How do LLMs Compute Verbal Confidence
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Answer GenerationSimilar Papers 제목 키워드 기반
On the Robustness of Verbal Confidence of LLMs in Adversarial Attacks
Robust verbal confidence generated by large language models (LLMs) is crucial for the deployment of LLMs to help ensure transparency, trust, and safety in many applications, including those involving human-AI interaction…
Wired for Overconfidence: A Mechanistic Perspective on Inflated Verbalized Confidence in LLMs
Large language models are often not just wrong, but \emph{confidently wrong}: when they produce factually incorrect answers, they tend to verbalize overly high confidence rather than signal uncertainty. Such verbalized o…
Are Large Language Models More Honest in Their Probabilistic or Verbalized Confidence?
Large language models (LLMs) have been found to produce hallucinations when the question exceeds their internal knowledge boundaries. A reliable model should have a clear perception of its knowledge boundaries, providing…
Uncertainty Distillation: Teaching Language Models to Express Semantic Confidence
As large language models (LLMs) are increasingly used for factual question-answering, it becomes more important for LLMs to have the capability to communicate the likelihood that their answer is correct. For these verbal…
Question AnsweringUncertainty QuantificationInfluential Training Data Retrieval for Explaining Verbalized Confidence of LLMs
Large language models (LLMs) can increase users' perceived trust by verbalizing confidence in their outputs. However, prior work has shown that LLMs are often overconfident, making their stated confidence unreliable sinc…
Information RetrievalQuestion Answering