Research map / Learning theory and algorithms / Prediction and decision losses
Learning Deterministic Weighted Automata with Queries and Counterexamples
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 WL* instead of spectral extraction | RNNs trained on UHL languages · UHL 2 | WER: 0.002 -> 0.0 | Helped |
| Use WL* instead of spectral extraction | RNNs trained on Tomita grammars · Tomita 3 | WER: 0.0071 -> 0.0 | Helped |
| Use WL* instead of spectral extraction | RNNs trained on Tomita grammars · Tomita 5 | WER: 0.0001 -> 0.0 | Helped |
| Use WL* instead of n-grams | RNNs trained on UHL languages · UHL 2 | WER: 0.12 -> 0.0 | Helped |
| Use WL* instead of n-grams | RNNs trained on SPiCe languages · SPiCe 4, 6, 7, 9, 10, 14 | WER | Hurt |
| Use WL* instead of spectral extraction | RNNs trained on SPiCe languages · SPiCe 0 | WER: 0.053 -> 0.084 | Hurt |
| Use WL* instead of spectral extraction | RNNs trained on SPiCe languages · SPiCe 2 | WER: 0.263 -> 0.08 | Helped |
| Use WL* instead of n-grams | RNNs trained on SPiCe languages · SPiCe 1, 2, 3 | WER | Helped |
Closest papers by meaning
- Constrained Decoding for Diffusion Language Models via Efficient Inference over Finite Automata (NeurIPS 2026 · similarity 0.87)
- Generalized Convergence Analysis of Tsetlin Automaton Based Algorithms: A Probabilistic Approach to Concept Learning (AAAI 2025 · similarity 0.86)
- On the Expressiveness and Length Generalization of Selective State Space Models on Regular Languages (AAAI 2025 · similarity 0.85)
- The Expressivity Boundary of Probabilistic Circuits: A Comparison with Large Language Models (NeurIPS 2026 · similarity 0.85)
- Provable Scaling Laws for the Test-Time Compute of Large Language Models (NeurIPS 2025 · similarity 0.84)
- A Probabilistic Perspective on Unlearning and Alignment for Large Language Models (ICLR 2025 · similarity 0.84)
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.