63 citations · 122 across the 32 of their papers we have counts for
25 papers · 1 filter
Lingua Franca or Probing Artifact? Rethinking Latent Language in Multilingual LLMs
Deniz Bayazit, Badr AlKhamissi, Antoine Bosselut
Latent language identification is often used to argue that multilingual language models route computation through language-specific states, such as English pivots. However, existin…
Hire Your Anthropologist! Rethinking Culture Benchmarks Through an Anthropological Lens
Mai AlKhamissi, Yunze Xiao, Badr AlKhamissi +1
Cultural evaluation of large language models has become increasingly important, yet current benchmarks often reduce culture to static facts or homogeneous values. This view conflic…
Inducing Dyslexia in Vision Language Models
Melika Honarmand, Ayati Sharma, Badr AlKhamissi +2
Dyslexia, a neurodevelopmental disorder characterized by persistent reading difficulties, is often linked to reduced activity of the visual word form area (VWFA) in the ventral occ…
Apertus: Democratizing Open and Compliant LLMs for Global Language Environments
Project Apertus, Alejandro Hernández-Cano, Alexander Hägele +100
We present Apertus, a fully open suite of large language models (LLMs) designed to address two systemic shortcomings in today's open model ecosystem: data compliance and multilingu…
Evaluating Contrast Localizer for Identifying Causal Units in Social & Mathematical Tasks in Language Models
Yassine Jamaa, Badr AlKhamissi, Satrajit Ghosh +1
This work adapts a neuroscientific contrast localizer to pinpoint causally relevant units for Theory of Mind (ToM) and mathematical reasoning tasks in large language models (LLMs)…
From Language to Cognition: How LLMs Outgrow the Human Language Network
Badr AlKhamissi, Greta Tuckute, Yingtian Tang +3
Large language models (LLMs) exhibit remarkable similarity to neural activity in the human language network. However, the key properties of language shaping brain-like representati…
The LLM Language Network: A Neuroscientific Approach for Identifying Causally Task-Relevant Units
Badr AlKhamissi, Greta Tuckute, Antoine Bosselut +1
Large language models (LLMs) exhibit remarkable capabilities on not just language tasks, but also various tasks that are not linguistic in nature, such as logical reasoning and soc…
TopoLM: brain-like spatio-functional organization in a topographic language model
Neil Rathi, Johannes Mehrer, Badr AlKhamissi +3
Neurons in the brain are spatially organized such that neighbors on tissue often exhibit similar response profiles. In the human language system, experimental studies have observed…
Rational Metareasoning for Large Language Models
C. Nicolò De Sabbata, Theodore R. Sumers, Badr AlKhamissi +2
Being prompted to engage in reasoning has emerged as a core technique for using large language models (LLMs), deploying additional inference-time compute to improve task performanc…
Khattat: Enhancing Readability and Concept Representation of Semantic Typography
Ahmed Hussein, Alaa Elsetohy, Sama Hadhoud +3
Designing expressive typography that visually conveys a word's meaning while maintaining readability is a complex task, known as semantic typography. It involves selecting an idea,…
Brain-Like Language Processing via a Shallow Untrained Multihead Attention Network
Badr AlKhamissi, Greta Tuckute, Antoine Bosselut +1
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…
"Flex Tape Can't Fix That": Bias and Misinformation in Edited Language Models
Karina Halevy, Anna Sotnikova, Badr AlKhamissi +2
Model editing has emerged as a cost-effective strategy to update knowledge stored in language models. However, model editing can have unintended consequences after edits are applie…
Investigating Cultural Alignment of Large Language Models
Badr AlKhamissi, Muhammad ElNokrashy, Mai AlKhamissi +1
The intricate relationship between language and culture has long been a subject of exploration within the realm of linguistic anthropology. Large Language Models (LLMs), promoted a…
A Context-Contrastive Inference Approach To Partial Diacritization
Muhammad ElNokrashy, Badr AlKhamissi
Diacritization plays a pivotal role in improving readability and disambiguating the meaning of Arabic texts. Efforts have so far focused on marking every eligible character (Full D…
Instruction-tuning Aligns LLMs to the Human Brain
Khai Loong Aw, Syrielle Montariol, Badr AlKhamissi +2
Instruction-tuning is a widely adopted finetuning method that enables large language models (LLMs) to generate output that more closely resembles human responses. However, no studi…
Rosetta Stone at KSAA-RD Shared Task: A Hop From Language Modeling To Word--Definition Alignment
Ahmed ElBakry, Mohamed Gabr, Muhammad ElNokrashy +1
A Reverse Dictionary is a tool enabling users to discover a word based on its provided definition, meaning, or description. Such a technique proves valuable in various scenarios, a…
Taqyim: Evaluating Arabic NLP Tasks Using ChatGPT Models
Zaid Alyafeai, Maged S. Alshaibani, Badr AlKhamissi +3
Large language models (LLMs) have demonstrated impressive performance on various downstream tasks without requiring fine-tuning, including ChatGPT, a chat-based model built on top…
OPT-R: Exploring the Role of Explanations in Finetuning and Prompting for Reasoning Skills of Large Language Models
Badr AlKhamissi, Siddharth Verma, Ping Yu +3
In this paper, we conduct a thorough investigation into the reasoning capabilities of Large Language Models (LLMs), focusing specifically on the Open Pretrained Transformers (OPT)…
ALERT: Adapting Language Models to Reasoning Tasks
Ping Yu, Tianlu Wang, Olga Golovneva +6
Current large language models can perform reasonably well on complex tasks that require step-by-step reasoning with few-shot learning. Are these models applying reasoning skills th…
Depth-Wise Attention (DWAtt): A Layer Fusion Method for Data-Efficient Classification
Muhammad ElNokrashy, Badr AlKhamissi, Mona Diab
Language Models pretrained on large textual data have been shown to encode different types of knowledge simultaneously. Traditionally, only the features from the last layer are use…
Meta AI at Arabic Hate Speech 2022: MultiTask Learning with Self-Correction for Hate Speech Classification
Badr AlKhamissi, Mona Diab
In this paper, we tackle the Arabic Fine-Grained Hate Speech Detection shared task and demonstrate significant improvements over reported baselines for its three subtasks. The task…
ToKen: Task Decomposition and Knowledge Infusion for Few-Shot Hate Speech Detection
Badr AlKhamissi, Faisal Ladhak, Srini Iyer +7
Hate speech detection is complex; it relies on commonsense reasoning, knowledge of stereotypes, and an understanding of social nuance that differs from one culture to the next. It…
A Review on Language Models as Knowledge Bases
Badr AlKhamissi, Millicent Li, Asli Celikyilmaz +2
Recently, there has been a surge of interest in the NLP community on the use of pretrained Language Models (LMs) as Knowledge Bases (KBs). Researchers have shown that LMs trained o…
Adapting MARBERT for Improved Arabic Dialect Identification: Submission to the NADI 2021 Shared Task
Badr AlKhamissi, Mohamed Gabr, Muhammad ElNokrashy +1
In this paper, we tackle the Nuanced Arabic Dialect Identification (NADI) shared task (Abdul-Mageed et al., 2021) and demonstrate state-of-the-art results on all of its four subtas…