Mind the Generation Process: Fine-Grained Confidence Estimation During LLM Generation
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866916902806224896 |
|---|---|
| author | Han, Jinyi Li, Tingyun Chen, Shisong Shi, Jie Wang, Xinyi Yue, Guanglei Liang, Jiaqing Lin, Xin Wen, Liqian Chen, Zulong Xiao, Yanghua |
| author_facet | Han, Jinyi Li, Tingyun Chen, Shisong Shi, Jie Wang, Xinyi Yue, Guanglei Liang, Jiaqing Lin, Xin Wen, Liqian Chen, Zulong Xiao, Yanghua |
| contents | While large language models (LLMs) have demonstrated remarkable performance across diverse tasks, they fundamentally lack self-awareness and frequently exhibit overconfidence, assigning high confidence scores to incorrect predictions. Accurate confidence estimation is therefore critical for enhancing the trustworthiness and reliability of LLM-generated outputs. However, existing approaches suffer from coarse-grained scoring mechanisms that fail to provide fine-grained, continuous confidence estimates throughout the generation process. To address these limitations, we introduce FineCE, a novel confidence estimation method that delivers accurate, fine-grained confidence scores during text generation. Specifically, we first develop a comprehensive pipeline for constructing training data that effectively captures the underlying probabilistic distribution of LLM responses, and then train a model to predict confidence scores for arbitrary text sequences in a supervised manner. Furthermore, we propose a Backward Confidence Integration (BCI) strategy that leverages information from the subsequent text to enhance confidence estimation for the current sequence during inference. We also introduce three strategies for identifying optimal positions to perform confidence estimation within the generation process. Extensive experiments on multiple benchmark datasets demonstrate that FineCE consistently outperforms existing classical confidence estimation methods. Our code and all baselines used in the paper are available on GitHub. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_12040 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Mind the Generation Process: Fine-Grained Confidence Estimation During LLM Generation Han, Jinyi Li, Tingyun Chen, Shisong Shi, Jie Wang, Xinyi Yue, Guanglei Liang, Jiaqing Lin, Xin Wen, Liqian Chen, Zulong Xiao, Yanghua Computation and Language Artificial Intelligence While large language models (LLMs) have demonstrated remarkable performance across diverse tasks, they fundamentally lack self-awareness and frequently exhibit overconfidence, assigning high confidence scores to incorrect predictions. Accurate confidence estimation is therefore critical for enhancing the trustworthiness and reliability of LLM-generated outputs. However, existing approaches suffer from coarse-grained scoring mechanisms that fail to provide fine-grained, continuous confidence estimates throughout the generation process. To address these limitations, we introduce FineCE, a novel confidence estimation method that delivers accurate, fine-grained confidence scores during text generation. Specifically, we first develop a comprehensive pipeline for constructing training data that effectively captures the underlying probabilistic distribution of LLM responses, and then train a model to predict confidence scores for arbitrary text sequences in a supervised manner. Furthermore, we propose a Backward Confidence Integration (BCI) strategy that leverages information from the subsequent text to enhance confidence estimation for the current sequence during inference. We also introduce three strategies for identifying optimal positions to perform confidence estimation within the generation process. Extensive experiments on multiple benchmark datasets demonstrate that FineCE consistently outperforms existing classical confidence estimation methods. Our code and all baselines used in the paper are available on GitHub. |
| title | Mind the Generation Process: Fine-Grained Confidence Estimation During LLM Generation |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2508.12040 |