Publications de Boi Faltings | EPFL Graph Search

Modelleyen: Continual Learning and Planning via Structured Modelling of Environment Dynamics

The current machine learning paradigm relies on continuous representations and fixed neural network architectures to approximate environmental structures, leading to challenges with continual learning, internal structure design, and goal-directed behavior ...

Springer Science and Business Media Deutschland GmbH2025

A Logical Fallacy-Informed Framework for Argument Generation

Boi Faltings, Robert West, Antoine Bosselut, Luca Mouchel, Debjit Paul

Despite the remarkable performance of large language models (LLMs), they still struggle with generating logically sound arguments, resulting in potential risks such as spreading misinformation. An important factor contributing to LLMs' suboptimal performan ...

Association for Computational Linguistics2025

On the Parallels Between Evolutionary Theory and the State of AI

Boi Faltings, Zeki Doruk Erden

This article critically examines the foundational principles of contemporary AI methods, exploring the limitations that hinder its potential. We draw parallels between the modern AI landscape and the 20th-century Modern Synthesis in evolutionary biology, a ...

ACM2025

Exploring Defeasibility in Causal Reasoning

Boi Faltings, Antoine Bosselut, Debjit Paul, Mahammad Ismayilzada, Lazar Milikic

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 effect should increase or decrease with the incorporation of strengthening argume ...

2024

Differentially private multi-agent constraint optimization

Boi Faltings, Aleksei Triastcyn, Sankarshan Damle, Sujit Prakash Gujar

Distributed constraint optimization (DCOP) is a framework in which multiple agents with private constraints (or preferences) cooperate to achieve a common goal optimally. DCOPs are applicable in several multi-agent coordination/allocation problems, such as ...

Springer2024

Peer Neighborhood Mechanisms: A Framework for Mechanism Generalization

Boi Faltings

Peer prediction incentive mechanisms for crowdsourcing are generally limited to eliciting samples from categorical distributions. Prior work on extending peer prediction to arbitrary distributions has largely relied on assumptions on the structures of the ...

2024

Making Reasoning Matter: Measuring and Improving Faithfulness of Chain-of-Thought Reasoning

Boi Faltings, Robert West, Antoine Bosselut, Debjit Paul

Large language models (LLMs) have been shown to perform better when asked to reason step-by-step before answering a question. However, it is unclear to what degree the model's final answer is faithful to the stated reasoning steps. In this paper, we perfor ...

Association for Computational Linguistics (ACL)2024

Unveiling the Art of Heading Design: A Harmonious Blend of Summarization, Neology, and Algorithm

Boi Faltings

Crafting an appealing heading is crucial for attracting readers and marketing work or products. A popular way is to summarize the main idea with a refined description and a memorable acronym. However, there lacks a systematic study and a formal benchmark i ...

Association for Computational Linguistics2024

The Odyssey of Commonsense Causality: From Foundational Benchmarks to Cutting-Edge Reasoning

Boi Faltings

Understanding commonsense causality is a unique mark of intelligence for humans. It helps people understand the principles of the real world better and benefits the decisionmaking process related to causation. For instance, commonsense causality is crucial ...

Association for Computational Linguistics2024

LIA: Privacy-Preserving Data Quality Evaluation in Federated Learning Using a Lazy Influence Approximation

Boi Faltings, Ljubomir Rokvic

In Federated Learning, it is crucial to handle low-quality, corrupted, or malicious data. However, traditional data valuation methods are not suitable due to privacy concerns. To address this, we propose a simple yet effective approach that utilizes a new ...

Institute of Electrical and Electronics Engineers Inc.2024