EPS Dashboard

Authors: Jon-Paul Cacioli

Summary

This paper tested how well 33 frontier language models know when they're right or wrong (metacognition) across six different knowledge domains from the MMLU benchmark. The author gave models 1,500 questions, asked them to rate their confidence (0-100), and measured whether high confidence actually predicted correct answers. Every model showed big variation across domains — models were consistently good at monitoring their accuracy on applied/professional knowledge but struggled with formal reasoning and natural science.

Main takeaways:

All models with above-chance metacognition showed significant domain-to-domain variation that aggregate scores hide
Applied/Professional knowledge was easiest to monitor (mean AUROC = 0.742, top-2 in 21/33 models); Formal Reasoning and Natural Science were hardest (bottom-2 in 27/33 models)
Some model families (Anthropic, Gemini, Qwen) show consistent within-family patterns in which domains are hard vs. easy, while others (DeepSeek, Gemma, OpenAI) don't
Three models that failed on binary yes/no confidence probes worked fine when asked for 0-100 scores, showing that the prompt format matters a lot
Gemma 4 31B showed a massive +0.202 AUROC improvement over Gemma 3 27B, suggesting newer models are getting better at knowing what they know

Relevance

Tangential but potentially useful — if personas have different "profiles" of what they're confident about (like these domain-level monitoring patterns), that could be a fingerprint for detecting persona-conditional behavior or measuring whether a persona has successfully installed. Not directly about my marker implantation work, but could be a diagnostic tool.

Threat model

Potential threat/caveat for clean result "A pretraining-data-poisoned Qwen3-4B backdoor only fires on the exact trigger tokens — paraphrases don't activate it, and base-model similarity to the trigger doesn't predict which inputs fire (MODERATE confidence)": this item discusses benchmark.

Abstract

arXiv:2605.06673v1 Announce Type: new Abstract: Aggregate metacognitive quality scores mask within-model variation across MMLU benchmark domains. We administered 1,500 MMLU items (250 per domain, under an a priori six-domain grouping) to 33 frontier LLMs from eight model families and computed Type-2 AUROC per model-domain cell using verbalized confidence (0-100). Total observations: 47,151. Every model with above-chance aggregate monitoring showed non-trivial domain-level variation. Applied/Professional knowledge was reliably the easiest benchmark domain to monitor (mean AUROC = .742, ranked top-2 in 21 of 33 models); Formal Reasoning and Natural Science were reliably the hardest (one of the two ranked bottom-2 in 27 of 33 models). The three middle domains were statistically indistinguishable (Kendall's W = .164). A subject-level coherence analysis (within-domain similarity ratio = 0.95) confirms the six-domain grouping is a pragmatic benchmark taxonomy, not a validated latent construct. Within-family profile-shape clustering is significant for Anthropic, Google-Gemini, and Qwen (permutation p < .0001) but not DeepSeek, Google-Gemma, or OpenAI. Gemma 4 31B showed a +.202 AUROC improvement over Gemma 3 27B. Three models classified Invalid on binary KEEP/WITHDRAW probes produced normal profiles under verbalized confidence, confirming probe-format specificity. Bootstrap 95% CIs on 198 cells have median width .199. Split-half aggregate stability r = .893; profile-level split-half is weaker (grand median r = .184). These results show stable benchmark-domain variation obscured by aggregate metrics, and support benchmark-stage domain screening as a step before deployment in specific application areas.