Get started
Author

David Demitri Africa

Observed names: Africa, David, Africa, David Demitri, Demitri Africa, David
ORCID: 0009-0005-3543-8891
Observed ORCID: 0009-0005-3543-8891
OpenAlex ID: A5119181839
Inoculation Prompting: Eliciting traits from LLMs during training can suppress them at test-time
2025 · Tan, Daniel, Woodruff, Anders, et al. · arXiv (Cornell University) · 47
PDF
No Answer Needed: Predicting LLM Answer Accuracy from Question-Only Linear Probes
2025 · Cencerrado, Iván Vicente Moreno, Masdemont, Arnau Padrés, et al. · arXiv (Cornell University) · 39
PDF
Can AI agents conduct open-ended AI research? Early evidence from two case studies
2026 · Kirgis, Peter, Kapoor, Sayash, et al. · arXiv (Cornell University) · 19
PDF
Tool Use Enables Undetectable Steganography in Multi-Agent LLM Systems
2026 · Rippin, Jimmy Laurence, Marshall, Simon C., et al. · arXiv (Cornell University) · 10
PDF
Batayan: A Filipino NLP benchmark for evaluating Large Language Models
2025 · Jann Railey Montalan, Jimson Paulo Layacan, et al. · Proceedings of the conference - Association for Computational Linguistics. Meeting · 6
PDF
Prefill Awareness in Large Language Models
2026 · Wang, Andy, Mahajan, Parv, et al. · arXiv (Cornell University) · 5
PDF
LURE: Live-Usage Replay Evaluations for Reducing Evaluation Awareness
2026 · Ivanov, Igor, Africa, David Demitri · arXiv (Cornell University) · 5
PDF
Inoculation Midtraining with Learned Neologisms
2026 · O'Brien, Kyle, Young, Edward James, et al. · arXiv (Cornell University) · 4
PDF
Consistency Training Along the Transformer Stack
2026 · Sukrati Gautam, Neil Shah, et al. · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP) · 4
PDF
Learning Dynamics of Meta-Learning in Small Model Pretraining
2025 · Africa, David Demitri, Weiss, Yuval, et al. · arXiv (Cornell University) · 4
PDF
Meta-Pretraining for Zero-Shot Cross-Lingual Named Entity Recognition in Low-Resource Philippine Languages
2025 · David Demitri Africa, Suchir Salhan, et al. · Workshop on Multilingual Representation Learning (MRL) · 4
PDF
Lag and duration of leader–follower relationships in mixed traffic using causal inference
2024 · David Demitri Africa, Ronald Benjamin Dy Quiangco, et al. · Chaos An Interdisciplinary Journal of Nonlinear Science · 4
Persona Cartography: Charting Language Model Personality Traits in Weight Space
2026 · Baines, Luke, Hawthorne, Anton Gonzalvez, et al. · arXiv (Cornell University) · 3
PDF
Consistency Training while Mitigating Obfuscation via Rate Matching
2026 · Imran, Sohaib, Gupta, Prakhar, et al. · arXiv (Cornell University) · 3
PDF
Investigating ReLoRA: Effects on the Learning Dynamics of Small Language Models
2025 · Yuval Weiss, David Demitri Africa, et al. · BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP (BlackboxNLP) · 3
PDF
Measuring Activation Control in Large Language Models
2026 · Kowalski, Marek Mateusz, Rivera, Joshua Fonseca, et al. · arXiv (Cornell University) · 2
PDF
Item Response Theory for AI Safety
2026 · Rivera, Joshua Fonseca, Shah, Neil, et al. · arXiv (Cornell University) · 2
PDF
Consistency Training Can Entrench Misalignment
2026 · Africa, David Demitri, Mani, Arathi · arXiv (Cornell University) · 2
PDF
Does Self-Evaluation Enable Wireheading in Language Models?
2025 · Africa, David Demitri, Ting, Hans Ethan · arXiv (Cornell University) · 2
PDF
Learning Modular Exponentiation with Transformers
2025 · Africa, David Demitri, Kapoor, Sara M., et al. · arXiv (Cornell University) · 2
PDF
Detecting CSAM Text-to-Image LoRAs From Weights
2026 · Africa, David Demitri, Heine, Cate, et al. · arXiv (Cornell University) · 1
PDF
Pico: A Modular Framework for Hypothesis-Driven Small Language Model Research
2025 · Martinez, Richard Diehl, Africa, David Demitri, et al. · arXiv (Cornell University) · 1
PDF
Pico: A Modular Framework for Hypothesis-Driven Small Language Model Research
2025 · Richard Diehl Martinez, David Demitri Africa, et al. · Conference on Empirical Methods in Natural Language Processing: System Demonstrations (EMNLP) · 1
PDF
Neologism Inoculation Prompting
2026 · Africa, David Demitri, Holmes, Cameron · arXiv (Cornell University)
PDF
Inter-Agent Influence: Evaluating Persuasion, Deception, and Coercion in Multi-Agent Systems
2026 · Smith, Chandler, Guo, Qi, et al. · arXiv (Cornell University)
PDF
Works count: 35
Citation count: 180
H-index: 6
I10-index: 4
Year
Topic
Type