Abir Harrasse
3 papers · 2025–2026 · 3 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓
🌍
Conference Polyglot · Bronze
Top co-authors
Research topics
Keywords
llm evaluation
(1)
layer-wise analysis
(1)
mechanistic interpretability
(1)
sparse autoencoder
(1)
steering vector
(1)
adversarial framework
(1)
text-to-sql generation
(1)
fine-tuned model
(1)
activation space
(1)
multi-agent system
(1)
backdoor removal
(1)
structured debate
(1)
model circuit
(1)
autoencoder mappings
(1)
refusal of harmful prompts
(1)
Papers
Debate, Deliberate, Decide (D3): A Cost-Aware Adversarial Framework for Reliable and Interpretable LLM Evaluation
EACL 2026
Activation Space Interventions Can Be Transferred Between Large Language Models
ICML 2025
TinySQL: A Progressive Text-to-SQL Dataset for Mechanistic Interpretability Research
EMNLP 2025