Let the Model Distribute Its Doubt: Confidence Estimation through Verbalized Probability Distribution

ArXi:2511.14275v2 Announce Type: replace Knowing the reliability of a model's response is essential in practical applications. Given the strong generation capabilities of large language models (LLMs), research has focused on generating verbalized confidence. This approach is further enhanced by integrating chain-of-thought reasoning, which provides logical and transparent estimates. However, how reasoning strategies affect the estimated confidence remains under-explored.