Papers by Badr AlKhamissi
“Flex Tape Can’t Fix That”: Bias and Misinformation in Edited Language Models (2024.emnlp-main)
Copied to clipboard
| Challenge: | Weight-based model editing methods can unintentionally alter unrelated parametric knowledge representations, potentially increasing the risk of harm. |
| Approach: | They propose a benchmark dataset for measuring bias amplification of model editing methods for demographic traits such as race, geographic origin, and gender. |
| Outcome: | The proposed methods can unintentionally alter unrelated parametric knowledge representations, potentially increasing the risk of harm. |
The LLM Language Network: A Neuroscientific Approach for Identifying Causally Task-Relevant Units (2025.naacl-long)
Copied to clipboard
| Challenge: | Recent advances in large language models (LLMs) have revealed their potential to perform far more than language processing tasks, showcasing abilities in reasoning and problem-solving. |
| Approach: | They identify language-selective units within 18 popular LLMs using the same localization approach that is used in neuroscience. |
| Outcome: | The proposed method shows that language-selective units are more aligned to brain recordings from the human language system than random units. |
Hire Your Anthropologist! Rethinking Culture Benchmarks Through an Anthropological Lens (2026.findings-eacl)
Copied to clipboard
| Challenge: | anthropological accounts of culture often focus on static facts or homogeneous values . large language models are being implemented in translation systems, educational tools and search engines . |
| Approach: | They propose to categorize how benchmarks frame culture such as knowledge, preference, performance, or bias. |
| Outcome: | The proposed framework categorizes how benchmarks frame culture, such as knowledge, preference, performance, or bias. |
From Language to Cognition: How LLMs Outgrow the Human Language Network (2025.emnlp-main)
Copied to clipboard
Badr AlKhamissi, Greta Tuckute, Yingtian Tang, Taha Osama A Binhuraib, Antoine Bosselut, Martin Schrimpf
| Challenge: | Large language models exhibit remarkable similarity to neural activity in the human language network, but their properties remain unclear. |
| Approach: | They benchmark 34 training checkpoints spanning 300B tokens across 8 different model sizes . they find that brain alignment tracks the development of formal linguistic competence more closely than functional linguistic competency. |
| Outcome: | The results show that large language models exhibit similarity to human language networks . they show that the correlation between next-word prediction and brain alignment fades once models surpass human language proficiency. |
ALERT: Adapt Language Models to Reasoning Tasks (2023.acl-long)
Copied to clipboard
Ping Yu, Tianlu Wang, Olga Golovneva, Badr AlKhamissi, Siddharth Verma, Zhijing Jin, Gargi Ghosh, Mona Diab, Asli Celikyilmaz
| Challenge: | Large language models have shown increasing in-context learning capabilities with scaling up the model and data sizes. |
| Approach: | They propose a benchmark and suite of analyses to evaluate reasoning skills of large language models. |
| Outcome: | The proposed model compares pre-trained and fine-tuned models on tasks that require reasoning skills to solve. |
Apertus: Democratizing Open and Compliant LLMs for Global Language Environments (2026.acl-long)
Copied to clipboard
Alejandro Hernández-Cano, Alexander Hägele, Allen Hao Huang, Angelika Romanou, Antoni-Joan Solergibert, Barna Pásztor, Bettina Messmer, Dhia Garbaya, Eduard Frank Ďurech, Ido Hakimi, Juan Garcia Giraldo, Mete Ismayilzada, Negar Foroutan, Skander Moalla, Tiancheng Chen, Vinko Sabolčec, Yixuan Xu, Michael Aerni, Badr AlKhamissi, Inés Altemir Marinas, Mohammad Hossein Amani, Matin Ansaripour, Ilia Badanin, Harold Benoit, Emanuela Boros, Nicholas John Browning, Fabian Bösch, Maximilian Böther, Niklas Canova, Camille Challier, Clément Charmillot, Jonathan Coles, Jan Milan Deriu, Arnout Devos, Lukas Drescher, Daniil Dzenhaliou, Maud Ehrmann, Dongyang Fan, Simin Fan, Silin Gao, Miguel Gila, María Grandury, Diba Hashemi, Alexander Miserlis Hoyle, Jiaming Jiang, Mark Klein, Andrei Kucharavy, Anastasiia Kucherenko, Frederike Lübeck, Roman Machacek, Theofilos Ioannis Manitaras, Andreas Marfurt, Kyle Matoba, Simon Matrenok, Henrique Mendonça, Fawzi Roberto Mohamed, Syrielle Montariol, Luca Mouchel, Sven Najem-Meyer, Jingwei Ni, Gennaro Oliva, Matteo Pagliardini, Elia Palme, Andrei Panferov, Léo Paoletti, Marco Passerini, Ivan Pavlov, Auguste Poiroux, Kaustubh Ponkshe, Nathan Ranchin, Javier Rando, Mathieu Sauser, Jakhongir Saydaliev, Mukhammadali Sayfiddinov, Marian Schneider, Stefano Schuppli, Marco Scialanga, Andrei Semenov, Kumar Shridhar, Raghav Singhal, Anna Sotnikova, Alexander Sternfeld, Ayush Kumar Tarun, Paul Teiletche, Jannis Vamvas, Xiaozhe Yao, Hao Zhao, Alexander Ilic, Ana Klimovic, Andreas Krause, Caglar Gulcehre, David Rosenthal, Elliott Ash, Florian Tramèr, Joost VandeVondele, Livio Veraldi, Martin Rajman, Thomas C. Schulthess, Torsten Hoefler, Antoine Bosselut, Martin Jaggi, Imanol Schlag
| Challenge: | Apertus is a fully open suite of large language models (LLMs) designed to address responsibility shortcomings in today’s open model ecosystem, namely data responsibility and global representation. |
| Approach: | They propose to release a fully open suite of large language models (LLMs) that address data responsibility and global representation shortcomings in today’s open model ecosystem. |
| Outcome: | The proposed model is pretrained on openly available data and suppresses verbatim recall of data while retaining task performance. |
Investigating Cultural Alignment of Large Language Models (2024.acl-long)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) are used to represent the diversity of human experience and culturally sensitive topics. |
| Approach: | They propose a method leveraging anthropological reasoning to enhance cultural alignment by prompting LLMs with different pretraining data mixtures in Arabic and English. |
| Outcome: | The proposed method enables users to better represent the diversity of human experience and the plurality of different cultures. |
ToKen: Task Decomposition and Knowledge Infusion for Few-Shot Hate Speech Detection (2022.emnlp-main)
Copied to clipboard
Badr AlKhamissi, Faisal Ladhak, Srinivasan Iyer, Veselin Stoyanov, Zornitsa Kozareva, Xian Li, Pascale Fung, Lambert Mathias, Asli Celikyilmaz, Mona Diab
| Challenge: | Hate speech detection is complex and requires commonsense reasoning and social nuance . prior work has shown that even humans cannot achieve a high agreement on whether a post constitutes HS . |
| Approach: | They frame a few-shot learning task to decompose a hate speech detection task into its "constituent" parts. they show that infusing commonsense knowledge from reasoning datasets improves the performance even further. |
| Outcome: | The proposed method outperforms baseline methods in the 16-shot case. |
Depth-Wise Attention (DWAtt): A Layer Fusion Method for Data-Efficient Classification (2024.lrec-main)
Copied to clipboard
| Challenge: | Language Models pretrained on large textual data can encode different types of knowledge simultaneously. |
| Approach: | They propose a method to re-surface intermediate layer features from non-final layers by combining them with a concatenation-based layer fusion method. |
| Outcome: | The proposed method outperforms the baseline model on large datasets and shows 3.68 9.73% gain. |