arXiv Computation and Language
Making Grid Beam Search Less Greedy
Read the original on arXiv Computation and Language →The Flow has not summarised this story yet — read it at arXiv Computation and Language.
Related stories
arXiv Computation and Language
Aug 27
Beam Search, Self-Consistency, and the Limits of Inference-Time Scaling for Grammar-Constrained Text-to-SQL in Small Language Models
The paper investigates how increasing inference-time computation—via wider beam search or sample‑plus‑vote—affects performance on grammar‑constrained text‑to‑SQL tasks for small language models. Using the Qwen2.5‑Instruct family (0.5B–7B parameters) on the Spider benchmark, the authors find that larger models consistently outperform higher inference compute on the same model size, and that beam search yields better accuracy than sample‑plus‑vote under matched budgets. These results suggest that, unlike unconstrained settings, scaling inference compute does not compensate for smaller model size when strict grammar constraints are applied.
arXiv Machine Learning
Jul 9
Constrained Decoding for Diffusion Language Models via Efficient Inference over Finite Automata
arXiv:2607. 07026v1 Announce Type: new Abstract: Constrained decoding is essential for serving LLMs, ensuring that generated outputs follow specific structures such as JSON schema-formatted function calls.
arXiv AI
Jun 2
EPIC: Efficient and Parallel Inference under CFG Constraints for Diffusion Language Models
arXiv:2606. 00722v1 Announce Type: cross Abstract: Controlling language model outputs is essential for ensuring structural validity, reliability, and downstream usability, and diffusion language models are no exception.
arXiv Computation and Language
Sep 2
Suffix-Constrained Greedy Search Algorithms for Causal Language Models
arXiv:2603.01243v3 Announce Type: replace Abstract: Large language models (LLMs) are powerful tools that have found applications beyond human-machine interfaces and chatbots. Beside free-form generat...
arXiv AI
Jun 10
STORM: Stepwise Token Optimization with Reward-Guided Beam Search
arXiv:2606. 10621v1 Announce Type: cross Abstract: Modern retrieval increasingly relies on dense and learned-sparse neural models that are effective but require encoding the entire corpus into a specialized index, rebuilt whenever the model changes.
arXiv AI
Aug 7
Learning Context-Free Grammars for Grammar-Constrained Decoding via Declarative Agentic Programming with Guarantees
arXiv:2608. 05493v1 Announce Type: cross Abstract: Language models (LMs) are increasingly used to interact with external services via programs written in domain-specific languages (DSLs).