2.3k citations · 2.9k across the 59 of their papers we have counts for
67 papers
Latent Taxonomies: How Property Induction Develops in Language Model Pre-training
Jan Sobotka, Ekaterina Goliakova, Marcin Detyniecki +2
When told that robins have sesamoid bones, people are far more prone to extend the property to sparrows than to whales. This behavior, called category-based property induction, is…
Do LLMs Game Formalization? Evaluating Faithfulness in Logical Reasoning
Kyuhee Kim, Auguste Poiroux, Antoine Bosselut
Formal verification guarantees proof validity but not formalization faithfulness. For natural-language logical reasoning, where models construct axiom systems from scratch without…
Large Language Models Align with the Human Brain during Creative Thinking
Mete Ismayilzada, Simone A. Luchini, Abdulkadir Gokce +5
Creative thinking is a fundamental aspect of human cognition, and divergent thinking-the capacity to generate novel and varied ideas-is widely regarded as its core generative engin…
CresOWLve: Benchmarking Creative Problem-Solving Over Real-World Knowledge
Mete Ismayilzada, Renqing Cuomao, Daniil Yurshevich +3
Creative problem-solving requires combining multiple cognitive abilities, including logical reasoning, lateral thinking, analogy-making, and commonsense knowledge, to discover insi…
AI Meets Mathematics Education: A Case Study on Supporting an Instructor in a Large Mathematics Class with Context-Aware AI
Jérémy Barghorn, Anna Sotnikova, Sacha Friedli +1
Large-enrollment university courses face persistent challenges in providing timely and scalable instructional support. While generative AI holds promise, its effective use depends…
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…
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…
ComperDial: Commonsense Persona-grounded Dialogue Dataset and Benchmark
Hiromi Wakaki, Yuki Mitsufuji, Yoshinori Maeda +5
We propose a new benchmark, ComperDial, which facilitates the training and evaluation of evaluation metrics for open-domain dialogue systems. ComperDial consists of human-scored re…
Reliable Evaluation and Benchmarks for Statement Autoformalization
Auguste Poiroux, Gail Weiss, Viktor Kunčak +1
Evaluating statement autoformalization, translating natural language mathematics into formal languages like Lean 4, remains a significant challenge, with few metrics, datasets, and…
Course Recommender Systems Need to Consider the Job Market
Jibril Frej, Anna Dai, Syrielle Montariol +2
Current course recommender systems primarily leverage learner-course interactions, course content, learner preferences, and supplementary course details like instructor, institutio…
ConGeo: Robust Cross-view Geo-localization across Ground View Variations
Li Mi, Chang Xu, Javiera Castillo-Navarro +4
Cross-view geo-localization aims at localizing a ground-level query image by matching it to its corresponding geo-referenced aerial view. In real-world scenarios, the task requires…
Complex Reasoning over Logical Queries on Commonsense Knowledge Graphs
Tianqing Fang, Zeming Chen, Yangqiu Song +1
Event commonsense reasoning requires the ability to reason about the relationship between events, as well as infer implicit context underlying that relationship. However, data scar…
"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…
ConVQG: Contrastive Visual Question Generation with Multimodal Guidance
Li Mi, Syrielle Montariol, Javiera Castillo-Navarro +3
Asking questions about visual environments is a crucial way for intelligent agents to understand rich multi-faceted scenes, raising the importance of Visual Question Generation (VQ…
Rethinking Skill Extraction in the Job Market Domain using Large Language Models
Khanh Cao Nguyen, Mike Zhang, Syrielle Montariol +1
Skill Extraction involves identifying skills and qualifications mentioned in documents such as job postings and resumes. The task is commonly tackled by training supervised models…
JOBSKAPE: A Framework for Generating Synthetic Job Postings to Enhance Skill Matching
Antoine Magron, Anna Dai, Mike Zhang +2
Recent approaches in skill matching, employing synthetic training data for classification or similarity model training, have shown promising results, reducing the need for time-con…
DiffuCOMET: Contextual Commonsense Knowledge Diffusion
Silin Gao, Mete Ismayilzada, Mengjie Zhao +3
Inferring contextually-relevant and diverse commonsense to understand narratives remains challenging for knowledge models. In this work, we develop a series of knowledge models, Di…
Efficient Tool Use with Chain-of-Abstraction Reasoning
Silin Gao, Jane Dwivedi-Yu, Ping Yu +7
To achieve faithful reasoning that aligns with human expectations, large language models (LLMs) need to ground their reasoning to real-world knowledge (e.g., web facts, math and ph…
Evaluating Language Model Agency through Negotiations
Tim R. Davidson, Veniamin Veselovsky, Martin Josifoski +4
We introduce an approach to evaluate language model (LM) agency using negotiation games. This approach better reflects real-world use cases and addresses some of the shortcomings o…
Exploring Defeasibility in Causal Reasoning
Shaobo Cui, Lazar Milikic, Yiyang Feng +4
Defeasibility in causal reasoning implies that the causal relationship between cause and effect can be strengthened or weakened. Namely, the causal strength between cause and effec…
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…
MEDITRON-70B: Scaling Medical Pretraining for Large Language Models
Zeming Chen, Alejandro Hernández Cano, Angelika Romanou +17
Large language models (LLMs) can potentially democratize access to medical knowledge. While many efforts have been made to harness and improve LLMs' medical knowledge and reasoning…
CRAB: Assessing the Strength of Causal Relationships Between Real-world Events
Angelika Romanou, Syrielle Montariol, Debjit Paul +3
Understanding narratives requires reasoning about the cause-and-effect relationships between events mentioned in the text. While existing foundation models yield impressive results…