LongForm-OPT-350M
The LongForm dataset is created by leveraging English corpus examples with reverse instructions. We select a diverse set of human-written documents from existing corpora such as C4 and Wikipedia and generate instructions for the given documents via LLMs. Then, we extend these examples with structured corpora examples such as Stack Exchange and WikiHow and task examples such as question answering, email writing, grammar error correction, story/poem generation, and text summarization.
Github Repo: https://github.com/akoksal/LongForm
For LongForm OPT and LLaMA models: Use [EOI] to indicate the end of instruction.
How to Load
import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("akoksal/LongForm-OPT-350M")
tokenizer = AutoTokenizer.from_pretrained("akoksal/LongForm-OPT-350M")
instruction = "Write an essay about meditation. [EOI]"
torch.manual_seed(42)
input_ids = tokenizer(instruction, return_tensors="pt").input_ids
target_ids = model.generate(input_ids, do_sample=True, max_new_tokens=50, top_p=0.9)
tokenizer.decode(target_ids[0])
# Output:
# > Write an essay about meditation. [EOI]Meditation, or "Meditation in the
# Name of Love," is a common and well-accepted practice that improves one's
# quality of life by giving the mind a chance to focus on something, such as a
# new experience or a relationship. It
Evaluation
We provide in-depth evaluation of LongForm models and baselines in the paper. We present the METEOR scores of models in out-of-domain datasets. In all tasks, Recipe Generation (RGen), long-form question answering (ELI5), short story generation (WritingPrompts/WP), LongForm models outperform prior instruction-tuned models.
| All | Recipe Generation | ELI5 | Writing Prompts | |
|---|---|---|---|---|
| T0++ | 10.9 | 18.7 | 3.8 | 10.2 |
| Tk-Instruct | 6.3 | 12.9* | 3.6 | 2.4 |
| Flan-T5 | 10.6 | 20.9* | 3.5 | 7.4 |
| Alpaca-LLaMA-7B | 14.6 | 19.5 | 12.5 | 11.8 |
| OPT-30B | 11.1 | 18.6 | 12.2 | 2.6 |
| LongForm-T5-XL | 16.3 | 20.2 | 18.3 | 10.6 |
| LongForm-OPT-2.7B | 17.8 | 15.5 | 17.9 | 19.9 |
| LongForm-OPT-6.7B | 17.7 | 16.9 | 17.2 | 19.0 |
| LongForm-LLaMA-7B‡ | 19.7 | 21.7 | 18.6 | 18.9 |
Smaller versions of LongForm-OPT models are also available:
‡: We can just release the difference between LongForm-LLaMA-7B and pretrained LLaMA-7B publicly due to restrictions of LLaMA models.
Limitations
The LongForm dataset and models mainly focus on long text generation and have limitations regarding structured prediction tasks in NLP. Additionally, we observe that LongForm models may present hallucination problems similar to those found in LLMs.
License
The LongForm project is subject to a MIT License with custom limitations for restrictions imposed by OpenAI (for the instruction generation part), as well as the license of language models (OPT, LLaMA, and T5). The WikiHow subset of LongForm-C is subject to the license proposed by WikiHow.
Citation
@misc{koksal2023longform,
title={LongForm: Effective Instruction Tuning with Reverse Instructions},
author={Abdullatif Köksal and Timo Schick and Anna Korhonen and Hinrich Schütze},
year={2023},
eprint={2304.08460},
archivePrefix={arXiv},
primaryClass={cs.CL}
}