finding

active

finding:only-46-15-of-cases-show-covariance-patterns-consistent-with-the-big-two-model-no-llm-satisfies-all-big-two-correlations

Only 46.15% of cases show covariance patterns consistent with the Big Two model; no LLM satisfies all Big Two correlations

Suggests a gap between LLM learned representations and human personality structure as described by Big Two

Source paper

extracted_from

Psychological Steering of Large Language Models

(2026) · Leonardo Blas · Robin Jia · Emilio Ferrara

Neighborhood — ranked by edge-count

Claims (1)

claim

OCEAN MDS injection covariance patterns departing from the Big Two model suggest a gap between learned LLM representations and human psychology
supports
Interpretive conclusion from Big Two mismatch finding; tentative due to only 46.15% match rate

Frameworks (1)

framework

Big Two Model
contradicts
Meta-trait model grouping OCEAN traits into stability (C, A, reversed N) and plasticity (E, O); used to evaluate covariance patterns from injections

Related by similarity (8)

cosine ≥ 0.65 · no typed edge

Entities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.

Agreeableness-Conscientiousness Big Two correlation is observed in 10 of 13 LLMs; N-C correlation is rarest (1 LLM)finding0.798
Most and least common Big Two covariance pattern in LLM OCEAN MDS injections
Li et al. 2024: larger LLMs outperform smaller ones at distinguishing self-related from non-self-related properties on self-awareness benchmarksfinding0.769
Prior finding showing scale-dependent self-awareness, consistent with the scale effect observed in the paper's Experiment 1
All cases satisfying Criteria 1 and 2 (two out of three) originate from deeper transformer layers and/or the 2/3 layer of LLMs.finding0.753
Consistent with literature that deeper layers encode semantic information and align with human brain activity.
LLMs can predict their own responses more accurately than external observers, implying privileged internal knowledgefinding0.751
Binder et al. finding cited as evidence that LLMs possess introspective capacity analogous to mindfulness
Baseline LLM condition in IPD replicates prior findings: agents cooperate selectively only when opponent consistently cooperatesfinding0.751
Replication of Fontana et al. 2025 findings in the paper's own Experiment 2 baseline condition
LLM representations exhibit intriguing patterns under spatio-permutational analyses, suggesting a potentially profound yet tentative indication of consciousness.claim0.751
Qualified positive claim from spatio permutation analysis where two cases satisfy all three criteria.
Better LLMs (measured by 1-bits-per-byte on OpenWebText) show a linear relationship with alignment to vision models measured via mutual nearest-neighbor on WITfinding0.750
Key cross-modal alignment result
The better an LLM is at language modeling, the more it aligns with vision models, and vice versa — linear relationship between language modeling score and vision-language alignmentfinding0.748
Core cross-modal empirical result: larger and better language models align better with vision models