English
Related papers

Related papers: Cultural Binding Heads in Language Models

200 papers

Large language models (LLMs) have shown impressive capabilities across tasks such as mathematics, coding, and reasoning, yet their learning ability, which is crucial for adapting to dynamic environments and acquiring new knowledge, remains…

Computation and Language · Computer Science 2025-12-29 Zhengyu Hu , Jianxun Lian , Zheyuan Xiao , Seraphina Zhang , Tianfu Wang , Nicholas Jing Yuan , Xing Xie , Hui Xiong

Large Language Models (LLMs) have been shown to be effective models of the human language system, with some models predicting most explainable variance of brain activity in current datasets. Even in untrained models, the representations…

Computation and Language · Computer Science 2024-06-24 Badr AlKhamissi , Greta Tuckute , Antoine Bosselut , Martin Schrimpf

As the reach of large language models (LMs) expands globally, their ability to cater to diverse cultural contexts becomes crucial. Despite advancements in multilingual capabilities, models are not designed with appropriate cultural nuances.…

Computation and Language · Computer Science 2024-03-21 Tarek Naous , Michael J. Ryan , Alan Ritter , Wei Xu

Alignment training has tradeoffs: it helps language models (LMs) gain in reasoning and instruction following but might lose out on skills such as creativity and calibration, where unaligned base models are better at. We aim to make the best…

Computation and Language · Computer Science 2025-10-14 Shangbin Feng , Wenhao Yu , Yike Wang , Hongming Zhang , Yulia Tsvetkov , Dong Yu

Large Language Models (LLMs) need to adapt their predictions to diverse cultural contexts to benefit diverse communities across the world. While previous efforts have focused on single-LLM, single-turn approaches, we propose to exploit the…

Computation and Language · Computer Science 2025-09-03 Dayeon Ki , Rachel Rudinger , Tianyi Zhou , Marine Carpuat

Large language models (LLMs) face challenges in aligning with diverse cultural values despite their remarkable performance in generation, which stems from inherent monocultural biases and difficulties in capturing nuanced cultural…

Computation and Language · Computer Science 2026-01-05 Jiahao Yuan , Zixiang Di , Shangzixin Zhao , Zhiqing Cui , Hanqing Wang , Guisong Yang , Usman Naseem

Language models (LMs) have been reported to implicitly encode character-level information, despite not being explicitly provided during training. However, the mechanisms underlying this phenomenon remain largely unexplored. To reveal the…

Computation and Language · Computer Science 2026-02-06 Soma Sato , Ryohei Sasano

Large language models (LLMs), even when specifically trained to process long input contexts, struggle to capture relevant information located in the middle of their input. This phenomenon has been known as the lost-in-the-middle problem. In…

Recent studies have highlighted the presence of cultural biases in Large Language Models (LLMs), yet often lack a robust methodology to dissect these phenomena comprehensively. Our work aims to bridge this gap by delving into the Food…

Computation and Language · Computer Science 2025-02-07 Li Zhou , Taelin Karidi , Wanlong Liu , Nicolas Garneau , Yong Cao , Wenyu Chen , Haizhou Li , Daniel Hershcovich

In human cognition, the binding problem describes the open question of how the brain flexibly integrates diverse information into cohesive object representations. Analogously, in machine learning, there is a pursuit for models capable of…

Machine Learning · Computer Science 2024-02-09 Sindy Löwe , Francesco Locatello , Max Welling

Despite the success of Large Language Models (LLMs) in table understanding, their internal mechanisms remain unclear. In this paper, we conduct an empirical study on 16 LLMs, covering general LLMs, specialist tabular LLMs, and…

Computation and Language · Computer Science 2026-03-17 Jia Wang , Chuanyu Qin , Mingyu Zheng , Qingyi Si , Peize Li , Zheng Lin

Cultural representation in Large Language Model (LLM) outputs has primarily been evaluated through the proxies of cultural diversity and factual accuracy. However, a crucial gap remains in assessing cultural alignment: the degree to which…

Computation and Language · Computer Science 2026-04-07 Erin MacMurray van Liemt , Aida Davani , Sinchana Kumbale , Neha Dixit , Sunipa Dev

Large language models (LLMs) are often described as multilingual because they can understand and respond in many languages. However, speaking a language is not the same as reasoning within a culture. This distinction motivates a critical…

Computation and Language · Computer Science 2026-04-07 Yuan Chang , Jiaming Qu , Zhu Li

Vision-language models (VLMs) can respond to queries about images in many languages. However, beyond language, culture affects how we see things. For example, individuals from Western cultures focus more on the central figure in an image…

Computation and Language · Computer Science 2025-03-04 Amith Ananthram , Elias Stengel-Eskin , Mohit Bansal , Kathleen McKeown

The field of cultural NLP has recently experienced rapid growth, driven by a pressing need to ensure that language technologies are effective and safe across a pluralistic user base. This work has largely progressed without a shared…

Computation and Language · Computer Science 2025-07-21 Naitian Zhou , David Bamman , Isaac L. Bleaman

Language models retain a significant amount of world knowledge from their pre-training stage. This allows knowledgeable models to be applied to knowledge-intensive tasks prevalent in information retrieval, such as ranking or question…

Computation and Language · Computer Science 2023-06-13 Jonas Wallat , Tianyi Zhang , Avishek Anand

With the rapid development of large language models (LLMs), they have significantly improved efficiency across a wide range of domains. However, recent studies have revealed that LLMs often exhibit gender bias, leading to serious social…

Computation and Language · Computer Science 2025-06-17 Xiaoqing Cheng , Hongying Zan , Lulu Kong , Jinwang Song , Min Peng

Theory of Mind (ToM) - the ability to attribute beliefs and intents to others - is fundamental for social intelligence, yet Vision-Language Model (VLM) evaluations remain largely Western-centric. In this work, we introduce CulturalToM-VQA,…

Computation and Language · Computer Science 2026-01-08 Zabir Al Nazi , GM Shahariar , Md. Abrar Hossain , Wei Peng

Large Language Models (LLMs) exhibit catastrophic performance degradation when processing contexts approaching certain critical thresholds, even when information remains relevant. This intelligence degradation-defined as over 30% drop in…

Computation and Language · Computer Science 2026-01-23 Weiwei Wang , Jiyong Min , Weijie Zou

Attention layers are widely used in natural language processing (NLP) and are beginning to influence computer vision architectures. Training very large transformer models allowed significant improvement in both fields, but once trained,…

Machine Learning · Computer Science 2021-05-21 Jean-Baptiste Cordonnier , Andreas Loukas , Martin Jaggi