that two individuals will share the same label. We leverage the recently-released KiloGram dataset, a collection of abstract tangram images that is orders of magnitude larger than previously available, exhibiting high diversity of properties like nameability. Our first study asks how nameability shapes convention formation, while the second asks how new conventions generalize to entirely new targets of reference. Our results raise new questions about how ad hoc conventions extend beyond target-specific re-use of specific lexical choices.

Takateru Yamakoshi, Thomas L. Griffiths, Robert D. Hawkins

Sampling is a promising bottom-up method for exposing what generative models have learned about language, but it remains unclear how to generate representative samples from popular masked language models (MLMs) like BERT. The MLM objective yields a dependency network with no guarantee of consistent conditional distributions, posing a problem for naive approaches. Drawing from theories of iterated learning in cognitive science, we explore the use of serial reproduction chains to sample from BERT's priors. In particular, we observe that a unique and consistent estimator of the ground-truth joint distribution is given by a Generative Stochastic Network (GSN) sampler, which randomly selects which token to mask and reconstruct on each step. We show that the lexical and syntactic statistics of sentences from GSN chains closely match the ground-truth corpus distribution and perform better than other methods in a large corpus of naturalness judgments. Our findings establish a firmer theoretical foundation for bottom-up probing and highlight richer deviations from human priors.

Samuel A. Barnett, Thomas L. Griffiths, Robert D. Hawkins

Language is not only used to transmit neutral information; we often seek to persuade by arguing in favor of a particular view. Persuasion raises a number of challenges for classical accounts of belief updating, as information cannot be taken at face value. How should listeners account for a speaker's "hidden agenda" when incorporating new information? Here, we extend recent probabilistic models of recursive social reasoning to allow for persuasive goals and show that our model provides a pragmatic account for why weakly favorable arguments may backfire, a phenomenon known as the weak evidence effect. Critically, this model predicts a systematic relationship between belief updates and expectations about the information source: weak evidence should only backfire when speakers are expected to act under persuasive goals and prefer the strongest evidence. We introduce a simple experimental paradigm called the Stick Contest to measure the extent to which the weak evidence effect depends on speaker expectations, and show that a pragmatic listener model accounts for the empirical data better than alternative models. Our findings suggest further avenues for rational models of social reasoning to illuminate classical decision-making phenomena.

Robert D. Hawkins, Megumi Sano, Noah D. Goodman et al.

From photorealistic sketches to schematic diagrams, drawing provides a versatile medium for communicating about the visual world. How do images spanning such a broad range of appearances reliably convey meaning? Do viewers understand drawings based solely on their ability to resemble the entities they refer to (i.e., as images), or do they understand drawings based on shared but arbitrary associations with these entities (i.e., as symbols)? In this paper, we provide evidence for a cognitive account of pictorial meaning in which both visual and social information is integrated to support effective visual communication. To evaluate this account, we used a communication task where pairs of participants used drawings to repeatedly communicate the identity of a target object among multiple distractor objects. We manipulated social cues across three experiments and a full internal replication, finding pairs of participants develop referent-specific and interaction-specific strategies for communicating more efficiently over time, going beyond what could be explained by either task practice or a pure resemblance-based account alone. Using a combination of model-based image analyses and crowdsourced sketch annotations, we further determined that drawings did not drift toward arbitrariness, as predicted by a pure convention-based account, but systematically preserved those visual features that were most distinctive of the target object. Taken together, these findings advance theories of pictorial meaning and have implications for how successful graphical conventions emerge via complex interactions between visual perception, communicative experience, and social context.

William P. McCarthy, Robert D. Hawkins, Haoliang Wang et al.

Many real-world tasks require agents to coordinate their behavior to achieve shared goals. Successful collaboration requires not only adopting the same communicative conventions, but also grounding these conventions in the same task-appropriate conceptual abstractions. We investigate how humans use natural language to collaboratively solve physical assembly problems more effectively over time. Human participants were paired up in an online environment to reconstruct scenes containing two block towers. One participant could see the target towers, and sent assembly instructions for the other participant to reconstruct. Participants provided increasingly concise instructions across repeated attempts on each pair of towers, using higher-level referring expressions that captured each scene's hierarchical structure. To explain these findings, we extend recent probabilistic models of ad-hoc convention formation with an explicit perceptual learning mechanism. These results shed light on the inductive biases that enable intelligent agents to coordinate upon shared procedural abstractions.

Theodore R. Sumers, Robert D. Hawkins, Mark K. Ho et al.

Speakers communicate to influence their partner's beliefs and shape their actions. Belief- and action-based objectives have been explored independently in recent computational models, but it has been challenging to explicitly compare or integrate them. Indeed, we find that they are conflated in standard referential communication tasks. To distinguish these accounts, we introduce a new paradigm called signaling bandits, generalizing classic Lewis signaling games to a multi-armed bandit setting where all targets in the context have some relative value. We develop three speaker models: a belief-oriented speaker with a purely informative objective; an action-oriented speaker with an instrumental objective; and a combined speaker which integrates the two by inducing listener beliefs that generally lead to desirable actions. We then present a series of simulations demonstrating that grounding production choices in future listener actions results in relevance effects and flexible uses of nonliteral language. More broadly, our findings suggest that language games based on richer decision problems are a promising avenue for insight into rational communication.

Sonia K. Murthy, Thomas L. Griffiths, Robert D. Hawkins

There is substantial variability in the expectations that communication partners bring into interactions, creating the potential for misunderstandings. To directly probe these gaps and our ability to overcome them, we propose a communication task based on color-concept associations. In Experiment 1, we establish several key properties of the mental representations of these expectations, or lexical priors, based on recent probabilistic theories. Associations are more variable for abstract concepts, variability is represented as uncertainty within each individual, and uncertainty enables accurate predictions about whether others are likely to share the same association. In Experiment 2, we then examine the downstream consequences of these representations for communication. Accuracy is initially low when communicating about concepts with more variable associations, but rapidly increases as participants form ad hoc conventions. Together, our findings suggest that people cope with variability by maintaining well-calibrated uncertainty about their partner and appropriately adaptable representations of their own.

Robert D. Hawkins, Michael Franke, Michael C. Frank et al.

Languages are powerful solutions to coordination problems: they provide stable, shared expectations about how the words we say correspond to the beliefs and intentions in our heads. Yet language use in a variable and non-stationary social environment requires linguistic representations to be flexible: old words acquire new ad hoc or partner-specific meanings on the fly. In this paper, we introduce CHAI (Continual Hierarchical Adaptation through Inference), a hierarchical Bayesian theory of coordination and convention formation that aims to reconcile the long-standing tension between these two basic observations. We argue that the central computational problem of communication is not simply transmission, as in classical formulations, but continual learning and adaptation over multiple timescales. Partner-specific common ground quickly emerges from social inferences within dyadic interactions, while community-wide social conventions are stable priors that have been abstracted away from interactions with multiple partners. We present new empirical data alongside simulations showing how our model provides a computational foundation for several phenomena that have posed a challenge for previous accounts: (1) the convergence to more efficient referring expressions across repeated interaction with the same partner, (2) the gradual transfer of partner-specific common ground to strangers, and (3) the influence of communicative context on which conventions eventually form.

Robert D. Hawkins, Takateru Yamakoshi, Thomas L. Griffiths et al.

Languages typically provide more than one grammatical construction to express certain types of messages. A speaker's choice of construction is known to depend on multiple factors, including the choice of main verb -- a phenomenon known as \emph{verb bias}. Here we introduce DAIS, a large benchmark dataset containing 50K human judgments for 5K distinct sentence pairs in the English dative alternation. This dataset includes 200 unique verbs and systematically varies the definiteness and length of arguments. We use this dataset, as well as an existing corpus of naturally occurring data, to evaluate how well recent neural language models capture human preferences. Results show that larger models perform better than smaller models, and transformer architectures (e.g. GPT-2) tend to out-perform recurrent architectures (e.g. LSTMs) even under comparable parameter and training settings. Additional analyses of internal feature representations suggest that transformers may better integrate specific lexical information with grammatical constructions.

Theodore R. Sumers, Mark K. Ho, Robert D. Hawkins et al.

We explore unconstrained natural language feedback as a learning signal for artificial agents. Humans use rich and varied language to teach, yet most prior work on interactive learning from language assumes a particular form of input (e.g., commands). We propose a general framework which does not make this assumption, using aspect-based sentiment analysis to decompose feedback into sentiment about the features of a Markov decision process. We then perform an analogue of inverse reinforcement learning, regressing the sentiment on the features to infer the teacher's latent reward function. To evaluate our approach, we first collect a corpus of teaching behavior in a cooperative task where both teacher and learner are human. We implement three artificial learners: sentiment-based "literal" and "pragmatic" models, and an inference network trained end-to-end to predict latent rewards. We then repeat our initial experiment and pair them with human teachers. All three successfully learn from interactive human feedback. The sentiment models outperform the inference network, with the "pragmatic" model approaching human performance. Our work thus provides insight into the information structure of naturalistic linguistic feedback as well as methods to leverage it for reinforcement learning.

Robert D. Hawkins, Noah D. Goodman, Adele E. Goldberg et al.

A key property of linguistic conventions is that they hold over an entire community of speakers, allowing us to communicate efficiently even with people we have never met before. At the same time, much of our language use is partner-specific: we know that words may be understood differently by different people based on our shared history. This poses a challenge for accounts of convention formation. Exactly how do agents make the inferential leap to community-wide expectations while maintaining partner-specific knowledge? We propose a hierarchical Bayesian model to explain how speakers and listeners solve this inductive problem. To evaluate our model's predictions, we conducted an experiment where participants played an extended natural-language communication game with different partners in a small community. We examine several measures of generalization and find key signatures of both partner-specificity and community convergence that distinguish our model from alternatives. These results suggest that partner-specificity is not only compatible with the formation of community-wide conventions, but may facilitate it when coupled with a powerful inductive mechanism.

Robert D. Hawkins, Michael C. Frank, Noah D. Goodman

The language we use over the course of conversation changes as we establish common ground and learn what our partner finds meaningful. Here we draw upon recent advances in natural language processing to provide a finer-grained characterization of the dynamics of this learning process. We release an open corpus (>15,000 utterances) of extended dyadic interactions in a classic repeated reference game task where pairs of participants had to coordinate on how to refer to initially difficult-to-describe tangram stimuli. We find that different pairs discover a wide variety of idiosyncratic but efficient and stable solutions to the problem of reference. Furthermore, these conventions are shaped by the communicative context: words that are more discriminative in the initial context (i.e. that are used for one target more than others) are more likely to persist through the final repetition. Finally, we find systematic structure in how a speaker's referring expressions become more efficient over time: syntactic units drop out in clusters following positive feedback from the listener, eventually leaving short labels containing open-class parts of speech. These findings provide a higher resolution look at the quantitative dynamics of ad hoc convention formation and support further development of computational models of learning in communication.

Robert D. Hawkins, Minae Kwon, Dorsa Sadigh et al.

To communicate with new partners in new contexts, humans rapidly form new linguistic conventions. Recent neural language models are able to comprehend and produce the existing conventions present in their training data, but are not able to flexibly and interactively adapt those conventions on the fly as humans do. We introduce an interactive repeated reference task as a benchmark for models of adaptation in communication and propose a regularized continual learning framework that allows an artificial agent initialized with a generic language model to more accurately and efficiently communicate with a partner over time. We evaluate this framework through simulations on COCO and in real-time reference game experiments with human partners.

Judith Degen, Robert D. Hawkins, Caroline Graf et al.

Referring is one of the most basic and prevalent uses of language. How do speakers choose from the wealth of referring expressions at their disposal? Rational theories of language use have come under attack for decades for not being able to account for the seemingly irrational overinformativeness ubiquitous in referring expressions. Here we present a novel production model of referring expressions within the Rational Speech Act framework that treats speakers as agents that rationally trade off cost and informativeness of utterances. Crucially, we relax the assumption that informativeness is computed with respect to a deterministic Boolean semantics, in favor of a non-deterministic continuous semantics. This innovation allows us to capture a large number of seemingly disparate phenomena within one unified framework: the basic asymmetry in speakers' propensity to overmodify with color rather than size; the increase in overmodification in complex scenes; the increase in overmodification with atypical features; and the increase in specificity in nominal reference as a function of typicality. These findings cast a new light on the production of referring expressions: rather than being wastefully overinformative, reference is usefully redundant.

Robert D. Hawkins, Hyowon Gweon, Noah D. Goodman

Recent debates over adults' theory of mind use have been fueled by surprising failures of perspective-taking in communication, suggesting that perspective-taking can be relatively effortful. How, then, should speakers and listeners allocate their resources to achieve successful communication? We begin with the observation that this shared goal induces a natural division of labor: the resources one agent chooses to allocate toward perspective-taking should depend on their expectations about the other's allocation. We formalize this idea in a resource-rational model augmenting recent probabilistic weighting accounts with a mechanism for (costly) control over the degree of perspective-taking. In a series of simulations, we first derive an intermediate degree of perspective weighting as an optimal tradeoff between expected costs and benefits of perspective-taking. We then present two behavioral experiments testing novel predictions of our model. In Experiment 1, we manipulated the presence or absence of occlusions in a director-matcher task and found that speakers spontaneously produced more informative descriptions to account for "known unknowns" in their partner's private view. In Experiment 2, we compared the scripted utterances used by confederates in prior work with those produced in interactions with unscripted directors. We found that confederates were systematically less informative than listeners would initially expect given the presence of occlusions, but listeners used violations to adaptively make fewer errors over time. Taken together, our work suggests that people are not simply "mindblind"; they use contextually appropriate expectations to navigate the division of labor with their partner. We discuss how a resource rational framework may provide a more deeply explanatory foundation for understanding flexible perspective-taking under processing constraints.