Verbal confidence in LLMs tracks future commit/abstain decisions more than answer correctness, while log-probabilities track correctness.
How do LLMs Compute Verbal Confidence
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
abstract
Verbal confidence -- prompting LLMs to state their confidence as a number or category -- is widely used to extract uncertainty estimates from black-box models. However, how LLMs internally generate such scores remains unknown. We address two questions: first, when confidence is computed -- just-in-time when requested, or automatically during answer generation and cached for later retrieval; and second, what verbal confidence represents -- token log-probabilities, or a richer evaluation of answer quality? Focusing on Gemma 3 27B (across TriviaQA, BigMath, and MMLU), Qwen 2.5 7B, and the reasoning model Magistral Small 24B, we provide convergent evidence for cached retrieval. Activation steering, patching, noising, and swap experiments reveal that confidence representations emerge at answer-adjacent positions before appearing at the verbalization site. Attention blocking pinpoints the information flow: confidence is gathered from answer tokens, cached at the first post-answer position, then retrieved for output. Critically, linear probing and variance partitioning reveal that these cached representations explain substantial variance in verbal confidence beyond token log-probabilities, suggesting a richer answer-quality evaluation rather than a simple fluency readout. These findings demonstrate that verbal confidence reflects automatic, sophisticated self-evaluation -- not post-hoc reconstruction -- with implications for understanding metacognition in LLMs and improving calibration.
citation-role summary
background 1
citation-polarity summary
years
2026 7roles
background 1polarities
background 1representative citing papers
VerifySteer selectively steers hidden states at paragraph boundaries using latent correctness signals to control verifier strictness and outperform baselines on ProcessBench and Hard2Verify with lower compute.
METIS internalizes curriculum judgment in LLM reinforcement fine-tuning by predicting within-prompt reward variance via in-context learning and jointly optimizing with a self-judgment reward, yielding superior performance and up to 67% faster convergence across math, code, and agent benchmarks.
LLMs exhibit Bayesian-like hypothesis updating with strong-sampling bias and an evaluation-generation gap but generalize poorly outside observed data.
LLMs implement a second-order confidence architecture where the PANL activation encodes both error likelihood and the ability to correct it, beyond verbal confidence or log-probabilities.
Seven 3-9B instruction-tuned LLMs produce verbal confidence that saturates at high values and fails psychometric validity criteria for Type-2 discrimination under minimal elicitation.
Fine-tuning Gemma 3 4B on unfiltered self-consistency targets produces a binary verbal correctness discriminator with AUROC 0.774 on TriviaQA, outperforming logit entropy after a modal-filtered pre-registration failed.
citing papers explorer
-
Internalizing Curriculum Judgment for LLM Reinforcement Fine-Tuning
METIS internalizes curriculum judgment in LLM reinforcement fine-tuning by predicting within-prompt reward variance via in-context learning and jointly optimizing with a self-judgment reward, yielding superior performance and up to 67% faster convergence across math, code, and agent benchmarks.