Open Access

Outputs for Fine-Tuning with Divergent Chains of Thought Boosts Reasoning Through Self-Correction in Language Models

Files

outputs.zip (846.4 MB)

Date

2024-06-21

Type

Dataset

Authors

Puerto, Haritz

Chubakov, Tilek
Zhu, Xiaodan
Tayyar Madabushi, Harish

Gurevych, Iryna

Description

Raw responses from the models, clean answers, post-processed predictions and evaluation results for each model and dataset using in the publication Fine-Tuning with Divergent Chains of Thought Boosts Reasoning Through Self-Correction in Language Models

Keywords

chain of thought, cot, large language model, llm, NLP

Identifier

https://tudatalib.ulb.tu-darmstadt.de/handle/tudatalib/4266

DFG Classification

4.43-04 Künstliche Intelligenz und Maschinelle Lernverfahren
4.43-05 Bild- und Sprachverarbeitung, Computergraphik und Visualisierung, Human Computer Interaction, Ubiquitous und Wearable Computing

License

Except where otherwise noted, this license is described as CC BY-SA 3.0

Full item page

Outputs for Fine-Tuning with Divergent Chains of Thought Boosts Reasoning Through Self-Correction in Language Models

Files

Date

Type

Authors

Journal Title

Journal ISSN

Volume Title

Publisher

Abstract

Description

Keywords

Citation

Identifier

Endorsement

DFG Classification

Project(s)

Faculty

Collections

License