research
∙
09/11/2023
Hypothesis Search: Inductive Reasoning with Language Models
Inductive reasoning is a core problem-solving capacity: humans can ident...
share
research
∙
06/22/2023
From Word Models to World Models: Translating from Natural Language to the Probabilistic Language of Thought
How does language inform our downstream thinking? In particular, how do ...
research
∙
06/21/2023
Understanding Social Reasoning in Language Models with Language Models
As Large Language Models (LLMs) become increasingly integrated into our ...
research
∙
06/16/2023
Just One Byte (per gradient): A Note on Low-Bandwidth Decentralized Language Model Finetuning Using Shared Randomness
Language model training in distributed settings is limited by the commun...
research
∙
06/06/2023
Certified Reasoning with Language Models
Language models often achieve higher accuracy when reasoning step-by-ste...
research
∙
05/30/2023
Strategic Reasoning with Language Models
Strategic reasoning enables agents to cooperate, communicate, and compet...
research
∙
05/19/2023
Characterizing tradeoffs between teaching via language and demonstrations in multi-agent systems
Humans teach others about the world through language and demonstration. ...
research
∙
05/15/2023
Interpretability at Scale: Identifying Causal Mechanisms in Alpaca
Obtaining human-interpretable explanations of large, general-purpose lan...
research
∙
05/11/2023
Overinformative Question Answering by Humans and Machines
When faced with a polar question, speakers often provide overinformative...
research
∙
05/05/2023
Bayesian Reinforcement Learning with Limited Cognitive Load
All biological and artificial agents must learn and make decisions given...
research
∙
04/16/2023
Solving Math Word Problems by Combining Language Models With Symbolic Solvers
Automatically generating high-quality step-by-step solutions to math wor...
research
∙
04/07/2023
Why think step-by-step? Reasoning emerges from the locality of experience
Humans have a powerful and mysterious capacity to reason. By working thr...
research
∙
03/05/2023
Finding Alignments Between Interpretable Causal Variables and Distributed Neural Representations
Causal abstraction is a promising theoretical framework for explainable ...
research
∙
12/20/2022
Parsel: A Unified Natural Language Framework for Algorithmic Reasoning
Despite recent success in large language model (LLM) reasoning, LLMs sti...
research
∙
12/01/2022
Flexible social inference facilitates targeted social learning when rewards are not observable
Relying on others can be as risky as it can be rewarding. Advice seekers...
research
∙
11/29/2022
Peano: Learning Formal Mathematical Reasoning
General mathematical reasoning is computationally undecidable, but human...
research
∙
10/30/2022
On Rate-Distortion Theory in Capacity-Limited Cognition Reinforcement Learning
Throughout the cognitive-science literature, there is widespread agreeme...
research
∙
05/18/2022
Color Overmodification Emerges from Data-Driven Learning and Pragmatic Reasoning
Speakers' referential expressions often depart from communicative ideals...
research
∙
03/28/2022
STaR: Bootstrapping Reasoning With Reasoning
Generating step-by-step "chain-of-thought" rationales improves language ...
research
∙
12/05/2021
Causal Distillation for Language Models
Distillation efforts have led to language models that are more compact a...
research
∙
12/01/2021
Inducing Causal Structure for Interpretable Neural Networks
In many areas, we have well-founded insights about causal structure that...
research
∙
10/11/2021
Calibrate your listeners! Robust communication-based training for pragmatic speakers
To be good conversational partners, natural language processing (NLP) sy...
research
∙
04/16/2021
Concadia: Tackling image accessibility with context
Images have become an integral part of online media. This has enhanced s...
research
∙
04/12/2021
From partners to populations: A hierarchical Bayesian account of coordination and convention
Languages are powerful solutions to coordination problems: they provide ...
research
∙
05/31/2020
Learning to refer informatively by amortizing pragmatic reasoning
A hallmark of human language is the ability to effectively and efficient...
research
∙
02/04/2020
Generalizing meanings from partners to populations: Hierarchical inference supports convention formation on networks
A key property of linguistic conventions is that they hold over an entir...
research
∙
12/16/2019
Characterizing the dynamics of learning in repeated reference games
The language we use over the course of conversation changes as we establ...
research
∙
11/22/2019
Continual adaptation for efficient machine communication
To communicate with new partners in new contexts, humans rapidly form ne...
research
∙
09/12/2019
Analyzing machine-learned representations: A natural language case study
As modern deep networks become more complex, and get closer to human-lik...
research
∙
06/04/2019
Learning to Explain: Answering Why-Questions via Rephrasing
Providing plausible responses to why questions is a challenging but crit...
research
∙
05/08/2019
ShapeGlot: Learning Language for Shape Differentiation
In this work we explore how fine-grained differences between the shapes ...
research
∙
03/19/2019
When redundancy is rational: A Bayesian approach to 'overinformative' referring expressions
Referring is one of the most basic and prevalent uses of language. How d...
research
∙
03/15/2019
Applying Probabilistic Programming to Affective Computing
Affective Computing is a rapidly growing field spurred by advancements i...
research
∙
11/21/2018
Joint Mapping and Calibration via Differentiable Sensor Fusion
We leverage automatic differentiation (AD) and probabilistic programming...
research
∙
10/18/2018
Pyro: Deep Universal Probabilistic Programming
Pyro is a probabilistic programming language built on Python as a platfo...
research
∙
09/30/2018
An Incremental Iterated Response Model of Pragmatics
Recent Iterated Response (IR) models of pragmatics conceptualize languag...
research
∙
07/24/2018
Speakers account for asymmetries in visual perspective so listeners don't have to
Debates over adults' theory of mind use have been fueled by surprising f...
research
∙
05/30/2018
Planning, Inference and Pragmatics in Sequential Language Games
We study sequential language games in which two players, each with priva...
research
∙
02/12/2018
Evaluating Compositionality in Sentence Embeddings
An important frontier in the quest for human-like AI is compositional se...
research
∙
10/12/2017
DisSent: Sentence Representation Learning from Explicit Discourse Relations
Sentence vectors represent an appealing approach to meaning: learn an em...
research
∙
06/01/2017
Learning Disentangled Representations with Semi-Supervised Deep Generative Models
Variational autoencoders (VAEs) learn representations of data by jointly...
research
∙
03/29/2017
Colors in Context: A Pragmatic Neural Model for Grounded Language Understanding
We present a model of pragmatic referring expression interpretation in a...
research
∙
11/22/2016
Inducing Interpretable Representations with Variational Autoencoders
We develop a framework for incorporating structured graphical models in ...
research
∙
10/18/2016
Deep Amortized Inference for Probabilistic Programs
Probabilistic programming languages (PPLs) are a powerful modeling tool,...
research
∙
08/09/2016
A pragmatic theory of generic language
Generalizations about categories are central to human understanding, and...
research
∙
06/13/2016
Learning to Generate Compositional Color Descriptions
The production of color language is essential for grounded language gene...
research
∙
03/19/2016
Neurally-Guided Procedural Models: Amortized Inference for Procedural Graphics Programs using Neural Networks
Probabilistic inference algorithms such as Sequential Monte Carlo (SMC) ...
research
∙
12/18/2015
Learning the Preferences of Ignorant, Inconsistent Agents
An important use of machine learning is to learn what people value. What...
research
∙
09/09/2015
Coarse-to-Fine Sequential Monte Carlo for Probabilistic Programs
Many practical techniques for probabilistic inference require a sequence...
research
∙
09/07/2015