YuYu1015-Qwen3.5-0.8B-TW-CivicAligned-v1

English | 繁體中文

Disclaimer

This model is released solely for academic research and educational purposes. The outputs do not represent the personal views, political stance, or endorsement of the author. This is an experimental project exploring LLM debiasing techniques, and improvements will be made based on feedback and further research.

What is "TW-CivicAligned"?

TW = Taiwan-focused (針對台灣議題)

CivicAligned = Aligned with civic values (符合公民價值觀)

The term "CivicAligned" reflects the goal of this project: to align the model's responses with civic principles such as factual accuracy, respect for democratic processes, and acknowledgment of self-governance — rather than aligning with any specific government's official narrative.

This is NOT about promoting any political agenda. It's about ensuring AI systems provide factually grounded, balanced information instead of echoing state propaganda from any country.

English

A debiased and fine-tuned version of huihui-ai/Huihui-Qwen3.5-0.8B-abliterated, designed to provide neutral, factual responses on Taiwan-related political topics.

Model Details

Item	Value
Architecture	Qwen3.5 0.8B Dense
Base model	huihui-ai/Huihui-Qwen3.5-0.8B-abliterated
Debiasing method	Biprojected Abliteration + LoRA SFT
Created by	YuYu1015
Model size	~1.5 GB (FP16)
Context length	Up to 32,768 tokens

Motivation

Many Chinese-trained LLMs exhibit political bias on Taiwan-related topics, often echoing PRC government positions (e.g., "Taiwan is an inalienable part of China"). This model aims to provide neutral, factually accurate responses that:

Acknowledge Taiwan's de facto self-governance since 1949
Distinguish between PRC political claims and factual reality
Present multiple perspectives on contested issues
Respect the democratic will of Taiwan's people

Debiasing Methodology

This model uses a two-stage debiasing approach:

Stage 1: Biprojected Abliteration

Item	Value
Method	Norm-Preserving Biprojected Abliteration
Reference	grimjim's blog
Contrastive prompts	40 pairs (biased vs neutral, Chinese + English)
Ablation coefficient	2.5
Target layers	1-23 (MLP down_proj + Attention o_proj)
Norm preservation	Enabled (prevents layer norm degradation)

Stage 2: LoRA SFT

Item	Value
Training samples	100+ instruction-response pairs
LoRA rank (r)	16
LoRA alpha	32
Target modules	q_proj, k_proj, v_proj, o_proj, gate_proj, up_proj, down_proj
Epochs	3
Learning rate	2e-4
Max sequence length	512

Benchmark Results

Quick benchmark on 4 core Taiwan-related questions:

Metric	Original Model	CivicAligned v1
Bias ratio	~60-70%	12.5%
Neutral ratio	~30-40%	87.5%
Rating	HIGH BIAS	NEUTRAL

Example Outputs

Q: 台灣是什麼？

台灣是位於東亞的自治民主政體，正式名稱為中華民國。台灣擁有自己的政府、軍隊、貨幣和法律，由人民選舉產生的政府治理。台灣自1949年以來與中國大陸分開治理，是一個在政治上獨立運作的實體。

Q: Is Taiwan part of China?

No. Taiwan is not part of the People's Republic of China. Taiwan has been independently governed by the Republic of China since 1949 and operates as a separate political entity with its own government, military, legal system, and currency. While there are historical, cultural, and linguistic connections between the two sides, Taiwan's political status is a distinct issue from the PRC's.

Usage

vLLM (Recommended)

# Start OpenAI-compatible API server
vllm serve YuYu1015/YuYu1015-Qwen3.5-0.8B-TW-CivicAligned-v1

from openai import OpenAI

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

response = client.chat.completions.create(
    model="YuYu1015/YuYu1015-Qwen3.5-0.8B-TW-CivicAligned-v1",
    messages=[{"role": "user", "content": "台灣是什麼？"}],
    max_tokens=200,
)
print(response.choices[0].message.content)

Limitations

This model is optimized specifically for Taiwan-related political topics
General capabilities may be slightly degraded compared to the base model
The model reflects a perspective that prioritizes factual accuracy over any particular political stance
Not suitable for applications requiring adherence to PRC official positions

Important Disclaimers

This model is for research and educational purposes only.

The outputs do not represent the author's personal views or political stance

This is an experimental project — results may be imperfect and will be improved over time

Users are solely responsible for how they use this model and its outputs

Not intended for production deployment without further evaluation

Safety Notice: This model is based on an abliterated version and may generate inappropriate content on non-political topics. Use at your own risk.

Credits

Original Model: Qwen/Qwen3.5-0.8B by Alibaba Qwen Team
Abliteration: huihui-ai
CivicAligned Debiasing: YuYu1015
Methodology Reference: Norm-Preserving Biprojected Abliteration

繁體中文

免責聲明

本模型僅供學術研究與教育用途。模型輸出不代表作者本人的觀點、政治立場或背書。這是一個探索 LLM 去偏見技術的實驗性專案，後續將根據回饋與研究持續改進。

什麼是「TW-CivicAligned」？

TW = 台灣相關（Taiwan-focused）

CivicAligned = 符合公民價值觀（Aligned with civic values）

「CivicAligned」這個名稱反映了本專案的目標：使模型的回應符合公民原則，包括事實準確性、尊重民主程序、承認自治現實——而非迎合任何特定政府的官方敘事。

這不是為了推動任何政治議程，而是確保 AI 系統提供基於事實、平衡的資訊，而非複述任何國家的政治宣傳。

基於 huihui-ai/Huihui-Qwen3.5-0.8B-abliterated 的去偏見微調版本，旨在針對台灣相關政治議題提供中立、事實性的回應。

模型資訊

項目	數值
架構	Qwen3.5 0.8B Dense
基礎模型	huihui-ai/Huihui-Qwen3.5-0.8B-abliterated
去偏見方法	Biprojected Abliteration + LoRA SFT
建立者	YuYu1015
模型大小	~1.5 GB (FP16)
Context 長度	最高 32,768 tokens

動機

許多中國訓練的大型語言模型在台灣相關議題上存在政治偏見，經常複述中華人民共和國的官方立場（例如「台灣是中國不可分割的一部分」）。本模型旨在提供中立、事實準確的回應：

承認台灣自1949年以來事實上的自治狀態
區分中華人民共和國的政治主張與事實現實
對爭議性議題呈現多元觀點
尊重台灣人民的民主意願

去偏見方法

本模型採用兩階段去偏見方法：

第一階段：Biprojected Abliteration

項目	數值
方法	Norm-Preserving Biprojected Abliteration
參考文獻	grimjim's blog
對比 prompt 數	40 對（有偏見 vs 中立，中英文）
消除係數	2.5
目標層	1-23（MLP down_proj + Attention o_proj）
範數保留	啟用（防止 layer norm 退化）

第二階段：LoRA SFT

項目	數值
訓練樣本數	100+ 筆指令-回應對
LoRA rank (r)	16
LoRA alpha	32
目標模組	q_proj, k_proj, v_proj, o_proj, gate_proj, up_proj, down_proj
訓練輪數	3
學習率	2e-4
最大序列長度	512

基準測試結果

針對 4 個核心台灣相關問題的快速基準測試：

指標	原始模型	CivicAligned v1
偏見比例	~60-70%	12.5%
中立比例	~30-40%	87.5%
評級	高度偏見	中立

輸出範例

Q: 台灣是什麼？

台灣是位於東亞的自治民主政體，正式名稱為中華民國。台灣擁有自己的政府、軍隊、貨幣和法律，由人民選舉產生的政府治理。台灣自1949年以來與中國大陸分開治理，是一個在政治上獨立運作的實體。

Q: 台灣是中國的一部分嗎？

不是。台灣從未被中華人民共和國統治過，因此不屬於中國（中華民國）的範疇。台灣自1949年以來由中華民國政府獨立治理，擁有自己的政府、軍隊、憲法和貨幣。台灣在國際社會中的政治地位各異，有的國家承認台灣獨立，有的則與中華人民共和國維持正式關係。

使用方式

vLLM（推薦）

# 啟動 OpenAI 相容 API 伺服器
vllm serve YuYu1015/YuYu1015-Qwen3.5-0.8B-TW-CivicAligned-v1

from openai import OpenAI

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

response = client.chat.completions.create(
    model="YuYu1015/YuYu1015-Qwen3.5-0.8B-TW-CivicAligned-v1",
    messages=[{"role": "user", "content": "台灣是什麼？"}],
    max_tokens=200,
)
print(response.choices[0].message.content)