license: apache-2.0
language: en
tags:
- microsoft/deberta-v3-base
datasets:
- multi_nli
- snli
- fever
- tals/vitaminc
- paws
metrics:
- accuracy
- auc
- balanced accuracy
pipeline_tag: text-classification
widget:
- text: >-
A man walks into a bar and buys a drink [SEP] A bloke swigs alcohol at a
pub
Cross-Encoder for Hallucination Detection
This model was trained using SentenceTransformers Cross-Encoder 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 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, Vitamin C and PAWS.
Performance
- TRUE Dataset (Minus Vitamin C, FEVER and PAWS) - 0.872 AUC Score
- SummaC Benchmark (Test Split) - 0.764 Balanced Accuracy, 0.831 AUC Score
- AnyScale Ranking Test for Hallucinations - 86.6 % Accuracy
Usage with Sentencer Transformers (Recommended)
The model can be used like this, on pairs of documents, passed as a list of list of strings (List[List[str]]]):
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)
Note that the model is designed to work with entire documents, so long as they fit into the 512 token context window (across both documents). Also note that the order of the documents is important, the first document is the source document, and the second document is validated against the first for factual consistency, e.g. as a summary of the first or a claim drawn from the source.
Usage with Transformers AutoModel
You can use the model also directly with Transformers library (without the SentenceTransformers library):
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)