Building machines that learn and think with people
What do we want from machine intelligence? We envision machines that are not just tools
for thought but partners in thought: reasonable, insightful, knowledgeable, reliable and …
for thought but partners in thought: reasonable, insightful, knowledgeable, reliable and …
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 humans make
meaning from language--and how can we leverage a theory of linguistic meaning to build …
meaning from language--and how can we leverage a theory of linguistic meaning to build …
Sequential monte carlo steering of large language models using probabilistic programs
Even after fine-tuning and reinforcement learning, large language models (LLMs) can be
difficult, if not impossible, to control reliably with prompts alone. We propose a new inference …
difficult, if not impossible, to control reliably with prompts alone. We propose a new inference …
The neuro-symbolic inverse planning engine (nipe): Modeling probabilistic social inferences from linguistic inputs
Human beings are social creatures. We routinely reason about other agents, and a crucial
component of this social reasoning is inferring people's goals as we learn about their …
component of this social reasoning is inferring people's goals as we learn about their …
Inferring the goals of communicating agents from actions and instructions
When humans cooperate, they frequently coordinate their activity through both verbal
communication and non-verbal actions, using this information to infer a shared goal and …
communication and non-verbal actions, using this information to infer a shared goal and …
Loose LIPS Sink Ships: Asking Questions in Battleship with Language-Informed Program Sampling
Questions combine our mastery of language with our remarkable facility for reasoning about
uncertainty. How do people navigate vast hypothesis spaces to pose informative questions …
uncertainty. How do people navigate vast hypothesis spaces to pose informative questions …
Applications of Large Language Models for Robot Navigation and Scene Understanding
W Chen - 2023 - dspace.mit.edu
Common-sense reasoning is a key challenge in robot navigation and 3D scene
understanding. Humans tend to reason about their environments in abstract terms, with a …
understanding. Humans tend to reason about their environments in abstract terms, with a …
Bayesian Statistical Modeling with Predictors from LLMs
State of the art large language models (LLMs) have shown impressive performance on a
variety of benchmark tasks and are increasingly used as components in larger applications …
variety of benchmark tasks and are increasingly used as components in larger applications …
Neural language models and human linguistic knowledge
J Hu - 2023 - dspace.mit.edu
Language is one of the hallmarks of intelligence, demanding explanation in a theory of
human cognition. However, language presents unique practical challenges for quantitative …
human cognition. However, language presents unique practical challenges for quantitative …
Cognitive Modeling with Scaffolded LLMs: A Case Study of Referential Expression Generation
To what extent can LLMs be used as part of a cognitive model of language generation? In
this paper, we approach this question by exploring a neuro-symbolic implementation of an …
this paper, we approach this question by exploring a neuro-symbolic implementation of an …