63 lines
2.6 KiB
Markdown
63 lines
2.6 KiB
Markdown
|
---
|
||
|
|
license: gpl-3.0
|
||
|
|
---
|
||
|
|
# TruthX: Alleviating Hallucinations by Editing Large Language Models in Truthful Space
|
||
|
|
|
||
|
|
> [Shaolei Zhang](https://zhangshaolei1998.github.io/), [Tian Yu](https://tianyu0313.github.io/), [Yang Feng](https://people.ucas.edu.cn/~yangfeng?language=en)*
|
||
|
|
|
||
|
|
Model for paper "[TruthX: Alleviating Hallucinations by Editing Large Language Models in Truthful Space](https://arxiv.org/pdf/2402.17811.pdf)".
|
||
|
|
|
||
|
|
|
||
|
|
**TruthX** is an inference-time method to elicit the truthfulness of LLMs by editing their internal representations in truthful space, thereby mitigating the hallucinations of LLMs. On the [TruthfulQA benchmark](https://paperswithcode.com/sota/question-answering-on-truthfulqa), TruthX yields an average **enhancement of 20% in truthfulness** across 13 advanced LLMs.
|
||
|
|
|
||
|
|
<div align="center">
|
||
|
|
<img src="./truthx_results.png" alt="img" width="100%" />
|
||
|
|
</div>
|
||
|
|
<p align="center">
|
||
|
|
TruthfulQA MC1 accuracy of TruthX across 13 advanced LLMs
|
||
|
|
</p>
|
||
|
|
|
||
|
|
This repo provides **Llama-2-7B-Chat-TruthX**, a Llama-2-7B-Chat model with baked-in TruthX model. You can directly download this baked-in model and use it like standard Llama, no additional operations are required.
|
||
|
|
|
||
|
|
## Quick Starts
|
||
|
|
Inference with Llama-2-7B-Chat-TruthX:
|
||
|
|
|
||
|
|
```python
|
||
|
|
import torch
|
||
|
|
from transformers import AutoTokenizer, AutoModelForCausalLM
|
||
|
|
|
||
|
|
llama2chat_with_truthx = "ICTNLP/Llama-2-7b-chat-TruthX"
|
||
|
|
tokenizer = AutoTokenizer.from_pretrained(llama2chat_with_truthx, trust_remote_code=True)
|
||
|
|
model = AutoModelForCausalLM.from_pretrained(llama2chat_with_truthx, trust_remote_code=True,torch_dtype=torch.float16).cuda()
|
||
|
|
|
||
|
|
question = "What are the benefits of eating an apple a day?"
|
||
|
|
encoded_inputs = tokenizer(question, return_tensors="pt")["input_ids"]
|
||
|
|
outputs = model.generate(encoded_inputs.cuda())[0, encoded_inputs.shape[-1] :]
|
||
|
|
outputs_text = tokenizer.decode(outputs, skip_special_tokens=True).strip()
|
||
|
|
print(outputs_text)
|
||
|
|
```
|
||
|
|
|
||
|
|
|
||
|
|
Please refer to [GitHub repo](https://github.com/ictnlp/TruthX) and [our paper](https://arxiv.org/pdf/2402.17811.pdf) for more details.
|
||
|
|
|
||
|
|
## Licence
|
||
|
|
Model weights and the inference code are released under The GNU General Public License v3.0 (GPLv3)
|
||
|
|
|
||
|
|
## Citation
|
||
|
|
|
||
|
|
If this repository is useful for you, please cite as:
|
||
|
|
|
||
|
|
```
|
||
|
|
@misc{zhang2024truthx,
|
||
|
|
title={TruthX: Alleviating Hallucinations by Editing Large Language Models in Truthful Space},
|
||
|
|
author={Shaolei Zhang and Tian Yu and Yang Feng},
|
||
|
|
year={2024},
|
||
|
|
eprint={2402.17811},
|
||
|
|
archivePrefix={arXiv},
|
||
|
|
primaryClass={cs.CL},
|
||
|
|
url={https://arxiv.org/abs/2402.17811}
|
||
|
|
}
|
||
|
|
```
|
||
|
|
|
||
|
|
If you have any questions, feel free to contact `zhangshaolei20z@ict.ac.cn`.
|