Pith. sign in

REVIEW 1 cited by

Probing Large Language Models from A Human Behavioral Perspective

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 2310.05216 v2 pith:C5ZHDBTP submitted 2023-10-08 cs.CL

classification cs.CL
keywords llmsmodelshumanlanguagebehaviorallargelayersmhsa
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

Large Language Models (LLMs) have emerged as dominant foundational models in modern NLP. However, the understanding of their prediction processes and internal mechanisms, such as feed-forward networks (FFN) and multi-head self-attention (MHSA), remains largely unexplored. In this work, we probe LLMs from a human behavioral perspective, correlating values from LLMs with eye-tracking measures, which are widely recognized as meaningful indicators of human reading patterns. Our findings reveal that LLMs exhibit a similar prediction pattern with humans but distinct from that of Shallow Language Models (SLMs). Moreover, with the escalation of LLM layers from the middle layers, the correlation coefficients also increase in FFN and MHSA, indicating that the logits within FFN increasingly encapsulate word semantics suitable for predicting tokens from the vocabulary.

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. How Multimodal LLMs Solve Image Tasks: A Lens on Visual Grounding, Task Reasoning, and Answer Decoding

    cs.CV 2025-08 conditional novelty 6.0 of 10

    Probing layer-wise embeddings with three prompt-variant families reveals a consistent grounding-reasoning-decoding structure in LLaVA-1.5, LLaVA-Next, and Qwen2-VL, with base LLM architecture shifting layer allocation.

Pith tools