arXiv AI
The Communication Bottleneck: A Round-Trip Study of Tree-Structured Expression Serialization in Language Models
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv AI
Aug 18
Structural Generalization on SLOG without Hand-Written Rules
arXiv:2604. 26157v4 Announce Type: replace-cross Abstract: Structural generalization in semantic parsing requires systems to apply learned compositional rules to novel structural combinations.
arXiv Machine Learning
Jun 25
Weave of Formal Thought
arXiv:2606. 25987v1 Announce Type: cross Abstract: Large language models (LLMs) attain remarkable surface fluency on code, yet they neither formally guarantee the syntactic validity of their output nor leverage the hierarchical structure defining the target language.
arXiv Machine Learning
Aug 12
The Parser Already Knows: Lightweight Bias Correction in Constrained Decoding
arXiv:2608. 10137v1 Announce Type: cross Abstract: Grammar Constrained Decoding (GCD) forces Language Models (LMs) to produce syntactically valid outputs by masking out non-conforming tokens at each step.
arXiv Computation and Language
1d ago
Constrained Decoding Eliminates Structural Failures in Small LLMs but Reveals a Scale-Dependent Semantic Gap
arXiv:2609.23742v1 Announce Type: new Abstract: Small open-source large language models (LLMs) in the 0.6B-4B parameter range are increasingly deployed for structured output generation (JSON, functio...
arXiv AI
Aug 7
MermaidSeqBench: An Evaluation Benchmark for NL-to-Mermaid Sequence Diagram Generation
arXiv:2511. 14967v3 Announce Type: replace-cross Abstract: Large language models (LLMs) have shown great promise in generating structured diagrams from natural language descriptions, particularly Mermaid sequence diagrams for software engineering.
arXiv AI
Jul 10
Rethinking LLM-as-a-Judge: Representation-as-a-Judge with Small Language Models via Semantic Capacity Asymmetry
arXiv:2601. 22588v2 Announce Type: replace-cross Abstract: Large language models (LLMs) are widely used as reference-free evaluators via prompting, but this "LLM-as-a-Judge" paradigm is costly, opaque, and sensitive to prompt design.