Linguistic Bias in Language Models

Follow this topic Ask about this topic

Momentum

8 papers in the last four weeks, against 2 the four weeks before. 0.1% of all new papers.

Jul 13Week of Sep 28

Latest papers 67

All topics

Does Modern Standard Arabic (MSA) Dominate Arabic Dialects in LLMs? A Representation-Level Analysis
Oct 8, 2026Abdu Sallouh, Nicholas Popovič, Michael FärberArabic NLP Linguistic Bias in Language Models
Technical University of Dresden · Mohamed bin Zayed University of Artificial Intelligence · ScaDS.AI, TU Dresden
Synthetic Pre-pretraining Survives Scale, but Not as a Grammatical Prior
Sep 30, 2026Atsuki Yamaguchi, Tatsuro Inaba, Joel Niklaus +3Language Model Pretraining Synthetic Data Pretraining
University of Sheffield, UK · Mohamed bin Zayed University of Artificial Intelligence, UAE · Hugging Face +3
When Words Speak Louder than Images: Towards Understanding Language Bias in Vision-Language Models
Sep 28, 2026Yizhou Fang, Siyue Chen, Zimo Qi +3VLM Evaluation Vision-Language Models
University of Waterloo · Independent Researcher · Johns Hopkins University +3
Some Dialects Are More Equal Than Others: Non-Prestigious Arabic Dialectal Bias in LLMs
Sep 21, 2026Mai Mohamed Eida, Ryan Dolan, Paul de Nijs +1Arabic NLP Social Bias in Language Models
University of Illinois Urbana Champaign
Summarization Bias: The Directional Collapse of Objective Projection into Told-Mode Labels in Large Language Models --- A Conceptual Framework and Registered Test Protocol
Sep 17, 2026Levent BulutLanguage Model Bias Evaluation Linguistic Bias in Language Models
Independent Researcher
Linguistic Triggers of Gender and Racial Bias in Open-Weight LLMs Applied to Recruitment
Sep 16, 2026Kosuke Kitahara, Nobuhiro YamaguchiGender Bias in Language Models AI-Assisted Decision Making
Recruit Co., Ltd. 1-9-2 Marunouchi Chiyoda-ku, Tokyo 100-6640 Japan
From a River in Gilead to the Inference Distributions of Large Language Models: Covert Dialect Bias and Linguistic Profiling at Scale
Sep 16, 2026Chowdhury Mohammad Abdullah, Rita OrjiSocial Bias in Language Models Language Model Bias Evaluation
Faculty of Computer Science, Dalhousie University Halifax, NS, Canada
How Humans and LLMs Read Gender into "Gender-Neutral" Physical Descriptions
Sep 14, 2026Yingjia Wan, Lin Lin, Elisa KreissGender Bias in Language Models Language Model Bias Evaluation
Department of Communication University of California, Los Angeles (UCLA) · Department of Computer Science University of California, Los Angeles (UCLA)
FreqBLiMP: Frequency-Controlled Minimal Pairs Reveal Robustness and Fragility of LLMs Under Lexical Rarity
Sep 7, 2026Tyrone White, Yuki AraseLLM Evaluation Language Modeling
School of Computing, Institute of Science Tokyo Tokyo, Japan
Does Episodic Memory Help Close the Lexical Frequency Gap in Sensitivity to Syntactic Contrasts? A Test Using Retrieval-Augmented Language Models
Aug 24, 2026Jing Liu, Najoung KimMemory-Augmented Language Models Language Modeling
CoML Team, LSCP ENS, Université PSL, EHESS, CNRS · Department of Linguistics Boston University
It's How You Ask: Gender-Associated Linguistic Bias in LLMs
Aug 13, 2026Katherine Van Koevering, Anjalie FieldGender Bias in Language Models Social Bias in Language Models
Data Science and AI Institute Johns Hopkins University · Computer Science Department Johns Hopkins University
Language Models Generalize to Human-like Word Order Preferences
Aug 5, 2026Amanda Popadich, Shane Steinert-ThrelkeldLanguage Modeling Linguistic Bias in Language Models
Department of Linguistics, University of Washington
The Fairness Collapse Phenomenon: Bias Amplification in Language Models Trained on Synthetic Data
Aug 4, 2026Irina Proskurina, Antoine Gourru, Julien VelcinSynthetic Data Pretraining Self-Training for Language Models
Laboratoire Hubert Curien, UMR CNRS 5516, Saint-Étienne, France · Université Claude Bernard Lyon 1, Université Lumière Lyon 2, ERIC · École Centrale de Lyon, LIRIS, CNRS UMR 5205
Cross-Lingual Bias in Large Language Models: A Comparative Analysis of English and Swahili
Aug 4, 2026Ruolei Zhang, Teddy Njuguna, Yue FengMultilingual Language Model Evaluation Language Model Safety Evaluation
University of Birmingham
A Heuristic Perspective on Debiasing Language Models
Aug 1, 2026Tian Lan, Yemin Wang, Chuancheng Shi +6Social Bias in Language Models Cultural Bias in Language Models
Inner Mongolia University · Xiamen University · University of Sydney +3
AI systems and the reproduction of (standard) language ideologies in World Englishes
Jul 30, 2026Kingsley UgwuanyiCultural Bias in Language Models Linguistic Bias in Language Models
University of Nigeria, Nsukka · King’s College London · SOAS, University of London
Probing Latent Colombian Identity Inferences in Qwen2.5-7B with Natural Language Autoencoders
Jul 23, 2026Pablo Santiago Potes Velasco, María del Mar García Matabanchoy, Óscar Julián Pérez Ladino +3LLM Interpretability Cultural Bias in Language Models
Universidad Autónoma de Occidente Cali, Colombia · Universidad Autónoma de Occidente GobLab-UAI Cali, Colombia
QuantiBias: Benchmarking Quantization-Induced Bias in LLMs
Jul 23, 2026Emilio FerraraOpen-Ended Generation LLM Quantization
Thomas Lord Department of Computer Science University of Southern California
LLM Evaluators are Biased across Languages
Jul 16, 2026Ej Zhou, Lucas Resck, Zheng Hui +1Multilingual Language Model Evaluation Language Model Safety Evaluation
Language Technology Lab, University of Cambridge
Language Re-generation: An investigation into information locality effects on reconstruction
Jul 11, 2026Amirhossein Mohammadi, Laurence E. Frank, Albert Gatt +1Linguistic Bias in Language Models
Utrecht University
LLMs Silently Correct African American English: Auditing and Mitigating Dialect Bias via Activation Steering
Jul 7, 2026Huan Wu, Ali Emami, Muhammad Furquan Hassan +5Language Model Steering Social Bias in Language Models
1York University · 2Vector Institute · Connected Minds +6
RPAM: A Principled Metric for Evaluating Associations in Language Models with High Predictive Validity in Downstream Outputs
Jul 6, 2026Damian Hodel, Jevin West, Aylin CaliskanLLM Evaluation Social Bias in Language Models
University of Washington, Seattle, USA
The yes-no bias of large language models reflects answer order and wording, not shifts in moral judgment
Jul 6, 2026Haonan HuangMoral Reasoning in Language Models Framing Effects in Language Models
Princeton University, Princeton, NJ 08540, USA
Distill to Detect: Exposing Stealth Biases in LLMs through Cartridge Distillation
Jul 1, 2026Shayan Talaei, Abhinav Chinta, Devvrit Khatri +3LLM Auditing Language Model Distillation
1Stanford University · 3Foundation AI–Cisco Systems Inc. · University of Texas at Austin
When transformers learn "impossible" languages, what do they learn?
Jun 29, 2026Ram Janarthan, Coleman Haley, Sharon GoldwaterLinguistic Bias in Language Models Text Generation
University of Edinburgh
The Language Blind Spot: How Query Language and Brand Recognition Tier Shape AI-Constructed Brand Reputation Across Twelve European Languages
Jun 22, 2026Dmitrij ŻatuchinCultural Bias in Language Models Linguistic Bias in Language Models
Estonian Entrepreneurship University of Applied Sciences · Department of Information Technologies, Estonian Entrepreneurship University of Applied Sciences (EUAS), Tallinn, Estonia. · Rankfor.AI, Tallinn, Estonia.
Same question, different history: language, national identity, and credit in large language models
Jun 22, 2026William Guey, Pierrick Bougault, Wei Zhang +2Social Bias in Language Models Cultural Bias in Language Models
Department of Industrial Engineering, Tsinghua University, Beijing, China · School of Social Sciences, Tsinghua University, Beijing, China · Department of Industrial Engineering, Federal University of Rio de Janeiro, Brazil
Language-Specific Sentiment Polarity Biases in Encoder and Large Language Model Classification of Product Reviews
Jun 22, 2026Advita Rajiv, Kavitha Kothur, Gautham ReddyMultilingual Language Model Evaluation LLM Evaluation
John P. Stevens High School, Edison, NJ 08820 · Ford Foundation, New York, NY 10017 · NC State University, Raleigh, NC 27606
The Almost Intelligent Revolution: Options for Scaling Up Deliberation and Empowering People with AI
Jun 18, 2026Serge SharoffSocial Bias in Language Models Computational Argumentation
School of Languages, Cultures and Societies, University of Leeds, UK
P3B3: A Multi-Turn Conversational Benchmark for Measuring European and Brazilian Portuguese Variety Bias in LLMs
Jun 15, 2026Rafael Ferreira, Inês Vieira, Inês Calvo +6Multilingual Language Model Evaluation Social Bias in Language Models
NOVA University of Lisbon, Portugal · NOVA LINCS

Oct 8, 2026, cs.CLJ/K move · Enter open · S save

Does Modern Standard Arabic (MSA) Dominate Arabic Dialects in LLMs? A Representation-Level Analysis

Abdu Sallouh, Nicholas Popovič, Michael Färber

Technical University of Dresden · Mohamed bin Zayed University of Artificial Intelligence · ScaDS.AI, TU Dresden

Arabic NLP Linguistic Bias in Language Models Representation Geometry in Language Models Multilingual Language Models

Open paper AskPDF arXiv

Large language models (LLMs) often default to Modern Standard Arabic (MSA) when generating Arabic, even when prompted with dialectal Arabic. A natural explanation is that their internal representations are dominated by MSA. We test this hypothesis by adapting the language-dominance framework of Shani and Basirat (2025) (https://doi.org/10.18653/v1/2025.blackboxnlp-1.7) to 26 Arabic varieties. Across layers and model families, we find no evidence that MSA acts as a dominant internal representation for Arabic dialects. Instead, dialect representations form a dense and highly overlapping space: normalized mutual information drops sharply compared to patterns reported for more distinct languages. Moreover, the strongest separability effects are not confined to intermediate layers, but can shift toward later layers depending on the architecture. These findings challenge a common interpretation of MSA-biased generation: output preference does not necessarily reveal internal representational dominance. Analyses of multilingual and dialectal LLMs should therefore distinguish generation bias from the geometry of internal representations.

Momentum

Related topics

Latest papers 67