REVIEW 21 cited by
From Word Models to World Models: Translating from Natural Language to the Probabilistic Language of Thought
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Signed reviews
read the original abstract
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.
Forward citations
Cited by 21 Pith papers
-
World Modeling with Probabilistic Structure Integration
A single probabilistic video model extracts optical flow, depth, and segments via counterfactual prompts, then integrates those structures as new token types to improve its own video predictions.
-
Language-Informed Synthesis of Rational Agent Models for Grounded Theory-of-Mind Reasoning On-The-Fly
LIRAS synthesizes PDDL world models and agent configurations from language, parses video frames into symbolic states, and runs Bayesian inverse planning (SIAM) to produce human-like graded social inferences across fiv...
-
When Do Neural Networks Learn World Models?
With Boolean variables, a low-degree bias, and a task distribution weighted toward simple functions of the latents, multi-task training provably recovers the latent world model up to permutations and negations.
-
Policy-as-logic for robust reasoning over rules
A policy-as-logic pipeline, where an LLM extracts facts and an answer-set solver reasons over them, beats prompt-only and code-only baselines on objective policy benchmarks while using fewer tokens.
-
Learning Task-Sufficient World Models by Synergizing Agentic Exploration and Structured Modeling
Closed-loop agentic probing plus minimality/sufficiency masking recovers compact task-sufficient world-model latents that improve sample-efficient policy learning and cross-task generalization.
-
What Does it Mean for a Neural Network to Learn a "World Model"?
Defines a world model as a simple commutative-diagram factorization through an intermediate representation, with conditions that the model be learned and emergent rather than inherited from input or output.
-
Understanding Human Limits in Pattern Recognition: A Computational Model of Sequential Reasoning in Rock, Paper, Scissors
An LLM agent reproduces human rock-paper-scissors pattern learning, and interventions suggest that hypothesis generation, not evaluation, is the main cognitive bottleneck.
-
Modeling Open-World Cognition as On-Demand Synthesis of Probabilistic Models
A hybrid language-model and probabilistic-program architecture predicts human judgments on novel open-world reasoning vignettes better than language-model-only baselines.
-
LLMs as World Models: Data-Driven and Human-Centered Pre-Event Simulation for Disaster Impact Assessment
The authors show that prompting LLMs with earthquake parameters, local building, demographic, and street view data yields Modified Mercalli Intensity estimates that track USGS 'Did You Feel It?' reports for the 2014 N...
-
Integrating Neural and Symbolic Components in a Model of Pragmatic Question-Answering
A neuro-symbolic Rational Speech Act model with LLM proposers and evaluators predicts human question-answer patterns about as well as the fully hand-specified probabilistic model.
-
LLM-Guided Probabilistic Program Induction for POMDP Model Estimation
LLM-guided probabilistic program induction can learn low-complexity POMDP models from ten demonstrations and outperform tabular learning, behavior cloning, and direct LLM planning in simulated and real robot domains.
-
Exploring the Potential for Large Language Models to Demonstrate Rational Probabilistic Beliefs
LLMs frequently violate the probability axioms of complementarity and monotonicity when rating the truth of everyday claims, even when using chain-of-thought or argumentative prompting techniques.
-
Neuro-Symbolic Frameworks: Conceptual Characterization and Empirical Comparative Analysis
A facet-based comparison of DeepProbLog, Scallop, and DomiKnowS with efficiency measurements on four toy tasks, identifying challenges for future neurosymbolic frameworks.
-
Generation and Evaluation in the Human Invention Process through the Lens of Game Design
A two-stage model adding simulated-play funness to a language-model proposal prior best fits novice-invented games, but the model comparison is undermined by including the observed games in the normalization set and b...
-
Analogy making as amortised model construction
Analogy is formalized as a partial MDP homomorphism, and a library of reusable abstract modules is proposed to amortize the cost of constructing and solving internal models of novel situations.
-
What's in the Box? Reasoning about Unseen Objects from Multimodal Cues
A neurosymbolic pipeline combining LLM parsing, audio classification, and Bayesian reasoning achieves r=0.78 correlation with human judgments on a new hidden-object guessing task.
-
Using LLMs to Advance the Cognitive Science of Collectives
A position paper arguing that LLMs can help cognitive scientists study collective behavior along structural, interactional, and individual complexity axes, with cautions about bias and reproducibility.
-
ZeroSumEval: Scaling LLM Evaluation with Inter-Model Competition
ZeroSumEval ranks 13 LLMs through over 7,000 head-to-head games and finds models fall short at creative generation and jailbreaking.
-
NeuroAI for AI Safety
A roadmap arguing that neuroscience-inspired approaches can materially improve technical AI safety, with feasibility analyses of several concrete research directions.
-
Position: Stop Acting Like Language Model Agents Are Normal Agents
LMAs should be treated as systems whose agency is unstable and must be measured, not as normal agents with persistent identity.
-
Revisiting Rogers' Paradox in the Context of Human-AI Interaction
A simulation of Rogers' Paradox with an AI agent that learns the population average shows that cheap AI alone does not improve collective world understanding, while critical appraisal and independent AI learning can.
Discussion (0). Continue with ORCID to comment.