Meta-Reasoning Improves Tool Use in Large Language Models
Fuente:
arXiv
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916958516019200 |
|---|---|
| author | Alazraki, Lisa Rei, Marek |
| author_facet | Alazraki, Lisa Rei, Marek |
| contents | External tools help large language models succeed at tasks where they would otherwise typically fail. In existing frameworks, choosing tools at test time relies on naive greedy decoding, regardless of whether the model has been fine-tuned on tool-annotated data or prompted with in-context examples. In contrast, we find that gathering and choosing among a suitable set of candidate tools has greater potential to lead to an optimal selection. We present Tool selECTion via meta-reasONing (TECTON), a two-phase system that first reasons over a task and outputs candidate tools using a custom fine-tuned language modelling head. Then, with the custom head disabled, it meta-reasons (i.e., it reasons over the previous reasoning process) to make a final choice. We show that TECTON results in substantial gains--both in-distribution and out-of-distribution--on a range of math reasoning datasets. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2411_04535 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Meta-Reasoning Improves Tool Use in Large Language Models Alazraki, Lisa Rei, Marek Computation and Language Artificial Intelligence External tools help large language models succeed at tasks where they would otherwise typically fail. In existing frameworks, choosing tools at test time relies on naive greedy decoding, regardless of whether the model has been fine-tuned on tool-annotated data or prompted with in-context examples. In contrast, we find that gathering and choosing among a suitable set of candidate tools has greater potential to lead to an optimal selection. We present Tool selECTion via meta-reasONing (TECTON), a two-phase system that first reasons over a task and outputs candidate tools using a custom fine-tuned language modelling head. Then, with the custom head disabled, it meta-reasons (i.e., it reasons over the previous reasoning process) to make a final choice. We show that TECTON results in substantial gains--both in-distribution and out-of-distribution--on a range of math reasoning datasets. |
| title | Meta-Reasoning Improves Tool Use in Large Language Models |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2411.04535 |