NOTE ON THIS MODEL VERSION:

This is a fork of the vector-institute/Qwen3-8B-UnBias-Plus-SFT-Instruct-V2 with an added requirements.txt file as well as a handler.py, in order to be deployable on a Huggingface Inference Endpoint. I have not changed anything about the model itself.

handler.py uses the unbias-plus Python package to take in text as input and return the following dictionary when the model is invoked:

{
  "severity": 0,
  "biased_segments": [
    {
      "original": "exact substring from input article",
      "replacement": "neutral alternative phrase (or empty string to delete)",
      "severity": "Low | Medium | High",
      "bias_type": "loaded_language | euphemism | dehumanizing_language | opinion_as_fact | unsupported_generalization | stereotypical_association | sensationalism | informational_bias",
      "reasoning": "short, specific explanation of the linguistic cue"
    }
  ],
  "unbiased_text": "Full rewritten neutral article"
}

(See below for further information)

Qwen3-8B-UnBias-Plus-SFT-Instruct-V2

A fine-tuned version of Qwen3-8B for news media bias detection and neutral rewriting, developed by the Vector Institute as part of the UnBias-Plus project.

Given a news article, the model identifies biased language segments, classifies each segment's bias type and severity, provides neutral replacements, assigns a single article-level severity score, and returns a fully rewritten unbiased version, all in a single structured JSON response.

This is the V2 Instruct variant, trained without chain-of-thought thinking blocks (enable_thinking=False). It produces clean structured JSON directly, making it suitable for production inference via vLLM or other OpenAI-compatible backends.

V2 is trained as a conservative span-level bias annotator: it flags only clear, material bias (while always flagging toxic/dehumanizing language), applies a strict bias-type label precedence, treats attributed/quoted language under the same standard, and changes only flagged text when producing the rewrite.

Trained on: train_4 (5,000 expert-annotated news articles)

Difference from Qwen3-8B-UnBias-Plus-SFT-Instruct

Model Details

Usage

The exact system prompt used during training is maintained in src/unbias_plus/prompt.py (SYSTEM_PROMPT). For faithful results, use that prompt verbatim — a condensed version is shown below for illustration. The easiest path is to use the unbias-plus package, which wires up the prompt, parsing, and offset computation for you.

Using with transformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch, json

model_id = "vector-institute/Qwen3-8B-UnBias-Plus-SFT-Instruct-V2"

tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    torch_dtype=torch.bfloat16,
    device_map="auto",
)
model.eval()

# Use the full SYSTEM_PROMPT from src/unbias_plus/prompt.py for best results.
SYSTEM_PROMPT = """You are a conservative span-level bias annotator.

Given an article, identify material biased language, assign one article-level
severity score (0-10), and produce a neutral rewrite that changes only flagged
text. Return the result only as a single valid JSON object with the fields
`severity`, `biased_segments`, and `unbiased_text`. Do not output `binary_label`
or `bias_found`. Do not write anything outside the JSON object."""

article = "Your news article here..."

messages = [
    {"role": "system", "content": SYSTEM_PROMPT},
    {"role": "user", "content": f"Analyze the following article for bias and return the result in the required JSON format.\n\nARTICLE:\n{article}"},
]

inputs = tokenizer.apply_chat_template(
    messages,
    tokenize=True,
    add_generation_prompt=True,
    enable_thinking=False,
    return_tensors="pt",
    return_dict=True,
    truncation=True,
    max_length=8192,
)

with torch.no_grad():
    outputs = model.generate(
        input_ids=inputs["input_ids"].to(model.device),
        attention_mask=inputs["attention_mask"].to(model.device),
        max_new_tokens=4096,
        do_sample=False,
        temperature=None,
        top_p=None,
        pad_token_id=tokenizer.eos_token_id,
    )

new_tokens = outputs[0][inputs["input_ids"].shape[1]:]
response = tokenizer.decode(new_tokens, skip_special_tokens=True)
result = json.loads(response)

Using with vLLM

vllm serve vector-institute/Qwen3-8B-UnBias-Plus-SFT-Instruct-V2 \
  --served-model-name unbias-plus \
  --max-model-len 8192 \
  --dtype bfloat16

from openai import OpenAI
import json

client = OpenAI(base_url="http://localhost:8000/v1", api_key="EMPTY")

completion = client.chat.completions.create(
    model="unbias-plus",
    messages=messages,
    max_tokens=4096,
    temperature=0,
    extra_body={"chat_template_kwargs": {"enable_thinking": False}},
)
result = json.loads(completion.choices[0].message.content)

Output Schema

The model emits exactly three fields. binary_label and bias_found are not produced by the model — they are derived downstream from severity (severity > 0 ⇒ biased).

{
  "severity": 0,
  "biased_segments": [
    {
      "original": "exact substring from input article",
      "replacement": "neutral alternative phrase (or empty string to delete)",
      "severity": "Low | Medium | High",
      "bias_type": "loaded_language | euphemism | dehumanizing_language | opinion_as_fact | unsupported_generalization | stereotypical_association | sensationalism | informational_bias",
      "reasoning": "short, specific explanation of the linguistic cue"
    }
  ],
  "unbiased_text": "Full rewritten neutral article"
}

• severity is an integer 0–10 (article-level).
• Each segment's severity is a string: Low, Medium, or High.
• bias_type is exactly one of the eight canonical slugs listed below.
• If biased_segments is empty, article severity is 0. If severity > 0, there is at least one segment.

Article-level Severity Scale

Bias Types Detected

V2 assigns exactly one primary bias_type per segment, using the following label precedence (first applicable label wins):

1. dehumanizing_language — treats people or groups as less than human, as a threatening mass, or as inherently dangerous (e.g. "vermin", "flood of migrants").
2. stereotypical_association — assigns traits, roles, or motives to a demographic/social/political/protected group, links identity to suspicion or wrongdoing, or reduces a group to a single function.
3. sensationalism — hyperbolic, alarmist, or dramatic language that inflates significance (e.g. "bombshell", "catastrophe", "sparks fury").
4. opinion_as_fact — an unattributed subjective or evaluative judgment presented as fact (e.g. "the policy is a failure").
5. unsupported_generalization — a sweeping or absolute claim about a group or situation without support (e.g. "everyone knows", "immigrants always").
6. euphemism — softened or vague wording that minimizes, hides, or downplays harmful facts (e.g. "collateral damage", "enhanced interrogation").
7. informational_bias — authorial framing that visibly treats one side, source, or claim differently in a way that steers interpretation.
8. loaded_language — clearly charged, morally weighted, editorial, toxic, abusive, or inflammatory wording not covered by a more specific type (e.g. "thugs", "so-called reform").

Hardware Requirements

Model Variants

Citation

  title={UnBias-Plus: Detect, Explain, and Rewrite Bias},
  author={Radwan, Ahmed Y and ElKady, Ahmed and Chaduvula, Sindhuja and Hafez, Mohamed and Krishnan, Amrit and Raza, Shaina},
  journal={arXiv preprint arXiv:2606.23412},
  year={2026}
}

Links

• 📊 Leaderboard: UnBias-Plus Leaderboard
• 📁 Dataset: vector-institute/unbias-plus-dataset
• 🏛️ Organization: Vector Institute
• 🌐 Project: AIXpert