Enhancing Confidence Expression in Large Language Models Through Learning from Past Experience
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_ | 1866911842080653312 |
|---|---|
| author | Han, Haixia Li, Tingyun Chen, Shisong Shi, Jie Du, Chengyu Xiao, Yanghua Liang, Jiaqing Lin, Xin |
| author_facet | Han, Haixia Li, Tingyun Chen, Shisong Shi, Jie Du, Chengyu Xiao, Yanghua Liang, Jiaqing Lin, Xin |
| contents | Large Language Models (LLMs) have exhibited remarkable performance across various downstream tasks, but they may generate inaccurate or false information with a confident tone. One of the possible solutions is to empower the LLM confidence expression capability, in which the confidence expressed can be well-aligned with the true probability of the generated answer being correct. However, leveraging the intrinsic ability of LLMs or the signals from the output logits of answers proves challenging in accurately capturing the response uncertainty in LLMs. Therefore, drawing inspiration from cognitive diagnostics, we propose a method of Learning from Past experience (LePe) to enhance the capability for confidence expression. Specifically, we first identify three key problems: (1) How to capture the inherent confidence of the LLM? (2) How to teach the LLM to express confidence? (3) How to evaluate the confidence expression of the LLM? Then we devise three stages in LePe to deal with these problems. Besides, to accurately capture the confidence of an LLM when constructing the training data, we design a complete pipeline including question preparation and answer sampling. We also conduct experiments using the Llama family of LLMs to verify the effectiveness of our proposed method on four datasets. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_10315 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Enhancing Confidence Expression in Large Language Models Through Learning from Past Experience Han, Haixia Li, Tingyun Chen, Shisong Shi, Jie Du, Chengyu Xiao, Yanghua Liang, Jiaqing Lin, Xin Computation and Language Large Language Models (LLMs) have exhibited remarkable performance across various downstream tasks, but they may generate inaccurate or false information with a confident tone. One of the possible solutions is to empower the LLM confidence expression capability, in which the confidence expressed can be well-aligned with the true probability of the generated answer being correct. However, leveraging the intrinsic ability of LLMs or the signals from the output logits of answers proves challenging in accurately capturing the response uncertainty in LLMs. Therefore, drawing inspiration from cognitive diagnostics, we propose a method of Learning from Past experience (LePe) to enhance the capability for confidence expression. Specifically, we first identify three key problems: (1) How to capture the inherent confidence of the LLM? (2) How to teach the LLM to express confidence? (3) How to evaluate the confidence expression of the LLM? Then we devise three stages in LePe to deal with these problems. Besides, to accurately capture the confidence of an LLM when constructing the training data, we design a complete pipeline including question preparation and answer sampling. We also conduct experiments using the Llama family of LLMs to verify the effectiveness of our proposed method on four datasets. |
| title | Enhancing Confidence Expression in Large Language Models Through Learning from Past Experience |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2404.10315 |