MARS: Meaning-Aware Response Scoring for Uncertainty Estimation in Generative LLMs
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866910823364952064 |
|---|---|
| author | Bakman, Yavuz Faruk Yaldiz, Duygu Nur Buyukates, Baturalp Tao, Chenyang Dimitriadis, Dimitrios Avestimehr, Salman |
| author_facet | Bakman, Yavuz Faruk Yaldiz, Duygu Nur Buyukates, Baturalp Tao, Chenyang Dimitriadis, Dimitrios Avestimehr, Salman |
| contents | Generative Large Language Models (LLMs) are widely utilized for their excellence in various tasks. However, their tendency to produce inaccurate or misleading outputs poses a potential risk, particularly in high-stakes environments. Therefore, estimating the correctness of generative LLM outputs is an important task for enhanced reliability. Uncertainty Estimation (UE) in generative LLMs is an evolving domain, where SOTA probability-based methods commonly employ length-normalized scoring. In this work, we propose Meaning-Aware Response Scoring (MARS) as an alternative to length-normalized scoring for UE methods. MARS is a novel scoring function that considers the semantic contribution of each token in the generated sequence in the context of the question. We demonstrate that integrating MARS into UE methods results in a universal and significant improvement in UE performance. We conduct experiments using three distinct closed-book question-answering datasets across five popular pre-trained LLMs. Lastly, we validate the efficacy of MARS on a Medical QA dataset. Code can be found https://github.com/Ybakman/LLM_Uncertainity. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_11756 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | MARS: Meaning-Aware Response Scoring for Uncertainty Estimation in Generative LLMs Bakman, Yavuz Faruk Yaldiz, Duygu Nur Buyukates, Baturalp Tao, Chenyang Dimitriadis, Dimitrios Avestimehr, Salman Computation and Language Machine Learning Generative Large Language Models (LLMs) are widely utilized for their excellence in various tasks. However, their tendency to produce inaccurate or misleading outputs poses a potential risk, particularly in high-stakes environments. Therefore, estimating the correctness of generative LLM outputs is an important task for enhanced reliability. Uncertainty Estimation (UE) in generative LLMs is an evolving domain, where SOTA probability-based methods commonly employ length-normalized scoring. In this work, we propose Meaning-Aware Response Scoring (MARS) as an alternative to length-normalized scoring for UE methods. MARS is a novel scoring function that considers the semantic contribution of each token in the generated sequence in the context of the question. We demonstrate that integrating MARS into UE methods results in a universal and significant improvement in UE performance. We conduct experiments using three distinct closed-book question-answering datasets across five popular pre-trained LLMs. Lastly, we validate the efficacy of MARS on a Medical QA dataset. Code can be found https://github.com/Ybakman/LLM_Uncertainity. |
| title | MARS: Meaning-Aware Response Scoring for Uncertainty Estimation in Generative LLMs |
| topic | Computation and Language Machine Learning |
| url | https://arxiv.org/abs/2402.11756 |