SAUP: Situation Awareness Uncertainty Propagation on LLM Agent
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866917853371826176 |
|---|---|
| author | Zhao, Qiwei Zhao, Xujiang Liu, Yanchi Cheng, Wei Sun, Yiyou Oishi, Mika Osaki, Takao Matsuda, Katsushi Yao, Huaxiu Chen, Haifeng |
| author_facet | Zhao, Qiwei Zhao, Xujiang Liu, Yanchi Cheng, Wei Sun, Yiyou Oishi, Mika Osaki, Takao Matsuda, Katsushi Yao, Huaxiu Chen, Haifeng |
| contents | Large language models (LLMs) integrated into multistep agent systems enable complex decision-making processes across various applications. However, their outputs often lack reliability, making uncertainty estimation crucial. Existing uncertainty estimation methods primarily focus on final-step outputs, which fail to account for cumulative uncertainty over the multistep decision-making process and the dynamic interactions between agents and their environments. To address these limitations, we propose SAUP (Situation Awareness Uncertainty Propagation), a novel framework that propagates uncertainty through each step of an LLM-based agent's reasoning process. SAUP incorporates situational awareness by assigning situational weights to each step's uncertainty during the propagation. Our method, compatible with various one-step uncertainty estimation techniques, provides a comprehensive and accurate uncertainty measure. Extensive experiments on benchmark datasets demonstrate that SAUP significantly outperforms existing state-of-the-art methods, achieving up to 20% improvement in AUROC. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_01033 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | SAUP: Situation Awareness Uncertainty Propagation on LLM Agent Zhao, Qiwei Zhao, Xujiang Liu, Yanchi Cheng, Wei Sun, Yiyou Oishi, Mika Osaki, Takao Matsuda, Katsushi Yao, Huaxiu Chen, Haifeng Computation and Language Machine Learning Large language models (LLMs) integrated into multistep agent systems enable complex decision-making processes across various applications. However, their outputs often lack reliability, making uncertainty estimation crucial. Existing uncertainty estimation methods primarily focus on final-step outputs, which fail to account for cumulative uncertainty over the multistep decision-making process and the dynamic interactions between agents and their environments. To address these limitations, we propose SAUP (Situation Awareness Uncertainty Propagation), a novel framework that propagates uncertainty through each step of an LLM-based agent's reasoning process. SAUP incorporates situational awareness by assigning situational weights to each step's uncertainty during the propagation. Our method, compatible with various one-step uncertainty estimation techniques, provides a comprehensive and accurate uncertainty measure. Extensive experiments on benchmark datasets demonstrate that SAUP significantly outperforms existing state-of-the-art methods, achieving up to 20% improvement in AUROC. |
| title | SAUP: Situation Awareness Uncertainty Propagation on LLM Agent |
| topic | Computation and Language Machine Learning |
| url | https://arxiv.org/abs/2412.01033 |