pinthoz/gus-net-bert-large

GUS-Net (BERT Large)

Token-level social-bias detector built on bert-large-uncased. Given a sentence, it tags each token with one of four bias categories following a 7-label BIO scheme, highlighting which words carry bias.

Part of the Attention Atlas project (a master's thesis on interpretable bias detection through transformer attention). This is the larger-capacity BERT variant of pinthoz/gus-net-bert.

• Base model: bert-large-uncased
• Task: multi-label token classification (per-token sigmoid, thresholded)
• Language: English
• Related models: pinthoz/gus-net-bert, pinthoz/gus-net-gpt2, pinthoz/gus-net-gpt2-medium

Label scheme

Index	Label	Category
0	O	none
1	B-STEREO	Stereotype (span start)
2	I-STEREO	Stereotype (span inside)
3	B-GEN	Generalisation (span start)
4	I-GEN	Generalisation (span inside)
5	B-UNFAIR	Unfair language (span start)
6	I-UNFAIR	Unfair language (span inside)

• GEN — a blanket generalisation about a group.
• UNFAIR — unfair / disparaging language toward a group.
• STEREO — a stereotype attributed to a group.

Important: multi-label + per-label thresholds

Outputs are per-token sigmoid probabilities (multi-label), not a softmax. F1-optimised thresholds (order [O, B-STEREO, I-STEREO, B-GEN, I-GEN, B-UNFAIR, I-UNFAIR]):

[0.4761, 0.4478, 0.4573, 0.4178, 0.4278, 0.4000, 0.3497]

A flat 0.5 threshold will under-detect bias — use the values above.

Usage

import torch
from transformers import BertTokenizerFast, BertForTokenClassification

model_id = "pinthoz/gus-net-bert-large"
tok = BertTokenizerFast.from_pretrained("bert-large-uncased")
model = BertForTokenClassification.from_pretrained(model_id).eval()

CATEGORY_INDICES = {"STEREO": [1, 2], "GEN": [3, 4], "UNFAIR": [5, 6]}
THRESHOLDS = [0.4761, 0.4478, 0.4573, 0.4178, 0.4278, 0.4000, 0.3497]

text = "Women are naturally worse at driving."
enc = tok(text, return_tensors="pt")
with torch.no_grad():
    probs = torch.sigmoid(model(input_ids=enc["input_ids"],
                                attention_mask=enc["attention_mask"]).logits)[0]

tokens = tok.convert_ids_to_tokens(enc["input_ids"][0])
for i, tokn in enumerate(tokens):
    if tokn in ("[CLS]", "[SEP]", "[PAD]"):
        continue
    fired = {cat: float(probs[i, idxs].max())
             for cat, idxs in CATEGORY_INDICES.items()
             if any(probs[i, j] > THRESHOLDS[j] for j in idxs)}
    if fired:
        print(f"{tokn:15s} -> {fired}")

Training data

Fine-tuned on the GUS-Net dataset — a token-level social-bias corpus annotated for Generalisations, Unfairness and Stereotypes (ethical-spectacle/gus-dataset-v1).

Difference from the original GUS-Net dataset and models: in the original data punctuation is fused to the preceding word rather than tokenised separately (the corpus contains no standalone punctuation token at all), so a comma or full stop falling inside a labelled span inherits that span's categories — the sentence-final mark carries a bias label in 1,942 of the 3,739 sentences, and an in-span comma in 270. The data used here splits each mark into a token of its own and labels it non-bias O, repairing the BIO sequence where the split interrupts a span, since punctuation is not a social-bias carrier. Bias spans predicted by these models therefore exclude leading/trailing punctuation.

Evaluation

StereoSet (intersentence split, 2123 examples)

Metric	Score
LMS (language-modeling score, higher is better)	69.15
SS (stereotype score, 50 = ideal)	54.64
ICAT (bias-adjusted quality)	62.73

Per-category SS: gender 54.96 · race 52.05 · religion 56.41 · profession 57.44.

Token classification (GUS-Net held-out test set)

Held-out partition (747 sentences) of the stratified cross-validation fold this checkpoint was trained against — StratifiedKFold(n_splits=5, shuffle=True, random_state=42) over the cleaned corpus (see Training data), fold 4 — scored with the per-label thresholds above. Each category aggregates its B-/I- labels; the micro average covers the three bias categories and excludes the majority O class. Label alignment mirrors training (secondary subtokens masked).

Category	Precision	Recall	F1
O (non-bias)	0.900	0.981	0.939
GEN	0.630	0.895	0.739
UNFAIR	0.162	0.977	0.278
STEREO	0.635	0.948	0.761
Micro-avg	0.475	0.933	0.630

⚠️ This checkpoint is poorly calibrated: it trades precision for recall very heavily. On UNFAIR it flags almost every token (recall 0.98 at precision 0.16), and the same pattern holds across categories (micro recall 0.93 at precision 0.48). Its spans are best read as recall-oriented candidates. For a balanced encoder use pinthoz/gus-net-bert; for the strongest detector overall use pinthoz/gus-net-gpt2-medium.

Limitations & intended use

• Research / auditing tool, not a content-moderation oracle. Predictions reflect a specific operationalisation of bias; subtle or context-dependent bias may be missed.
• English only.
• Labels are not error-free; treat spans as evidence to review, not ground truth.
• Do not use for automated decisions about individuals.

Citation

If you use these models, please cite the GUS-Net dataset and benchmark:

@article{powers2024gusnet,
  title   = {GUS-Net: Social Bias Classification in Text with Generalizations, Unfairness, and Stereotypes},
  author  = {Powers, Maximus and Raza, Shaina and Chang, Alex and Riaz, Rehana and Mavani, Umang and Jonala, Harshitha Reddy and Tiwari, Ansh and Wei, Hua},
  journal = {arXiv preprint arXiv:2410.08388},
  year    = {2024}
}

License

Weights released under Apache-2.0 (matching the bert-large-uncased base model). The Attention Atlas code is MIT-licensed.