Scholar
Emanuele La Malfa
Google Scholar ID: 4_91m08AAAAJ
University of Oxford, The Alan Turing Institute
Citations & Impact
Citations
462
H-index
11
i10-index
11
Publications
20
Co-authors
23
list available
Publications
Resume (English only)
Academic Achievements
- Paper 'Large Language Models Miss the Multi-Agent Mark' accepted at NeurIPS'25 (acceptance rate ~5%)
- Paper 'Understanding the Logical Capabilities of Large Language Models via Out-of-Context Representation Learning' accepted at EMNLP'25 (Findings)
- Paper 'Fixed Point Explainability' available online as of May 2025
- Paper 'Assessing Dialect Fairness and Robustness of Large Language Models in Reasoning Tasks' accepted at ACL'25 (main conference)
- Paper 'When Claims Evolve: Evaluating and Enhancing the Robustness of Embedding Models Against Misinformation Edits' accepted at ACL'25 (Findings)
- Paper 'Language Models are Implicitly Continuous' accepted at ICLR'25
- Paper 'Language Models as a Service: Overview of a New Paradigm and its Challenges' published in JAIR and to be presented orally at AAAI'25
