Antoine Bosselut

Crosscoding Through Time: Tracking Emergence & Consolidation Of Linguistic Representations Throughout LLM Pretraining ACL 2026 DRIVINGVQA: A Dataset for Interleaved Visual Chain-of-Thought in Real-World Driving Scenarios EACL 2026 ConLID: Supervised Contrastive Learning for Low-Resource Language Identification EACL 2026 Tracking the Limits of Knowledge Propagation: How LLMs Fail at Multi-Step Reasoning with Conflicting Knowledge EACL 2026 Apertus: Democratizing Open and Compliant LLMs for Global Language Environments ACL 2026 Parity-Aware Byte-Pair Encoding: Improving Cross-lingual Fairness in Tokenization ACL 2026 From Language to Cognition: How LLMs Outgrow the Human Language Network EMNLP 2025 Context is Gold to find the Gold Passage: Evaluating and Training Contextual Document Embeddings EMNLP 2025 Reliable Evaluation and Benchmarks for Statement Autoformalization EMNLP 2025 The LLM Language Network: A Neuroscientific Approach for Identifying Causally Task-Relevant Units NAACL 2025 PICLe: Pseudo-annotations for In-Context Learning in Low-Resource Named Entity Detection NAACL 2025 A Logical Fallacy-Informed Framework for Argument Generation NAACL 2025 Evaluating Morphological Compositional Generalization in Large Language Models NAACL 2025 INCLUDE: Evaluating Multilingual Language Understanding with Regional Knowledge ICLR 2025 Global MMLU: Understanding and Addressing Cultural and Linguistic Biases in Multilingual Evaluation ACL 2025 Challenges for AI in Multimodal STEM Assessments: a Human-AI Comparison ACL 2025 Efficient Tool Use with Chain-of-Abstraction Reasoning COLING 2025 VinaBench: Benchmark for Faithful and Consistent Visual Narratives CVPR 2025 GeoExplorer: Active Geo-localization with Curiosity-Driven Exploration ICCV 2025 RLMEval: Evaluating Research-Level Neural Theorem Proving EMNLP 2025 Creative Preference Optimization EMNLP 2025 CAVE : Detecting and Explaining Commonsense Anomalies in Visual Environments EMNLP 2025 Making Reasoning Matter: Measuring and Improving Faithfulness of Chain-of-Thought Reasoning EMNLP 2024 ConVQG: Contrastive Visual Question Generation with Multimodal Guidance AAAI 2024 REFINER: Reasoning Feedback on Intermediate Representations EACL 2024 Rethinking Skill Extraction in the Job Market Domain using Large Language Models EACL 2024 JobSkape: A Framework for Generating Synthetic Job Postings to Enhance Skill Matching EACL 2024 ConGeo: Robust Cross-view Geo-localization across Ground View Variations ECCV 2024 “Flex Tape Can’t Fix That”: Bias and Misinformation in Edited Language Models EMNLP 2024 Let Me Teach You: Pedagogical Foundations of Feedback for Language Models EMNLP 2024 Discovering Knowledge-Critical Subnetworks in Pretrained Language Models EMNLP 2024 DiffuCOMET: Contextual Commonsense Knowledge Diffusion ACL 2024 Complex Reasoning over Logical Queries on Commonsense Knowledge Graphs ACL 2024 Exploring Defeasibility in Causal Reasoning ACL 2024 EPFL-MAKE at “Discharge Me!”: An LLM System for Automatically Generating Discharge Summaries of Clinical Electronic Health Record ACL 2024 kogito: A Commonsense Knowledge Inference Toolkit EACL 2023 CAR: Conceptualization-Augmented Reasoner for Zero-Shot Commonsense Question Answering EMNLP 2023 RECKONING: Reasoning through Dynamic Knowledge Encoding NIPS 2023 DISCO: Distilling Counterfactuals with Large Language Models ACL 2023 PeaCoK: Persona Commonsense Knowledge for Consistent and Engaging Narratives ACL 2023 Mitigating Label Biases for In-context Learning ACL 2023 Breaking the Language Barrier: Improving Cross-Lingual Reasoning with Structured Self-Attention EMNLP 2023 Towards a Mechanistic Interpretation of Multi-Step Reasoning Capabilities of Language Models EMNLP 2023 CRoW: Benchmarking Commonsense Reasoning in Real-World Tasks EMNLP 2023 CRAB: Assessing the Strength of Causal Relationships Between Real-world Events EMNLP 2023 Deep Bidirectional Language-Knowledge Graph Pretraining NIPS 2022 Synthetic Disinformation Attacks on Automated Fact Verification Systems AAAI 2022 Conditional set generation using Seq2seq models EMNLP 2022 Discovering Language-neutral Sub-networks in Multilingual Language Models EMNLP 2022 ComFact: A Benchmark for Linking Contextual Commonsense Knowledge EMNLP 2022 Fast Model Editing at Scale ICLR 2022 GreaseLM: Graph REASoning Enhanced Language Models ICLR 2022 Memory-Based Model Editing at Scale ICML 2022 The GEM Benchmark: Natural Language Generation, its Evaluation and Metrics IJCNLP 2021 Discourse Understanding and Factual Consistency in Abstractive Summarization EACL 2021 Edited Media Understanding Frames: Reasoning About the Intent and Implications of Visual Misinformation IJCNLP 2021 On-the-Fly Attention Modulation for Neural Generation IJCNLP 2021 Conversational Multi-Hop Reasoning with Neural Commonsense Knowledge and Symbolic Logic Rules EMNLP 2021 (Comet-) Atomic 2020: On Symbolic and Neural Commonsense Knowledge Graphs AAAI 2021 Dynamic Neuro-Symbolic Knowledge Graph Construction for Zero-shot Commonsense Question Answering AAAI 2021 QA-GNN: Reasoning with Language Models and Knowledge Graphs for Question Answering NAACL 2021 “I’m Not Mad”: Commonsense Implications of Negation and Contradiction NAACL 2021 On-the-Fly Attention Modulation for Neural Generation ACL 2021 Edited Media Understanding Frames: Reasoning About the Intent and Implications of Visual Misinformation ACL 2021 The GEM Benchmark: Natural Language Generation, its Evaluation and Metrics ACL 2021 Commonsense Reasoning for Natural Language Processing ACL 2020 The Amazing World of Neural Language Generation EMNLP 2020 Commonsense Knowledge Base Completion with Structural and Semantic Context AAAI 2020 Back to the Future: Unsupervised Backprop-based Decoding for Counterfactual and Abductive Commonsense Reasoning EMNLP 2020 WIQA: A dataset for “What if...” reasoning over procedural text EMNLP 2019 Counterfactual Story Reasoning and Generation EMNLP 2019 Everything Happens for a Reason: Discovering the Purpose of Actions in Procedural Text EMNLP 2019 Everything Happens for a Reason: Discovering the Purpose of Actions in Procedural Text IJCNLP 2019 Counterfactual Story Reasoning and Generation IJCNLP 2019 WIQA: A dataset for “What if...” reasoning over procedural text IJCNLP 2019 Proceedings of the Workshop on Methods for Optimizing and Evaluating Neural Language Generation NAACL 2019 Be Consistent! Improving Procedural Text Comprehension using Label Consistency NAACL 2019 COMET: Commonsense Transformers for Automatic Knowledge Graph Construction ACL 2019 Deep Communicating Agents for Abstractive Summarization NAACL 2018 Modeling Naive Psychology of Characters in Simple Commonsense Stories ACL 2018 Learning to Write with Cooperative Discriminators ACL 2018 Reasoning about Actions and State Changes by Injecting Commonsense Knowledge EMNLP 2018 Discourse-Aware Neural Rewards for Coherent Text Generation NAACL 2018 Simulating Action Dynamics with Neural Process Networks ICLR 2018 Learning Prototypical Event Structure from Photo Albums ACL 2016