English
Related papers

Related papers: Cultural Binding Heads in Language Models

200 papers

Language confusion -- where large language models (LLMs) generate unintended languages against the user's need -- remains a critical challenge, especially for English-centric models. We present the first mechanistic interpretability (MI)…

Computation and Language · Computer Science 2025-09-19 Ercong Nie , Helmut Schmid , Hinrich Schütze

Cultural Intelligence (CQ) refers to the ability to understand unfamiliar cultural contexts, a crucial skill for large language models (LLMs) to effectively engage with globally diverse users. Existing studies often focus on explicitly…

Computation and Language · Computer Science 2025-10-10 Ziyi Liu , Priyanka Dey , Jen-tse Huang , Zhenyu Zhao , Bowen Jiang , Rahul Gupta , Yang Liu , Yao Du , Jieyu Zhao

Large Language Models (LLMs) are pretrained on extensive multilingual corpora to acquire both language-specific cultural knowledge and general knowledge. Ideally, while LLMs should provide consistent responses to culture-independent…

Computation and Language · Computer Science 2025-02-11 Yumeng Wang , Zhiyuan Fan , Qingyun Wang , May Fung , Heng Ji

Large language models (LLMs) have demonstrated significant capabilities in solving mathematical problems expressed in natural language. However, multilingual and culturally-grounded mathematical reasoning in low-resource languages lags…

Computation and Language · Computer Science 2026-04-21 Israel Abebe Azime , Tadesse Destaw Belay , Dietrich Klakow , Philipp Slusallek , Anshuman Chhabra

Culture fundamentally shapes people's reasoning, behavior, and communication. As people increasingly use generative artificial intelligence (AI) to expedite and automate personal and professional tasks, cultural values embedded in AI models…

Computation and Language · Computer Science 2024-09-20 Yan Tao , Olga Viberg , Ryan S. Baker , Rene F. Kizilcec

Language and culture are deeply intertwined, yet it has been unclear how and where multilingual large language models encode culture. Here, we build on an established methodology for identifying language-specific neurons to localize and…

Computation and Language · Computer Science 2025-11-12 Danial Namazifard , Lukas Galke Poech

Large Language Models (LLMs) are typically trained on data mixtures: most data come from web scrapes, while a small portion is curated from high-quality sources with dense domain-specific knowledge. In this paper, we show that when training…

Machine Learning · Computer Science 2026-05-12 Xinran Gu , Kaifeng Lyu , Jiazheng Li , Jingzhao Zhang

We demonstrate that large language models' (LLMs) mathematical reasoning is culturally sensitive: testing 14 models from Anthropic, OpenAI, Google, Meta, DeepSeek, Mistral, and Microsoft across six culturally adapted variants of the GSM8K…

Artificial Intelligence · Computer Science 2026-04-09 Aabid Karim , Abdul Karim , Bhoomika Lohana , Matt Keon , Jaswinder Singh , Abdul Sattar

Large Language Models (LLMs) like GPT-4 and Gemini have significantly advanced artificial intelligence by enabling machines to generate and comprehend human-like text. Despite their impressive capabilities, LLMs are not immune to…

Computation and Language · Computer Science 2024-12-19 Jiaxu Lou , Yifan Sun

Recently, retrieval augmentation and tool augmentation have demonstrated a remarkable capability to expand the internal memory boundaries of language models (LMs) by providing external context. However, internal memory and external context…

Computation and Language · Computer Science 2024-02-29 Zhuoran Jin , Pengfei Cao , Hongbang Yuan , Yubo Chen , Jiexin Xu , Huaijun Li , Xiaojian Jiang , Kang Liu , Jun Zhao

Large Language Models (LLMs) are increasingly deployed in high-stakes decision-making contexts. While prior work has shown that LLMs exhibit cognitive biases behaviorally, whether these biases correspond to identifiable internal…

Artificial Intelligence · Computer Science 2026-04-03 Fan Huang , Songheng Zhang , Haewoon Kwak , Jisun An

In this work, we study whether multilingual language models (MultiLMs) can transfer logical reasoning abilities to other languages when they are fine-tuned for reasoning in a different language. We evaluate the cross-lingual reasoning…

Computation and Language · Computer Science 2023-10-25 Negar Foroutan , Mohammadreza Banaei , Karl Aberer , Antoine Bosselut

Although the cultural (mis)alignment of Large Language Models (LLMs) has attracted increasing attention -- often framed in terms of cultural bias -- until recently there has been limited work on the design and development of datasets for…

Multimodal Large Language Models (MLLMs), trained primarily on English-centric data, frequently generate culturally inappropriate or misaligned responses in cross-cultural settings. To mitigate this, we introduce the task of cross-cultural…

Artificial Intelligence · Computer Science 2026-05-11 Zhen Zeng , Leijiang Gu , Feng Li , Jing Yu , Zenglin Shi

Annotation bias in NLP datasets remains a major challenge for developing multilingual Large Language Models (LLMs), particularly in culturally diverse settings. Bias from task framing, annotator subjectivity, and cultural mismatches can…

Computation and Language · Computer Science 2025-11-19 Xia Cui , Ziyi Huang , Naeemeh Adel

In this work, we survey the way in which classification is used as a sensemaking practice in cultural analytics, and assess where large language models can fit into this landscape. We identify ten tasks supported by publicly available…

Computation and Language · Computer Science 2024-10-17 David Bamman , Kent K. Chang , Li Lucy , Naitian Zhou

Large language models (LLMs) have shown a remarkable ability to learn and perform complex tasks through in-context learning (ICL). However, a comprehensive understanding of its internal mechanisms is still lacking. This paper explores the…

Computation and Language · Computer Science 2025-04-03 Joy Crosbie , Ekaterina Shutova

Vision-Language Models (VLMs) excel at visual description yet remain under-validated for cultural interpretation. Existing benchmarks assess perception without interpretation, and common evaluation proxies, such as automated metrics and…

Computation and Language · Computer Science 2026-02-26 Haorui Yu , Xuehang Wen , Fengrui Zhang , Qiufeng Yi

Pretraining language models on formal language can improve their acquisition of natural language. Which features of the formal language impart an inductive bias that leads to effective transfer? Drawing on insights from linguistics and…

Computation and Language · Computer Science 2025-05-28 Michael Y. Hu , Jackson Petty , Chuan Shi , William Merrill , Tal Linzen

We provide causal mechanistic validation that in-context learning (ICL) decomposes into two separable mechanisms: Task Schema (abstract task type recognition) and Binding (specific input-output associations). Through activation patching…

Machine Learning · Computer Science 2025-12-22 Chaeha Kim
‹ Prev 1 3 4 5 6 7 10 Next ›