SallySims/equibert-microaggression

EquiBERT — Microaggression Detector

Model ID: SallySims/equibert-microaggression

Single-label classifier that identifies the type of microaggression present in workplace communications.

Labels

ID	Label	Example
0	none	No microaggression detected
1	microinsult	"You're surprisingly articulate"
2	microinvalidation	"I don't see colour"
3	microassault	Deliberate exclusionary behaviour
4	environmental	Absence of diverse representation
5	behavioural	Non-verbal exclusion
6	second_generation	Systemic/institutional microaggression

Usage

from transformers import AutoTokenizer

tokenizer = AutoTokenizer.from_pretrained("SallySims/equibert-microaggression")
text = "You are surprisingly articulate for someone from your background."
inputs = tokenizer(text, return_tensors="pt", truncation=True, max_length=128)
# predicted_class = model(**inputs).logits.argmax(-1)

Task Head Architecture

CLS → Dropout(0.1) → Linear(hidden, hidden//2) → GELU → Linear(hidden//2, 7)
                                                                  ↓
                                                     CrossEntropyLoss (single-label)

Model Description

EquiBERT is a multi-task DEI (Diversity, Equity and Inclusion) transformer built on a dual-encoder backbone that fuses RoBERTa-base and DeBERTa-v3-base via a learned weighted sum (α parameter). The fused representation is fed into task-specific heads covering 17 distinct DEI analysis tasks.

Organisation: SallySims Framework: PyTorch + HuggingFace Transformers Backbone: RoBERTa-base + DeBERTa-v3-base (dual encoder, fused) Language: English Domain: Organisational DEI text — HR communications, policies, job descriptions, performance reviews, leadership statements, reports

Architecture

Input Text
    │
    ├──▶ RoBERTa-base encoder ──▶ Linear projection
    │                                     │
    └──▶ DeBERTa-v3-base encoder ──▶ Linear projection
                                          │
                              Weighted fusion (learned α)
                                          │
                                   Layer Norm + Dropout
                                          │
                              Task-specific head (see below)

Training Data

Trained on synthetic DEI organisational text generated by the EquiBERT synthetic data pipeline, covering 20 DEI categories across HR, policy, leadership, and workforce analytics domains. For production use, fine-tune on real labelled DEI data.

Limitations

• Trained on synthetic data — predictions should be validated before use in real HR or policy decisions.
• English-only.
• Not a substitute for qualified DEI practitioners or legal advice.
• May reflect biases present in the training corpus.

Citation

If you use EquiBERT in your research, please cite:

@misc{equibert2024,
  author    = {SallySims},
  title     = {EquiBERT: A Multi-Task DEI Transformer},
  year      = {2024},
  publisher = {HuggingFace},
  url       = {https://huggingface.co/SallySims}
}

All EquiBERT Models

Model	Task	Primary Metric
equibert-bias-classifier	Bias Detection	Macro F1
equibert-microaggression	Microaggression Detection	Macro F1
equibert-category-tagger	DEI Category Tagging	Macro F1
equibert-event-exclusion	Event Exclusion Classification	Macro F1
equibert-inclusive-language	Inclusive Language Scoring	Span F1
equibert-review-auditor	Performance Review Auditing	Span F1
equibert-washing-detector	DEI Washing Detection	MAE
equibert-framing-scorer	Report Framing Scoring	MAE
equibert-awareness-scorer	DEI Awareness Scoring	MAE
equibert-similarity	Semantic Similarity	Accuracy
equibert-ner	DEI Entity Recognition	Span F1
equibert-relation-extraction	Relation Extraction	Macro F1
equibert-qa	Extractive QA	Span EM
equibert-search	Semantic Search	MRR@10
equibert-nli	NLI / Textual Entailment	Macro F1
equibert-generator	DEI Text Generation	ROUGE-L