FactorSpec: Serving Exact Relational Constraints as Speculative Drafts
cs.LG, cs.AI
Submitted: 2026-11-01
Updated: 2026-11-01
Terminology
Sources
- Constrained Decoding Eliminates Structural Failures in Small LLMs but Reveals a Scale-Dependent Semantic Gap
- Accelerating Large Language Model Decoding with Speculative Sampling
- Chemical diversity of gas in distant galaxies: The metal and dust enrichment and variations within absorbing galaxies
- Correctness-Guaranteed Code Generation via Constrained Decoding
- LLM+P: Empowering Large Language Models with Optimal Planning Proficiency
- New perspectives on recent trends for Kolmogorov operators
- Speculative Decoding: Performance or Illusion?
- The Llama 3 Herd of Models
- Future Validity is the Missing Statistic: From Impossibility to $\Phi$-Estimation for Grammar-Faithful Speculative Decoding
- Qwen3 Technical Report
- The Hidden Cost of Structured Generation in LLMs: Draft-Conditioned Constrained Decoding
- Constraints Are Graphs, Not Chains: Exact Decoding for Diffusion Language Models
- AgentSpec: Speculative Decoding for Batch Inference of LLM Agents
- Efficient Guided Generation for Large Language Models
- Trie Automata for Constrained Decoding over Large Finite Sets
- $\tau$-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains
- Correctness Forensics for Batch Speculative Decoding: Diagnosing the Ragged Tensor Problem
- Decode-Time Grammars: Constrained LLM Generation over a Refinement Order of Grammar Fragments
- NATURAL PLAN: Benchmarking LLMs on Natural Language Planning
Related papers
- A Physics-Regulated Neural Framework for Learning 3D Grain Growth Dynamics
- FlexMoE: Learning One-for-All Multi-Budget Expert Pruning for Flexible MoE Deployment
- OptiMind: Improving Small Language Models for Optimization Modeling through Formulation Guidance and Multi-Turn Learning
- Staying in the Sweet Spot: Boost Reasoning Evolution via Responsive Rollout Difficulty Manipulation
- Examining the Impact of Data and Training Methods on Emergent and Subliminal Misalignment
- Rethinking Black-Box On-Policy Distillation: A Rubric-based Analysis