---
license: apache-2.0
language: en
tags:
  - microsoft/deberta-v3-base
datasets:
  - multi_nli
  - snli
  - fever
  - tals/vitaminc
  - paws
metrics:
  - accuracy
  - auc
  - balanced accuracy
---
# Cross-Encoder for Hallucination Detection
This model was trained using [SentenceTransformers](https://sbert.net) [Cross-Encoder](https://www.sbert.net/examples/applications/cross-encoder/README.html) class. 
The model outputs a probabilitity from 0 to 1, 0 being a hallucination and 1 being factually consistent. 
The predictions can be thresholded at 0.5 to predict whether a document is consistent with its source.

## Training Data
This model is based on [microsoft/deberta-v3-base](https://huggingface.co/microsoft/deberta-v3-base) and is trained initially on NLI data to determine textual entailment, before being further fine tuned on summarization datasets with samples annotated for factual consistency including [FEVER](https://huggingface.co/datasets/fever), [Vitamin C](https://huggingface.co/datasets/tals/vitaminc) and [PAWS](https://huggingface.co/datasets/paws).

## Performance

* [TRUE Dataset](https://arxiv.org/pdf/2204.04991.pdf) (Minus Vitamin C, FEVER and PAWS) - 0.872 AUC Score
* [SummaC Benchmark](https://aclanthology.org/2022.tacl-1.10.pdf) (Test Split) - 0.764 Balanced Accuracy, 0.831 AUC Score
* [AnyScale Ranking Test for Hallucinations](https://www.anyscale.com/blog/llama-2-is-about-as-factually-accurate-as-gpt-4-for-summaries-and-is-30x-cheaper) - 86.6 % Accuracy

## Usage with Sentencer Transformers (Recommended)

The model can be used like this:

```python
from sentence_transformers import CrossEncoder

model = CrossEncoder('vectara/hallucination_evaluation_model')
scores = model.predict([
    ["A man walks into a bar and buys a drink", "A bloke swigs alcohol at a pub"],
    ["A person on a horse jumps over a broken down airplane.", "A person is at a diner, ordering an omelette."],
    ["A person on a horse jumps over a broken down airplane.", "A person is outdoors, on a horse."],
    ["A boy is jumping on skateboard in the middle of a red bridge.", "The boy skates down the sidewalk on a blue bridge"],
    ["A man with blond-hair, and a brown shirt drinking out of a public water fountain.", "A blond drinking water in public."],
    ["A man with blond-hair, and a brown shirt drinking out of a public water fountain.", "A blond man wearing a brown shirt is reading a book."],
    ["Mark Wahlberg was a fan of Manny.", "Manny was a fan of Mark Wahlberg."],  
])
```

This returns a numpy array representing a factual consistency score. A score < 0.5 indicates a likely hallucination):
```
array([0.61051559, 0.00047493709, 0.99639291, 0.00021221573, 0.99599433, 0.0014127002, 0.002.8262993], dtype=float32)
```

## Usage with Transformers AutoModel
You can use the model also directly with Transformers library (without the SentenceTransformers library):

```python
from transformers import AutoTokenizer, AutoModelForSequenceClassification
import torch
import numpy as np

model = AutoModelForSequenceClassification.from_pretrained('vectara/hallucination_evaluation_model')
tokenizer = AutoTokenizer.from_pretrained('vectara/hallucination_evaluation_model')

pairs = [
    ["A man walks into a bar and buys a drink", "A bloke swigs alcohol at a pub"],
    ["A person on a horse jumps over a broken down airplane.", "A person is at a diner, ordering an omelette."],
    ["A person on a horse jumps over a broken down airplane.", "A person is outdoors, on a horse."],
    ["A boy is jumping on skateboard in the middle of a red bridge.", "The boy skates down the sidewalk on a blue bridge"],
    ["A man with blond-hair, and a brown shirt drinking out of a public water fountain.", "A blond drinking water in public."],
    ["A man with blond-hair, and a brown shirt drinking out of a public water fountain.", "A blond man wearing a brown shirt is reading a book."],
    ["Mark Wahlberg was a fan of Manny.", "Manny was a fan of Mark Wahlberg."], 
]

inputs = tokenizer.batch_encode_plus(pairs, return_tensors='pt', padding=True)

model.eval()
with torch.no_grad():
    outputs = model(**inputs)
    logits = outputs.logits.cpu().detach().numpy()
    # convert logits to probabilities
    scores = 1 / (1 + np.exp(-logits)).flatten()
```

This returns a numpy array representing a factual consistency score. A score < 0.5 indicates a likely hallucination):
```
array([0.61051559, 0.00047493709, 0.99639291, 0.00021221573, 0.99599433, 0.0014127002, 0.002.8262993], dtype=float32)
```