finding

active

finding:focus-concept-spearman-0-40-isotonic-r2-0-12-in-llama-3-2-3b-n-400-p-10-5

Focus concept: Spearman ρ=0.40, isotonic R²=0.12 in LLaMA-3.2-3B (n=400, p<10⁻⁵)

Weakest but still significant pooled introspective coupling in primary model

Source paper

extracted_from

Quantitative Introspection in Language Models: Tracking Emotive States Across Conversation

(2026) · Nicolas Martorell · Bianchi, Bruno

Neighborhood — ranked by edge-count

Claims (1)

claim

Numeric self-report is a viable, complementary black-box tool for monitoring LLM internal emotive states alongside white-box probe methods
supports
Central practical conclusion; both methods partially track the same latent state but with different failure modes

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.

Interest concept: Spearman ρ=0.76, isotonic R²=0.54 between logit self-report and probe score in LLaMA-3.2-3B (n=400)finding0.896
Strongest pooled introspective coupling across the four emotive concepts in the primary model
Impulsivity concept: Spearman ρ=0.51, isotonic R²=0.31 in LLaMA-3.2-3B (n=400, p<10⁻¹²)finding0.885
Third-strongest pooled introspective coupling in primary model
Wellbeing concept: Spearman ρ=0.68, isotonic R²=0.48 in LLaMA-3.2-3B (n=400, p<10⁻²⁶)finding0.860
Second-strongest pooled introspective coupling in primary model
Focus→wellbeing: ρ increases from 0.42 (α=-4) to 0.85 (α=+4); R² from 0.34 to 0.75 in LLaMA-3.2-3Bfinding0.828
Scatter plot visualization of the dramatic tightening of probe-report relationship at extreme steering settings
LLaMA-3.1-8B-Instruct wellbeing introspection: ρ=0.93, isotonic R²=0.90 (LMM probe slope p<10⁻¹⁰)finding0.798
Near-ceiling introspective performance for wellbeing concept in 8B model; nearly deterministic probe-report relationship
Cross-concept steering: focus→wellbeing R² increases from 0.30 (α=-4) to 0.76 (α=+4), ∆R²=0.30, p<0.001 in LLaMA-3.2-3Bfinding0.796
Strongest cross-concept introspection improvement; survives BH correction (q≈0.011)
LLaMA-3.2-1B impulsivity introspection: ρ=0.21, p<10⁻⁴ (significant but weaker than 3B ρ=0.52)finding0.777
Impulsivity shows significant introspection in 1B but declines in 8B; non-monotonic scaling
Wellbeing same-concept steering: LMM alpha slope=0.19, focus=0.40, interest=0.25, impulsivity=0.067 in LLaMA-3.2-3Bfinding0.773
Quantifies per-concept effect size of same-concept steering on self-report