Pith. sign in

REVIEW 1 cited by

Human Behavioral Benchmarking: Numeric Magnitude Comparison Effects in Large Language Models

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 2305.10782 v3 pith:4C7DDSAT submitted 2023-05-18 cs.AI

classification cs.AI
keywords llmsrepresentationshumanlanguagebehavioralmodelsnumbernumbers
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
abstract

Large Language Models (LLMs) do not differentially represent numbers, which are pervasive in text. In contrast, neuroscience research has identified distinct neural representations for numbers and words. In this work, we investigate how well popular LLMs capture the magnitudes of numbers (e.g., that $4 < 5$) from a behavioral lens. Prior research on the representational capabilities of LLMs evaluates whether they show human-level performance, for instance, high overall accuracy on standard benchmarks. Here, we ask a different question, one inspired by cognitive science: How closely do the number representations of LLMscorrespond to those of human language users, who typically demonstrate the distance, size, and ratio effects? We depend on a linking hypothesis to map the similarities among the model embeddings of number words and digits to human response times. The results reveal surprisingly human-like representations across language models of different architectures, despite the absence of the neural circuitry that directly supports these representations in the human brain. This research shows the utility of understanding LLMs using behavioral benchmarks and points the way to future work on the number representations of LLMs and their cognitive plausibility.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 1 Pith paper

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

  1. The potential -- and the pitfalls -- of using pre-trained language models as cognitive science theories

    cs.CL 2025-01 accept novelty 4.0 of 10

    Pretrained language models can serve as credible cognitive science theories only if researchers validate linking hypotheses and avoid pitfalls of commission and omission.

Pith tools