mlsanityData to 14 Oct 2026

From Word Models to World Models: Translating from Natural Language to the Probabilistic Language of Thought

arXiv 2306.12672 ↗First posted 22 Jun 2023cs.CL cs.AI cs.SCcited by 119

On the map: World models → World models for language agents

also in 1 more
Abstract (arXiv)

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 machines that think in more human-like ways? In this paper, we propose rational meaning construction, a computational framework for language-informed thinking that combines neural language models with probabilistic models for rational inference. We frame linguistic meaning as a context-sensitive mapping from natural language into a probabilistic language of thought (PLoT)--a general-purpose symbolic substrate for generative world modeling. Our architecture integrates two computational tools that have not previously come together: we model thinking with probabilistic programs, an expressive representation for commonsense reasoning; and we model meaning construction with large language models (LLMs), which support broad-coverage translation from natural language utterances to code expressions in a probabilistic programming language. We illustrate our framework through examples covering four core domains from cognitive science: probabilistic reasoning, logical and relational reasoning, visual and physical reasoning, and social reasoning. In each, we show that LLMs can generate context-sensitive translations that capture pragmatically-appropriate linguistic meanings, while Bayesian inference with the generated programs supports coherent and robust commonsense reasoning. We extend our framework to integrate cognitively-motivated symbolic modules (physics simulators, graphics engines, and planning algorithms) to provide a unified commonsense thinking interface from language. Finally, we explore how language can drive the construction of world models themselves. We hope this work will provide a roadmap towards cognitive models and AI systems that synthesize the insights of both modern and classical computational perspectives.

Key facts. Cited by 119 papers in the map (data through 14 Oct 2026). Placed in World models for language agents, one of 11 directions in World models. Builds on 73 of its 372 references that are in the map. First posted on arXiv 22 Jun 2023.

Builds on

73 of 372 references.

Closest ancestors · 1

Same direction, newest first

  1. 2020Language Models are Few-Shot Learners28 May

Other references · 72

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2022Training language models to follow instructions with human feedbackcited by 15,971
  3. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
  4. 2021Training Verifiers to Solve Math Word Problemscited by 10,109
  5. 2021Evaluating Large Language Models Trained on Codecited by 8,320
  6. 2022Hierarchical Text-Conditional Image Generation with CLIP Latentscited by 6,585
  7. 2022Large Language Models are Zero-Shot Reasonerscited by 4,374
  8. 2023Toolformer: Language Models Can Teach Themselves to Use Toolscited by 4,182
  9. 2021On the Opportunities and Risks of Foundation Modelscited by 4,033
  10. 2023Sparks of Artificial General Intelligence: Early experiments with GPT-4cited by 2,592
  11. 2022Do As I Can, Not As I Say: Grounding Language in Robotic Affordancescited by 2,348
  12. 2018Deep contextualized word representationscited by 2,290
38 more
  1. 2023Voyager: An Open-Ended Embodied Agent with Large Language Modelscited by 2,191
  2. 2021Improving language models by retrieving from trillions of tokenscited by 1,293
  3. 2022LaMDA: Language Models for Dialog Applicationscited by 1,220
  4. 2021Scaling Language Models: Methods, Analysis & Insights from Training Gophercited by 1,202
  5. 2019BERT Rediscovers the Classical NLP Pipelinecited by 1,059
  6. 2022Atlas: Few-shot Learning with Retrieval Augmented Language Modelscited by 952
  7. 2020On Faithfulness and Factuality in Abstractive Summarizationcited by 900
  8. 2021Show Your Work: Scratchpads for Intermediate Computation with Language Modelscited by 886
  9. 2022A Generalist Agentcited by 808
  10. 2023LLM+P: Empowering Large Language Models with Optimal Planning Proficiencycited by 501
  11. 2022InCoder: A Generative Model for Code Infilling and Synthesiscited by 498
  12. 2019CLEVRER: CoLlision Events for Video REpresentation and Reasoningcited by 484
  13. 2022Large Language Models Struggle to Learn Long-Tail Knowledgecited by 458
  14. 2023Logic-LM: Empowering Large Language Models with Symbolic Solvers for Faithful Logical Reasoningcited by 391
  15. 2022Selection-Inference: Exploiting Large Language Models for Interpretable Logical Reasoningcited by 334
  16. 2018Neural-Symbolic VQA: Disentangling Reasoning from Vision and Language Understandingcited by 304
  17. 2023Large Language Models Fail on Trivial Alterations to Theory-of-Mind Taskscited by 292
  18. 2023Faithful Chain-of-Thought Reasoningcited by 288
  19. 2017Challenges in Data-to-Document Generationcited by 226
  20. 2023Evaluating the Logical Reasoning Ability of ChatGPT and GPT-4cited by 202
  21. 2021Implicit Representations of Meaning in Neural Language Modelscited by 180
  22. 2022Hydra: A Real-time Spatial Perception System for 3D Scene Graph Construction and Optimizationcited by 178
  23. 2022ROSCOE: A Suite of Metrics for Scoring Step-by-Step Reasoningcited by 177
  24. 2020DreamCoder: Growing generalizable, interpretable knowledge with wake-sleep Bayesian program learningcited by 161
  25. 2019Good-Enough Compositional Data Augmentationcited by 158
  26. 2022MRKL Systems: A modular, neuro-symbolic architecture that combines large language models, external knowledge sources and discrete reasoningcited by 156
  27. 2023Task and Motion Planning with Large Language Models for Object Rearrangementcited by 141
  28. 2022On the Origin of Hallucinations in Conversational Models: Is it the Datasets or the Models?cited by 138
  29. 2023Translating Natural Language to Planning Goals with Large-Language Modelscited by 133
  30. 2020How Can We Accelerate Progress Towards Human-like Linguistic Generalization?cited by 114
  31. 2016Data Recombination for Neural Semantic Parsingcited by 111
  32. 2018Coarse-to-Fine Decoding for Neural Semantic Parsingcited by 110
  33. 2022Language Model Cascadescited by 107
  34. 2020Graph-based, Self-Supervised Program Repair from Diagnostic Feedbackcited by 94
  35. 2023Red teaming ChatGPT via Jailbreaking: Bias, Robustness, Reliability and Toxicitycited by 89
  36. 2023On the Planning Abilities of Large Language Models (A Critical Investigation with a Proposed Benchmark)cited by 85
  37. 2022Mind's Eye: Grounded Language Model Reasoning through Simulationcited by 84
  38. 2022A very preliminary analysis of DALL-E 2cited by 82

50 most cited of 72 All 72 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 18; 2024: 47; 2025: 34; 2026: 20.

119 papers.

Sort:

By area:

  1. 2023The Rise and Potential of Large Language Model Based Agents: A Surveycited by 1,439
  2. 2023Cognitive Architectures for Language Agentscited by 429
  3. 2024Mechanistic Interpretability for AI Safety -- A Reviewcited by 422
  4. 2024To CoT or not to CoT? Chain-of-thought helps mainly on math and symbolic reasoningcited by 263
  5. 2023Reasoning or Reciting? Exploring the Capabilities and Limitations of Language Models Through Counterfactual Taskscited by 246
  6. 2024Aligning Cyber Space with Physical World: A Comprehensive Survey on Embodied AIcited by 179
  7. 2023LINC: A Neurosymbolic Approach for Logical Reasoning by Combining Language Models with First-Order Logic Proverscited by 168
  8. 2024A Comprehensive Study of Knowledge Editing for Large Language Modelscited by 163
  9. 2023SeaEval for Multilingual Foundation Models: From Cross-Lingual Alignment to Cultural Reasoningcited by 94
  10. 2023Phenomenal Yet Puzzling: Testing Inductive Reasoning Capabilities of Language Models with Hypothesis Refinementcited by 89
  11. 2024Pandora: Towards General World Model with Natural Language Actions and Video Statescited by 86
  12. 2024Open-Endedness is Essential for Artificial Superhuman Intelligencecited by 80
38 more
  1. 2024Building Machines that Learn and Think with Peoplecited by 73
  2. 2023Language Models, Agent Models, and World Models: The LAW for Machine Reasoning and Planningcited by 60
  3. 2024Is this the real life? Is this just fantasy? The Misleading Success of Simulating Social Interactions With LLMscited by 59
  4. 2024Elements of World Knowledge (EWoK): A Cognition-Inspired Framework for Evaluating Basic World Knowledge in Language Modelscited by 55
  5. 2024Can Language Models Serve as Text-Based World Simulators?cited by 52
  6. 2024Beyond Preferences in AI Alignmentcited by 49
  7. 2024Large Language Models and Cognitive Science: A Comprehensive Review of Similarities, Differences, and Challengescited by 49
  8. 2023From task structures to world models: What do LLMs know?cited by 46
  9. 2024Automated Statistical Model Discovery with Language Modelscited by 41
  10. 2023Statler: State-Maintaining Language Models for Embodied Reasoningcited by 40
  11. 2024On the Prospects of Incorporating Large Language Models (LLMs) in Automated Planning and Scheduling (APS)cited by 40
  12. 2024Generating Code World Models with Large Language Models Guided by Monte Carlo Tree Searchcited by 40
  13. 2024Moral Alignment for LLM Agentscited by 39
  14. 2023Visual cognition in multimodal large language modelscited by 38
  15. 2024Benchmarking Agentic Workflow Generationcited by 37
  16. 2025Bayesian Teaching Enables Probabilistic Reasoning in Large Language Modelscited by 37
  17. 2024Can Large Language Models Understand Symbolic Graphics Programs?cited by 35
  18. 2025Emergent Symbolic Mechanisms Support Abstract Reasoning in Large Language Modelscited by 31
  19. 2023Provably safe systems: the only path to controllable AGIcited by 29
  20. 2025Text2World: Benchmarking Large Language Models for Symbolic World Model Generationcited by 26
  21. 2023LARP: Language-Agent Role Play for Open-World Gamescited by 24
  22. 2023The Neuro-Symbolic Inverse Planning Engine (NIPE): Modeling Probabilistic Social Inferences from Linguistic Inputscited by 23
  23. 2024DeLLMa: Decision Making Under Uncertainty with Large Language Modelscited by 21
  24. 2024Eliciting the Priors of Large Language Models using Iterated In-Context Learningcited by 19
  25. 2024BIRD: A Trustworthy Bayesian Inference Framework for Large Language Modelscited by 18
  26. 2024Large Language Model Benchmarks in Medical Taskscited by 17
  27. 2026Calibrate-Then-Act: Cost-Aware Exploration in LLM Agentscited by 17
  28. 2024A Notion of Complexity for Theory of Mind via Discrete World Modelscited by 16
  29. 2025Social World Modelscited by 16
  30. 2024Generating consistent PDDL domains with Large Language Modelscited by 15
  31. 2024Goals as Reward-Producing Programscited by 14
  32. 2024BlendRL: A Framework for Merging Symbolic and Neural Policy Learningcited by 14
  33. 2025Modeling Open-World Cognition as On-Demand Synthesis of Probabilistic Modelscited by 14
  34. 2025Simulating Society Requires Simulating Thoughtcited by 13
  35. 2024Loose LIPS Sink Ships: Asking Questions in Battleship with Language-Informed Program Samplingcited by 12
  36. 2024OneEdit: A Neural-Symbolic Collaboratively Knowledge Editing Systemcited by 12
  37. 2025LLM-Guided Probabilistic Program Induction for POMDP Model Estimationcited by 12
  38. 2023AI for Mathematics: A Cognitive Science Perspectivecited by 10

50 most cited of 119 All 119 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2021Towards General Natural Language Understanding with Probabilistic Worldbuilding
  2. 2025On the Thinking-Language Modeling Gap in Large Language Models
  3. 2024A Philosophical Introduction to Language Models -- Part I: Continuity With Classic Debates
  4. 2026Induction and Inquiry via Probabilistic Reasoning over Language and Code
  5. 2025Language and Thought: The View from LLMs
  6. 2024"Understanding AI": Semantic Grounding in Large Language Models
  7. 2026Reasoning aligns language models to human cognition
  8. 2023Why Can Large Language Models Generate Correct Chain-of-Thoughts?