Pith. sign in

REVIEW 3 cited by

The Neuro-Symbolic Inverse Planning Engine (NIPE): Modeling Probabilistic Social Inferences from Linguistic Inputs

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

arxiv 2306.14325 v2 pith:7AAIE7QX submitted 2023-06-25 cs.AI cs.LG

classification cs.AIcs.LG
keywords goalhumaninferencelanguagemodelsociallinguisticactions
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

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 actions. In many settings, we can perform intuitive but reliable goal inference from language descriptions of agents, actions, and the background environments. In this paper, we study this process of language driving and influencing social reasoning in a probabilistic goal inference domain. We propose a neuro-symbolic model that carries out goal inference from linguistic inputs of agent scenarios. The "neuro" part is a large language model (LLM) that translates language descriptions to code representations, and the "symbolic" part is a Bayesian inverse planning engine. To test our model, we design and run a human experiment on a linguistic goal inference task. Our model closely matches human response patterns and better predicts human judgements than using an LLM alone.

Discussion (0). Sign in to comment.

Forward citations

Cited by 3 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Modeling Open-World Cognition as On-Demand Synthesis of Probabilistic Models

    cs.CL 2025-07 conditional novelty 6.0 of 10

    A hybrid language-model and probabilistic-program architecture predicts human judgments on novel open-world reasoning vignettes better than language-model-only baselines.

  2. What's in the Box? Reasoning about Unseen Objects from Multimodal Cues

    cs.AI 2025-06 reject novelty 5.0 of 10

    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.

  3. Belief Attribution as Mental Explanation: The Role of Accuracy, Informativity, and Causality

    cs.CL 2025-05 conditional novelty 5.0 of 10

    When people say what an agent believes, they prefer beliefs that are causally relevant to the agent's actions, more than beliefs that are merely accurate or informative.

Pith tools