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 …
Reasoning with language model is planning with world model
Large language models (LLMs) have shown remarkable reasoning capabilities, especially
when prompted to generate intermediate reasoning steps (eg, Chain-of-Thought, CoT) …
when prompted to generate intermediate reasoning steps (eg, Chain-of-Thought, CoT) …
Language models, agent models, and world models: The law for machine reasoning and planning
Despite their tremendous success in many applications, large language models often fall
short of consistent reasoning and planning in various (language, embodied, and social) …
short of consistent reasoning and planning in various (language, embodied, and social) …
Language models show human-like content effects on reasoning
Abstract reasoning is a key ability for an intelligent system. Large language models (LMs)
achieve above-chance performance on abstract reasoning tasks, but exhibit many …
achieve above-chance performance on abstract reasoning tasks, but exhibit many …
Structured, flexible, and robust: benchmarking and improving large language models towards more human-like behavior in out-of-distribution reasoning tasks
Human language offers a powerful window into our thoughts--we tell stories, give
explanations, and express our beliefs and goals through words. Abundant evidence also …
explanations, and express our beliefs and goals through words. Abundant evidence also …
Inner monologue: Embodied reasoning through planning with language models
Recent works have shown how the reasoning capabilities of Large Language Models
(LLMs) can be applied to domains beyond natural language processing, such as planning …
(LLMs) can be applied to domains beyond natural language processing, such as planning …
Statler: State-maintaining language models for embodied reasoning
Large language models (LLMs) provide a promising tool that enable robots to perform
complex robot reasoning tasks. However, the limited context window of contemporary LLMs …
complex robot reasoning tasks. However, the limited context window of contemporary LLMs …
Tree of thoughts: Deliberate problem solving with large language models
Abstract Language models are increasingly being deployed for general problem solving
across a wide range of tasks, but are still confined to token-level, left-to-right decision …
across a wide range of tasks, but are still confined to token-level, left-to-right decision …
Chain of code: Reasoning with a language model-augmented code emulator
Code provides a general syntactic structure to build complex programs and perform precise
computations when paired with a code interpreter--we hypothesize that language models …
computations when paired with a code interpreter--we hypothesize that language models …
Facts as experts: Adaptable and interpretable neural memory over symbolic knowledge
Massive language models are the core of modern NLP modeling and have been shown to
encode impressive amounts of commonsense and factual information. However, that …
encode impressive amounts of commonsense and factual information. However, that …