Trustworthy Summarization via Uncertainty Quantification and Risk Awareness in Large Language Models
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866908572787408896 |
|---|---|
| author | Pan, Shuaidong Wu, Di |
| author_facet | Pan, Shuaidong Wu, Di |
| contents | This study addresses the reliability of automatic summarization in high-risk scenarios and proposes a large language model framework that integrates uncertainty quantification and risk-aware mechanisms. Starting from the demands of information overload and high-risk decision-making, a conditional generation-based summarization model is constructed, and Bayesian inference is introduced during generation to model uncertainty in the parameter space, which helps avoid overconfident predictions. The uncertainty level of the generated content is measured using predictive distribution entropy, and a joint optimization of entropy regularization and risk-aware loss is applied to ensure that key information is preserved and risk attributes are explicitly expressed during information compression. On this basis, the model incorporates risk scoring and regulation modules, allowing summaries to cover the core content accurately while enhancing trustworthiness through explicit risk-level prompts. Comparative experiments and sensitivity analyses verify that the proposed method significantly improves the robustness and reliability of summarization in high-risk applications while maintaining fluency and semantic integrity. This research provides a systematic solution for trustworthy summarization and demonstrates both scalability and practical value at the methodological level. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_01231 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Trustworthy Summarization via Uncertainty Quantification and Risk Awareness in Large Language Models Pan, Shuaidong Wu, Di Computation and Language Artificial Intelligence Machine Learning This study addresses the reliability of automatic summarization in high-risk scenarios and proposes a large language model framework that integrates uncertainty quantification and risk-aware mechanisms. Starting from the demands of information overload and high-risk decision-making, a conditional generation-based summarization model is constructed, and Bayesian inference is introduced during generation to model uncertainty in the parameter space, which helps avoid overconfident predictions. The uncertainty level of the generated content is measured using predictive distribution entropy, and a joint optimization of entropy regularization and risk-aware loss is applied to ensure that key information is preserved and risk attributes are explicitly expressed during information compression. On this basis, the model incorporates risk scoring and regulation modules, allowing summaries to cover the core content accurately while enhancing trustworthiness through explicit risk-level prompts. Comparative experiments and sensitivity analyses verify that the proposed method significantly improves the robustness and reliability of summarization in high-risk applications while maintaining fluency and semantic integrity. This research provides a systematic solution for trustworthy summarization and demonstrates both scalability and practical value at the methodological level. |
| title | Trustworthy Summarization via Uncertainty Quantification and Risk Awareness in Large Language Models |
| topic | Computation and Language Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2510.01231 |