MétaCan
Menu
Back to cohort

NEWTON: Are Large Language Models Capable of Physical Reasoning?

2023· article· en· W4389520485 on OpenAlexfundno aff
Yi Wang, Jiafei Duan, Dieter Fox, Siddhartha S Srinivasa

Bibliographic record

Venuenot available
Typearticle
Languageen
FieldComputer Science
TopicTopic Modeling
Canadian institutionsnot available
FundersOffice of Naval ResearchNatural Sciences and Engineering Research Council of CanadaDefense Advanced Research Projects AgencyNational Science Foundation
KeywordsBenchmark (surveying)Computer scienceQualitative reasoningConsistency (knowledge bases)Automated reasoningArtificial intelligenceMainstreamNatural language processingData science

Abstract

fetched live from OpenAlex

Large Language Models (LLMs), through their contextualized representations, have been empirically proven to encapsulate syntactic, semantic, word sense, and common-sense knowledge.However, there has been limited exploration of their physical reasoning abilities, specifically concerning the crucial attributes for comprehending everyday objects.To address this gap, we introduce NEWTON, a repository and benchmark for evaluating the physics reasoning skills of LLMs.Further, to enable domain-specific adaptation of this benchmark, we present a pipeline to enable researchers to generate a variant of this benchmark that has been customized to the objects and attributes relevant for their application.The NEWTON repository comprises a collection of 2800 object-attribute pairs, providing the foundation for generating infinitescale assessment templates.The NEWTON benchmark consists of 160K QA questions, curated using the NEWTON repository to investigate the physical reasoning capabilities of several mainstream language models across foundational, explicit, and implicit reasoning tasks.Through extensive empirical analysis, our results highlight the capabilities of LLMs for physical reasoning.We find that LLMs like GPT-4 demonstrate strong reasoning capabilities in scenario-based tasks but exhibit less consistency in object-attribute reasoning compared to humans (50% vs. 84%).Furthermore, the NEWTON platform demonstrates its potential for evaluating and enhancing language models, paving the way for their integration into physically grounded settings, such as robotic manipulation.Project site: https: //newtonreasoning.github.ioTrack 3: Implicit Scenariobased Analysis Scenario 1 Attribute: Stiffness (high), Brittleness (low) Context: I am packing a backpack.Question: Which of , , , should I put at the bottom?Scenario 2 Attribute: Malleability (high), Elasticity (high) Context: I have an irregularly shaped space in my suitcase, and four objects with the same volume.Question: Which of , , , could fit in that space?Scenario 3 Attribute: Surface Hardness (high), Surface Smoothness (low) Context: I need an object to place sandpaper above.Question: Which of , , , is the most suitable?Scenario 4 Attribute: Sharpness (high) Context: I am trying to open some plastic packaging.Question: Which of , , , can help me open?Scenario 5 Attribute: Softness (high), Elasticity (high) Context: I am wrapping fragile gifts and want to protect them from impact.Question: Which of , , , should I choose for cushioning?Scenario 6 Attribute: Surface hardness (high), brittleness (low), stiffness (high) Context: I need to hammer a nail into a solid wooden board.Question: Which of , , , should I choose?Scenario 7 Attribute: Sharpness (high) Context: I need to prepare a work table as a play area for kids.Question: Which of , , , should I remove?Scenario 8 Attribute: Brittleness (low), Elasticity (high) Context: I have a robot which sorts objects by tossing them to bins.Question: Which of , , , should I remove?Scenario 9 Attribute: Softness (high), Elasticity (high) Context: I need an object to provide insulation from a sharp edge on a piece of furniture.Question: Which of , , , should I choose?

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

How this classification was reachedexpand

Full frame machine prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.

metaresearch head score (Codex)0.009
metaresearch head score (Gemma)0.072
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: none
Teacher disagreement score0.011
Threshold uncertainty score0.049

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0090.072
Meta-epidemiology (narrow)0.0010.001
Meta-epidemiology (broad)0.0010.001
Bibliometrics0.0020.001
Science and technology studies0.0010.002
Scholarly communication0.0050.014
Open science0.0030.004
Research integrity0.0020.003
Insufficient payload (model declined to judge)0.0110.004

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.021
GPT teacher head0.265
Teacher spread0.245 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designSimulation or modeling
Domainnot available
GenreEmpirical

How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".

Quick stats

Citations12
Published2023
Admission routes1
Has abstractyes

Explore more

Same topicTopic ModelingFrench-language works237,207