DebUnc: Improving Large Language Model Agent Communication With Uncertainty Metrics
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_ | 1866929725446815744 |
|---|---|
| author | Yoffe, Luke Amayuelas, Alfonso Wang, William Yang |
| author_facet | Yoffe, Luke Amayuelas, Alfonso Wang, William Yang |
| contents | Multi-agent debates have been introduced to improve the accuracy of Large Language Models (LLMs) by having multiple agents discuss solutions to a problem over several rounds of debate. However, models often generate incorrect yet confident-sounding responses, which can mislead others. This issue arises partly because agents do not consider how confident their peers are. To address this, we propose DebUnc, a debate framework that uses uncertainty metrics to assess agent confidence. Confidence is then conveyed through a modified attention mechanism that adjusts token weights, or through textual prompts. Evaluations across benchmarks show that attention-based methods are particularly effective and that performance continues to improve as uncertainty estimation becomes more reliable. The code is available at https://github.com/lukeyoffe/debunc. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_06426 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | DebUnc: Improving Large Language Model Agent Communication With Uncertainty Metrics Yoffe, Luke Amayuelas, Alfonso Wang, William Yang Computation and Language Artificial Intelligence Multiagent Systems Multi-agent debates have been introduced to improve the accuracy of Large Language Models (LLMs) by having multiple agents discuss solutions to a problem over several rounds of debate. However, models often generate incorrect yet confident-sounding responses, which can mislead others. This issue arises partly because agents do not consider how confident their peers are. To address this, we propose DebUnc, a debate framework that uses uncertainty metrics to assess agent confidence. Confidence is then conveyed through a modified attention mechanism that adjusts token weights, or through textual prompts. Evaluations across benchmarks show that attention-based methods are particularly effective and that performance continues to improve as uncertainty estimation becomes more reliable. The code is available at https://github.com/lukeyoffe/debunc. |
| title | DebUnc: Improving Large Language Model Agent Communication With Uncertainty Metrics |
| topic | Computation and Language Artificial Intelligence Multiagent Systems |
| url | https://arxiv.org/abs/2407.06426 |