Research map / Large language models / Language, safety and interpretability
Automata Learning and Identification of the Support of Language Models
Satwik Bhattamishra, Michael Hahn, Varun Kanade
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| use NSP continuation labels instead of binary labels (ablation) | L* · DYCK-(2,2) | samples to recover target DFA: ≈10 vs fails with 10^3 samples | Improved |
| use NSP continuation labels instead of binary labels (ablation) | L* · DYCK-(2,4) and DYCK-(4,3) | samples to recover target DFA: ≈100 vs fails with 10^3 samples | Improved |
| use NSP continuation labels instead of binary labels (ablation) | L* · Tomita grammars | states extracted | No clear effect |
| use NSP continuation labels instead of binary labels (ablation) | L* · Parity | states extracted | Improved |
Closest papers by meaning
- Representing Formal Languages: A Comparison Between Finite Automata and Recurrent Neural Networks (ICLR 2019 · similarity 0.90)
- Training Neural Networks as Recognizers of Formal Languages (ICLR 2025 · similarity 0.89)
- In-Context Language Learning: Architectures and Algorithms (ICML 2024 · similarity 0.85)
- Neural-Symbolic Recursive Machine for Systematic Generalization (ICLR 2024 · similarity 0.85)
- Towards Auto-Regressive Next-Token Prediction: In-context Learning Emerges from Generalization (ICLR 2025 · similarity 0.85)
- Bridging Expressivity and Scalability with Adaptive Unitary SSMs (NeurIPS 2025 · similarity 0.85)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
