← Back to all news
arXiv Computation and Language By Ju-Chun Ko

Uncensored Is Not Unbiased: Abliteration Removes Refusals but Not Script-Dependent Bias About Taiwan

Read the original on arXiv Computation and Language →

The study evaluates whether ‘abliterated’ (uncensored) language models truly eliminate political bias by comparing matched pairs of 2‑bit models—NVIDIA’s Nemotron 3.5 Bolt 74B‑A9B and Qwen3.8‑Flash‑Next—against community‑created abliterations. Across Traditional Chinese, Simplified Chinese, and English, the models’ responses about Taiwan’s status varied more with script than with abliteration; even after removing refusals, the models still affirmed that Taiwan is part of the PRC, especially in Simplified Chinese. The research shows that removing refusal mechanisms does not eradicate script‑dependent bias, and that the choice of script can significantly influence a model’s political stance.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computation and Language.

Related stories

arXiv Computation and Language
Oct 15

OpenTWBench (Open Taiwan Benchmark): Taiwan-Domain Knowledge Evaluation for Large Language Models, and How the Measurement Apparatus Shapes the Score

arXiv:2610.19848v1 Announce Type: new Abstract: We present OpenTWBench, an open evaluation suite for Taiwan-domain knowledge in large language models, built around two benchmarks. tw-exam-bench conta...

By Liang-Hsun Huang, Min-Yi Chen, Chao-Chun Chuang, Yu-Wei Liu, Che-Yu Wu, Po-Feng Lee
llmsbenchmarkssafety
More like this →
arXiv AI
Oct 31

The Model as One Rater Among Several: Measuring Political Positions in Data-Sparse Regions with a Language-Model Panel

The paper introduces a method for measuring political positions in data‑sparse regions by treating a large language model as a single fallible rater within a panel, analogous to expert surveys. It demonstrates that this panel approach yields reliable agreement across multiple models and reveals that disagreements often stem from differing interpretations of the regime rather than factual errors. The authors provide a full rubric, prompt, and data set, using the Middle East and North Africa as a worked example.

By Tarek Gara
llmssafety
More like this →
arXiv Computation and Language
Sep 18

Benchmarking LLM Compliance with China AI Generated Content Regulations

The paper "Benchmarking LLM Compliance with China AI Generated Content Regulations" presents a new framework for evaluating large language models (LLMs) against China’s AI‑generated content compliance rules. Using 2,303 questions across six dimensions—including 203 self‑constructed constitutional queries—the authors assess 20 prominent LLMs, finding that international models show high compliance, especially on ideologically aligned dimensions. The study establishes a regulatory benchmark that allows the global AI community to test both Chinese and non‑Chinese LLMs under unified, legally grounded compliance criteria.

By Chenrui Cui, Hongye Fang, Lisha Song, Weichao Chen, Yue Zhu, Gang Xu
llmsbenchmarkssafety
More like this →