Calibrated few-shot prompting was a surprisingly weak baseline for truth classification compared to linear probes

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

• System prompting and few-shot produce highly similar activations (cosine 0.83-0.92 at safety-critical layers), indicating a shared prompt-side mechanism distinct from activation steering.claim0.814
  Evidence for two representational pathways based on cross-method activation divergence
• few-shot promptingmethod0.811
  Providing k labeled examples in the prompt to steer model behavior.
• Few-shot thresholds and transition widths track ρd/dr at fixed computational complexityclaim0.793
  E2 main interpretive claim.
• Few-shot linear probe steering baselinemethod0.791
  Constructing steering vectors from the difference of mean activations on positive and negative examples, for comparison.
• LLMs linearly represent truth-relevant information beyond the plausibility of text, as evidenced by probes trained on likely performing poorly on anti-correlated datasetsclaim0.778
  Establishes that the observed linear structure is not merely a representation of text probability
• Chain-of-thought prompting produced a similar increase in helpful intention of large models as few-shot prompting.finding0.775
  Ablation result from Experiment 3 on chain-of-thought prompting effects.
• Few-shot prompting had a negative effect on HH-intent for smaller models and a significant positive impact on larger models.finding0.774
  Ablation result from Experiment 3 on few-shot prompting effects.
• The ordering of few-shot thresholds k50 and transition widths aligns with k50 ∝ dr/ρd.claim0.761
  Interpretation of E2 results.