PPaperPicks

Antoine Bosselut

35 papers at tracked venues · 17 at CORE A* · active 20242026

Venues

Frequent coauthors

Papers

  1. AI meets Mathematics Education: Supporting Instructors in Large Mathematics Classes with Context-Aware AI
    CHI 2026 ·
    Jérémy Valentin Barghorn
  2. Apertus: Democratizing Open and Compliant LLMs for Global Language Environments
    ACL 2026 ·
    Alejandro Hernández-Cano
  3. ConLID: Supervised Contrastive Learning for Low-Resource Language Identification
  4. Crosscoding Through Time: Tracking Emergence & Consolidation Of Linguistic Representations Throughout LLM Pretraining
  5. DRIVINGVQA: A Dataset for Interleaved Visual Chain-of-Thought in Real-World Driving Scenarios
  6. Parity-Aware Byte-Pair Encoding: Improving Cross-lingual Fairness in Tokenization
  7. Tracking the Limits of Knowledge Propagation: How LLMs Fail at Multi-Step Reasoning with Conflicting Knowledge
  8. A Logical Fallacy-Informed Framework for Argument Generation
  9. CAVE : Detecting and Explaining Commonsense Anomalies in Visual Environments
  10. Context is Gold to find the Gold Passage: Evaluating and Training Contextual Document Embeddings
  11. Creative Preference Optimization
  12. Evaluating Morphological Compositional Generalization in Large Language Models
  13. For Better or for Worse, Transformers Seek Patterns for Memorization
  14. From Language to Cognition: How LLMs Outgrow the Human Language Network
  15. GeoExplorer: Active Geo-Localization with Curiosity-Driven Exploration
  16. Global MMLU: Understanding and Addressing Cultural and Linguistic Biases in Multilingual Evaluation
  17. INCLUDE: Evaluating Multilingual Language Understanding with Regional Knowledge
  18. Measuring what Matters: Construct Validity in Large Language Model Benchmarks
  19. PICLe: Pseudo-annotations for In-Context Learning in Low-Resource Named Entity Detection
  20. Positional Fragility in LLMs: How Offset Effects Reshape Our Understanding of Memorization Risks
  21. RLMEval: Evaluating Research-Level Neural Theorem Proving
  22. Reliable Evaluation and Benchmarks for Statement Autoformalization
  23. The LLM Language Network: A Neuroscientific Approach for Identifying Causally Task-Relevant Units
  24. VinaBench: Benchmark for Faithful and Consistent Visual Narratives
  25. "Flex Tape Can't Fix That": Bias and Misinformation in Edited Language Models
  26. A Design Space for Intelligent and Interactive Writing Assistants
  27. Complex Reasoning over Logical Queries on Commonsense Knowledge Graphs
  28. ConGeo: Robust Cross-View Geo-Localization Across Ground View Variations
  29. ConVQG: Contrastive Visual Question Generation with Multimodal Guidance
  30. Course Recommender Systems Need to Consider the Job Market
  31. DiffuCOMET: Contextual Commonsense Knowledge Diffusion
  32. Discovering Knowledge-Critical Subnetworks in Pretrained Language Models
  33. Exploring Defeasibility in Causal Reasoning
  34. Let Me Teach You: Pedagogical Foundations of Feedback for Language Models
  35. Making Reasoning Matter: Measuring and Improving Faithfulness of Chain-of-Thought Reasoning