Jérémie Dentan

Orcid: 0009-0001-5561-8030

According to our database1, Jérémie Dentan authored at least 7 papers between 2024 and 2026.

Collaborative distances:
  • Dijkstra number2 of five.
  • Erdős number3 of five.

Timeline

Legend:

Book  In proceedings  Article  PhD thesis  Dataset  Other 

Links

On csauthors.net:

Bibliography

2026
Activation Surgery: Jailbreaking White-box LLMs without Touching the Prompt.
CoRR, March, 2026

Unveiling Decision-Making in LLMs for Text Classification : Extraction of influential and interpretable concepts with Sparse Autoencoders.
Proceedings of the Findings of the Association for Computational Linguistics: EACL 2026, 2026

Guess or Recall? Training CNNs to Classify and Localize Memorization in LLMs.
Proceedings of the Fortieth AAAI Conference on Artificial Intelligence, 2026

2025
MUCH: A Multilingual Claim Hallucination Benchmark.
CoRR, November, 2025

Predicting Memorization Within Large Language Models Fine-Tuned for Classification.
Proceedings of the ECAI 2025 - 28th European Conference on Artificial Intelligence, 25-30 October 2025, Bologna, Italy, 2025

2024
Predicting and analyzing memorization within fine-tuned Large Language Models.
CoRR, 2024

Reconstructing training data from document understanding models.
Proceedings of the 33rd USENIX Security Symposium, 2024


  Loading...