| license: apache-2.0 | |
| datasets: | |
| - RUC-NLPIR/FlashRAG_datasets | |
| language: | |
| - en | |
| metrics: | |
| - f1 | |
| - recall | |
| base_model: | |
| - Qwen/Qwen2.5-3B-Instruct | |
| pipeline_tag: question-answering | |
| tags: | |
| - ambiguity | |
| - reinforcement-learning | |
| - agent | |
| - This repository contains the RL-trained model accompanying our paper, A^2Search: Ambiguity-Aware Question Answering with Reinforcement Learning. More details are available at https://github.com/zfj1998/A2Search |