Papers by Amir Abdullah
TinySQL: A Progressive Text-to-SQL Dataset for Mechanistic Interpretability Research (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing text-to-SQL datasets are too complex and noisy for rigorous interpretability analysis. |
| Approach: | They propose text-to-SQL generation as an ideal task to study mechanistic interpretability . they use edge attribution patching and sparse autoencoders to identify minimal circuits . |
| Outcome: | The proposed task combines the formal structure of toy tasks with real-world complexity. |
Beyond Linear Steering: Unified Multi-Attribute Control for Language Models (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Empirical results show that K-Steering outperforms strong baselines in accurately steering multiple behaviors. |
| Approach: | They propose a method that trains a single classifier on hidden activations and computes intervention directions via gradients at inference time. |
| Outcome: | The proposed method outperforms strong baselines in steering multiple behaviors. |
Make Mechanistic Interpretability Auditable: A Call to Develop Guidelines via Continuous Collaborative Reviewing (2026.acl-long)
Copied to clipboard
Michael Lan, Narmeen Fatimah Oozeer, Chaithanya Bandi, Philip Quirke, Austin Meek, Fazl Barez, Amir Abdullah
| Challenge: | a recent paper found conflicting conclusions for the same behavior in a neural network . authors propose auditing MI itself is essential for its application in AI safety, industry, and governance . |
| Approach: | They propose to develop a system that can audit experiments to ensure validity . authors propose to generalize good practices found on platform into expert-verified guidelines . |
| Outcome: | a new review system could be developed that can be standardized and audited . authors argue that auditing MI is essential for its application in AI safety, industry, and governance . |
PCMID: Multi-Intent Detection through Supervised Prototypical Contrastive Learning (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Existing approaches to intent detection assume that each utterance represents only a single intent. |
| Approach: | They propose a framework for intent detection that can learn multiple representations of a given user utterance under the context of different intent labels in an optimized semantic space. |
| Outcome: | The proposed framework achieves state-of-the-art on multiple public benchmark datasets and a private real-world dataset for the multi-intent detection task. |