ConvFinQA

# Adapting Large Language Models to Domains via Continual Pre-Training
This repo contains the **ConvFinQA dataset** used in our **ICLR 2024** paper [Adapting Large Language Models via Reading Comprehension](https://huggingface.co/papers/2309.09530).

We explore **continued pre-training on domain-specific corpora** for large language models. While this approach enriches LLMs with domain knowledge, it significantly hurts their prompting ability for question answering. Inspired by human learning via reading comprehension, we propose a simple method to **transform large-scale pre-training corpora into reading comprehension texts**, consistently improving prompting performance across tasks in biomedicine, finance, and law domains. **Our 7B model competes with much larger domain-specific models like BloombergGPT-50B**.

### [2024/11/29] 🤗 Introduce the multimodal version of AdaptLLM at [AdaMLLM](https://huggingface.co/AdaptLLM/Adapt-MLLM-to-Domains), for adapting MLLMs to domains 🤗

**************************** **Updates** ****************************
* 2024/11/29: Released [AdaMLLM](https://huggingface.co/AdaptLLM/Adapt-MLLM-to-Domains) for adapting MLLMs to domains
* 2024/9/20: Our [research paper for Instruction-Pretrain](https://huggingface.co/papers/2406.14491) has been accepted by EMNLP 2024
* 2024/8/29: Updated [guidelines](https://huggingface.co/datasets/AdaptLLM/finance-tasks) on evaluating any 🤗Huggingface models on the domain-specific tasks
* 2024/6/22: Released the [benchmarking code](https://github.com/microsoft/LMOps/tree/main/adaptllm)
* 2024/6/21: Released the general version of AdaptLLM at [Instruction-Pretrain](https://huggingface.co/instruction-pretrain)
* 2024/4/2: Released the [raw data splits (train and test)](https://huggingface.co/datasets/AdaptLLM/ConvFinQA) of all the evaluation datasets
* 2024/1/16: Our [research paper for AdaptLLM](https://huggingface.co/papers/2309.09530) has been accepted by ICLR 2024
* 2023/12/19: Released our [13B base models](https://huggingface.co/AdaptLLM/law-LLM-13B) developed from LLaMA-1-13B
* 2023/12/8: Released our [chat models](https://huggingface.co/AdaptLLM/law-chat) developed from LLaMA-2-Chat-7B
* 2023/9/18: Released our [paper](https://huggingface.co/papers/2309.09530), [code](https://github.com/microsoft/LMOps), [data](https://huggingface.co/datasets/AdaptLLM/law-tasks), and [base models](https://huggingface.co/AdaptLLM/law-LLM) developed from LLaMA-1-7B

## Domain-Specific LLaMA-1
### LLaMA-1-7B
In our paper, we develop three domain-specific models from LLaMA-1-7B, which are also available in Huggingface: [Biomedicine-LLM](https://huggingface.co/AdaptLLM/medicine-LLM), [Finance-LLM](https://huggingface.co/AdaptLLM/finance-LLM) and [Law-LLM](https://huggingface.co/AdaptLLM/law-LLM), the performances of our AdaptLLM compared to other domain-specific LLMs are:

<p align='center'>
<img src="https://cdn-uploads.huggingface.co/production/uploads/650801ced5578ef7e20b33d4/6efPwitFgy-pLTzvccdcP.png" width="700">
</p>

### LLaMA-1-13B
Moreover, we scale up our base model to LLaMA-1-13B to see if **our method is similarly effective for larger-scale models**, and the results are consistently positive too: [Biomedicine-LLM-13B](https://huggingface.co/AdaptLLM/medicine-LLM-13B), [Finance-LLM-13B](https://huggingface.co/AdaptLLM/finance-LLM-13B) and [Law-LLM-13B](https://huggingface.co/AdaptLLM/law-LLM-13B).

## Domain-Specific LLaMA-2-Chat
Our method is also effective for aligned models! LLaMA-2-Chat requires a [specific data format](https://huggingface.co/blog/llama2#how-to-prompt-llama-2), and our **reading comprehension can perfectly fit the data format** by transforming the reading comprehension into a multi-turn conversation. We have also open-sourced chat models in different domains: [Biomedicine-Chat](https://huggingface.co/AdaptLLM/medicine-chat), [Finance-Chat](https://huggingface.co/AdaptLLM/finance-chat) and [Law-Chat](https://huggingface.co/AdaptLLM/law-chat)

## Domain-Specific Tasks

### Pre-templatized/Formatted Testing Splits
To easily reproduce our prompting results, we have uploaded the filled-in zero/few-shot input instructions and output completions of the test each domain-specific task: [biomedicine-tasks](https://huggingface.co/datasets/AdaptLLM/medicine-tasks), [finance-tasks](https://huggingface.co/datasets/AdaptLLM/finance-tasks), and [law-tasks](https://huggingface.co/datasets/AdaptLLM/law-tasks).

**Note:** those filled-in instructions are specifically tailored for models before alignment and do NOT fit for the specific data format required for chat models.

### Raw Datasets
We have also uploaded the raw training and testing splits, for facilitating fine-tuning or other usages:
- [ChemProt](https://huggingface.co/datasets/AdaptLLM/ChemProt)
- [RCT](https://huggingface.co/datasets/AdaptLLM/RCT)
- [ConvFinQA](https://huggingface.co/datasets/AdaptLLM/ConvFinQA)
- [FiQA_SA](https://huggingface.co/datasets/AdaptLLM/FiQA_SA)
- [Headline](https://huggingface.co/datasets/AdaptLLM/Headline)
- [NER](https://huggingface.co/datasets/AdaptLLM/NER)
- [FPB](https://huggingface.co/datasets/AdaptLLM/FPB)

The other datasets used in our paper have already been available in huggingface, and you can directly load them with the following code:
```python
from datasets import load_dataset

# MQP:
dataset = load_dataset('medical_questions_pairs')
# PubmedQA:
dataset = load_dataset('bigbio/pubmed_qa')
# USMLE:
dataset=load_dataset('GBaker/MedQA-USMLE-4-options')
# SCOTUS
dataset = load_dataset("lex_glue", 'scotus')
# CaseHOLD
dataset = load_dataset("lex_glue", 'case_hold')
# UNFAIR-ToS
dataset = load_dataset("lex_glue", 'unfair_tos')
```

## Citation
If you find our work helpful, please cite us:
```bibtex
@inproceedings{
cheng2024adapting,
title={Adapting Large Language Models via Reading Comprehension},
author={Daixuan Cheng and Shaohan Huang and Furu Wei},
booktitle={The Twelfth International Conference on Learning Representations},
year={2024},
url={https://openreview.net/forum?id=y886UXPEZ0}
}
```

and the original dataset:
```bibtex
@inproceedings{ConvFinQA,
author = {Zhiyu Chen and
Shiyang Li and
Charese Smiley and
Zhiqiang Ma and
Sameena Shah and
William Yang Wang},
title = {ConvFinQA: Exploring the Chain of Numerical Reasoning in Conversational
Finance Question Answering},
booktitle = {{EMNLP}},
pages = {6279--6292},
publisher = {Association for Computational Linguistics},
year = {2022}
}
```

# 基于持续预训练的大语言模型领域适配
本仓库包含我们发表于**国际学习表征会议2024（ICLR 2024）**的论文《基于阅读理解的大语言模型（Large Language Model, LLM）适配》中使用的**ConvFinQA数据集**。

我们针对大语言模型探索了**领域专属语料上的持续预训练**方案。尽管该方法能够为大语言模型注入领域知识，但会显著损害其在问答任务上的提示学习能力。受人类通过阅读理解进行学习的启发，我们提出了一种简单方法，可**将大规模预训练语料转换为阅读理解文本**，该方法能够持续提升大语言模型在生物医学、金融与法律领域各类任务上的提示学习性能。我们的7B参数模型可与BloombergGPT-50B等超大规模领域专属模型相媲美。

### [2024/11/29] 🤗 推出AdaptLLM的多模态版本[AdaMLLM](https://huggingface.co/AdaptLLM/Adapt-MLLM-to-Domains)，用于多模态大语言模型（Multimodal Large Language Model, MLLM）的领域适配 🤗

**************************** **更新日志** ****************************
* 2024/11/29：发布用于多模态大语言模型领域适配的[AdaMLLM](https://huggingface.co/AdaptLLM/Adapt-MLLM-to-Domains)
* 2024/9/20：我们的[指令预训练研究论文](https://huggingface.co/papers/2406.14491)被**自然语言处理经验方法会议2024（EMNLP 2024）**收录
* 2024/8/29：更新了[评估指南](https://huggingface.co/datasets/AdaptLLM/finance-tasks)，用于在领域专属任务上评估任意🤗Huggingface模型
* 2024/6/22：发布[基准测试代码](https://github.com/microsoft/LMOps/tree/main/adaptllm)
* 2024/6/21：在[指令预训练（Instruction-Pretrain）](https://huggingface.co/instruction-pretrain)平台发布AdaptLLM通用版本
* 2024/4/2：发布所有评估数据集的[原始拆分数据（训练集与测试集）](https://huggingface.co/datasets/AdaptLLM/ConvFinQA)
* 2024/1/16：我们的[AdaptLLM研究论文](https://huggingface.co/papers/2309.09530)被ICLR 2024收录
* 2023/12/19：发布基于LLaMA-1-13B构建的[13B参数基础模型](https://huggingface.co/AdaptLLM/law-LLM-13B)
* 2023/12/8：发布基于LLaMA-2-Chat-7B构建的[对话模型](https://huggingface.co/AdaptLLM/law-chat)
* 2023/9/18：发布基于LLaMA-1-7B构建的[研究论文](https://huggingface.co/papers/2309.09530)、[代码](https://github.com/microsoft/LMOps)、[数据集](https://huggingface.co/datasets/AdaptLLM/law-tasks)与[基础模型](https://huggingface.co/AdaptLLM/law-LLM)

## 领域专属LLaMA-1模型
### LLaMA-1-7B
在本论文中，我们基于LLaMA-1-7B构建了三款领域专属模型，目前已在Huggingface平台开源：[生物医学大语言模型（Biomedicine-LLM）](https://huggingface.co/AdaptLLM/medicine-LLM)、[金融大语言模型（Finance-LLM）](https://huggingface.co/AdaptLLM/finance-LLM)与[法律大语言模型（Law-LLM）](https://huggingface.co/AdaptLLM/law-LLM)。我们的AdaptLLM与其他领域专属大语言模型的性能对比如下：

<p align='center'>
<img src="https://cdn-uploads.huggingface.co/production/uploads/650801ced5578ef7e20b33d4/6efPwitFgy-pLTzvccdcP.png" width="700">
</p>

### LLaMA-1-13B
此外，我们将基础模型扩展至LLaMA-1-13B，以验证**我们的方法在更大规模模型上是否同样有效**，实验结果同样显示该方法效果显著：[Biomedicine-LLM-13B](https://huggingface.co/AdaptLLM/medicine-LLM-13B)、[Finance-LLM-13B](https://huggingface.co/AdaptLLM/finance-LLM-13B)与[Law-LLM-13B](https://huggingface.co/AdaptLLM/law-LLM-13B)。

## 领域专属LLaMA-2-Chat模型
我们的方法同样适用于对齐后的模型！LLaMA-2-Chat需要遵循[特定的数据格式](https://huggingface.co/blog/llama2#how-to-prompt-llama-2)，而我们的**阅读理解转换方案可将阅读理解文本转化为多轮对话**，完美适配该格式。我们还开源了多个领域的对话模型：[Biomedicine-Chat](https://huggingface.co/AdaptLLM/medicine-chat)、[Finance-Chat](https://huggingface.co/AdaptLLM/finance-chat)与[Law-Chat](https://huggingface.co/AdaptLLM/law-chat)

## 领域专属任务
### 预模板化/格式化测试集拆分
为便于复现我们的提示学习实验结果，我们上传了各领域专属任务的零样本/少样本输入提示与输出结果填充模板：[biomedicine-tasks](https://huggingface.co/datasets/AdaptLLM/medicine-tasks)、[finance-tasks](https://huggingface.co/datasets/AdaptLLM/finance-tasks)与[law-tasks](https://huggingface.co/datasets/AdaptLLM/law-tasks)。
**注意：** 此类填充提示专为未对齐的基础模型设计，不适用于对话模型所需的特定数据格式。

### 原始数据集
我们还上传了原始训练集与测试集拆分文件，以方便微调或其他用途：
- [ChemProt](https://huggingface.co/datasets/AdaptLLM/ChemProt)
- [RCT](https://huggingface.co/datasets/AdaptLLM/RCT)
- [ConvFinQA](https://huggingface.co/datasets/AdaptLLM/ConvFinQA)
- [FiQA_SA](https://huggingface.co/datasets/AdaptLLM/FiQA_SA)
- [Headline](https://huggingface.co/datasets/AdaptLLM/Headline)
- [NER](https://huggingface.co/datasets/AdaptLLM/NER)
- [FPB](https://huggingface.co/datasets/AdaptLLM/FPB)

本论文中使用的其他数据集已在Huggingface平台上线，您可通过以下代码直接加载：
python
from datasets import load_dataset

# MQP:
dataset = load_dataset('medical_questions_pairs')
# PubmedQA:
dataset = load_dataset('bigbio/pubmed_qa')
# USMLE:
dataset=load_dataset('GBaker/MedQA-USMLE-4-options')
# SCOTUS
dataset = load_dataset("lex_glue", 'scotus')
# CaseHOLD
dataset = load_dataset("lex_glue", 'case_hold')
# UNFAIR-ToS
dataset = load_dataset("lex_glue", 'unfair_tos')

## 引用
若您的工作受益于本项目，请引用以下论文：
bibtex
@inproceedings{
cheng2024adapting,
title={Adapting Large Language Models via Reading Comprehension},
author={Daixuan Cheng and Shaohan Huang and Furu Wei},
booktitle={The Twelfth International Conference on Learning Representations},
year={2024},
url={https://openreview.net/forum?id=y886UXPEZ0}
}

若需引用原始ConvFinQA数据集，请使用：
bibtex
@inproceedings{ConvFinQA,
author = {Zhiyu Chen and
Shiyang Li and
Charese Smiley and
Zhiqiang Ma and
Sameena Shah and
William Yang Wang},
title = {ConvFinQA: Exploring the Chain of Numerical Reasoning in Conversational
Finance Question Answering},
booktitle = {{EMNLP}},
pages = {6279--6292},
publisher = {Association for Computational Linguistics},
year = {2022}
}

搜集汇总

背景与挑战

背景概述

ConvFinQA是一个金融领域的对话式问答数据集，专注于探索数值推理链。该数据集用于大型语言模型的领域适应研究，特别是在金融问答任务中评估模型的数值推理能力。