61 citations · 160 across the 21 of their papers we have counts for
28 papers
Causal interventions expose implicit situation models for commonsense language understanding
Takateru Yamakoshi, James L. McClelland, Adele E. Goldberg +1
Accounts of human language processing have long appealed to implicit ``situation models'' that enrich comprehension with relevant but unstated world knowledge. Here, we apply causa…
Overinformative Question Answering by Humans and Machines
Polina Tsvilodub, Michael Franke, Robert D. Hawkins +1
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 informat…
Semantic uncertainty guides the extension of conventions to new referents
Ron Eliav, Anya Ji, Yoav Artzi +1
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…
Flexible social inference facilitates targeted social learning when rewards are not observable
Robert D. Hawkins, Andrew M. Berdahl, Alex "Sandy" Pentland +3
Groups coordinate more effectively when individuals are able to learn from others' successes. But acquiring such knowledge is not always easy, especially in real-world environments…
Abstract Visual Reasoning with Tangram Shapes
Anya Ji, Noriyuki Kojima, Noah Rush +4
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…
How to talk so AI will learn: Instructions, descriptions, and autonomy
Theodore R Sumers, Robert D Hawkins, Mark K Ho +2
From the earliest years of our lives, humans use language to express our beliefs and desires. Being able to talk to artificial agents about our preferences would thus fulfill a cen…
Identifying concept libraries from language about object structure
Catherine Wong, William P. McCarthy, Gabriel Grand +5
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 lever…
Using Natural Language and Program Abstractions to Instill Human Inductive Biases in Machines
Sreejan Kumar, Carlos G. Correa, Ishita Dasgupta +7
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 bi…
Mixed-effects transformers for hierarchical adaptation
Julia White, Noah Goodman, Robert Hawkins
Language use differs dramatically from context to context. To some degree, modern language models like GPT-3 are able to account for such variance by conditioning on a string of pr…
Probing BERT's priors with serial reproduction chains
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…
A pragmatic account of the weak evidence effect
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 classica…
Open-domain clarification question generation without question examples
Julia White, Gabriel Poesia, Robert Hawkins +2
An overarching goal of natural language processing is to enable machines to communicate seamlessly with humans. However, natural language can be ambiguous or unclear. In cases of u…
Learning to communicate about shared procedural abstractions
William P. McCarthy, Robert D. Hawkins, Haoliang Wang +2
Many real-world tasks require agents to coordinate their behavior to achieve shared goals. Successful collaboration requires not only adopting the same communicative conventions, b…
Extending rational models of communication from beliefs to actions
Theodore R. Sumers, Robert D. Hawkins, Mark K. Ho +1
Speakers communicate to influence their partner's beliefs and shape their actions. Belief- and action-based objectives have been explored independently in recent computational mode…
Shades of confusion: Lexical uncertainty modulates ad hoc coordination in an interactive communication task
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…
From partners to populations: A hierarchical Bayesian account of coordination and convention
Robert D. Hawkins, Michael Franke, Michael C. Frank +4
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…
Investigating representations of verb bias in neural language models
Robert D. Hawkins, Takateru Yamakoshi, Thomas L. Griffiths +1
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,…
Learning Rewards from Linguistic Feedback
Theodore R. Sumers, Mark K. Ho, Robert D. Hawkins +2
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 lear…
Generalizing meanings from partners to populations: Hierarchical inference supports convention formation on networks
Robert D. Hawkins, Noah D. Goodman, Adele E. Goldberg +1
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. A…
Characterizing the dynamics of learning in repeated reference games
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…
Continual adaptation for efficient machine communication
Robert D. Hawkins, Minae Kwon, Dorsa Sadigh +1
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 conv…
ShapeGlot: Learning Language for Shape Differentiation
Panos Achlioptas, Judy Fan, Robert X. D. Hawkins +2
In this work we explore how fine-grained differences between the shapes of common objects are expressed in language, grounded on images and 3D models of the objects. We first build…
Pragmatic inference and visual abstraction enable contextual flexibility during visual communication
Judith Fan, Robert Hawkins, Mike Wu +1
Visual modes of communication are ubiquitous in modern life --- from maps to data plots to political cartoons. Here we investigate drawing, the most basic form of visual communicat…
When redundancy is useful: A Bayesian approach to 'overinformative' referring expressions
Judith Degen, Robert D. Hawkins, Caroline Graf +2
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…